Files
aimsight-labeling/auto/SNCF01.jsonl
T

89 lines
74 KiB
JSON

{"id": "SNCF01-1", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "BG.1: all its measurements are rejected, from the start of the data to the end of the batch; its curve is missing entirely. Its recognition error stays above the threshold, by day and by night, whatever the weather; on the night image its spot appears doubled. Target permanently poorly seen (orientation, installation or configuration to be checked): act on the target; no curve to read.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-2", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "F4.1: all its measurements are rejected over the batch; its curve is missing entirely. Its recognition error stays above the threshold permanently; on the images its spot is small and faint. Target permanently poorly seen: act on the target; no curve to read.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-3", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "CV.7: most of its measurements are rejected over the whole batch, its recognition error oscillating around the threshold; its curve has only scattered points, and the last ones accepted, at the end of the batch, move strongly away from its level without anything else moving. Target permanently poorly seen (by day, its spot touches the edge of a bright structure on the image): act on the target; ignore its curve.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-4", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Target issue", "description": "F4.4: most of its measurements are rejected over the whole batch, its recognition error staying stuck to the threshold; its curve has only scattered, noisy points. Faint, doubled spot on the night image. Target permanently poorly seen: act on the target; ignore its curve.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-7", "start": "2026-10-04T00:00Z", "end": "2026-11-01T00:00Z", "family": "Displacement", "description": "Over the whole batch, as one single episode, the corrected curves of many targets drift slowly, with no return: corr_y rises on BG.2, F4.5, F4.6, P4, CV.8, F4.3, P5, and drops on P1, P7, CV.1; corr_x drops on P2, P3, P4, F4.6; the drift flattens at the end of the month; part of the drop of P7, CV.1 comes from the jump of 15/10 in the morning, labelled separately. At the same time, the camera rotation drops and its tilt rises slowly, the reprojection error of the references increases and, relative to the overall movement of the targets, the positions of the targets relative to one another change more and more over the month (P1, P7, F4.5, BG.2 especially), like those of the references: the whole scene slowly deforms in the image, while the camera tilts. No temperature is available for this station (empty metrics); the cause is not established (seasonal cooling, incomplete compensation of the camera tilt, a reference that moves, or a movement of the wall). The movement of the structure is not established: to be watched.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-11-01T0000"}
{"id": "SNCF01-39", "start": "2026-10-14T07:15Z", "end": "2026-10-15T01:15Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (14/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and the night, until the camera comes to rest around one in the morning; the two-in-the-morning gap and the camera jump of the early morning, labelled separately, come after this rest. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-98", "start": "2026-10-14T09:30Z", "end": "2026-10-14T16:30Z", "family": "Visibility", "description": "By day (14/10), in the sun (hard shadows on the wall on the image of 13:00): the corrected curves of the low targets fluctuate much more than at night, from one measurement to the next, with one-measurement jumps that come back at once, mostly CV.4, CV.2, F4.3, CV.6, F4.2, BG.2, F4.5 and F4.6, and CV.2 and CV.4 are rejected at times; the night before and the evening after are calm. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the scene, by sunny day only), not visible as such on the images; some rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-99", "start": "2026-10-14T10:30Z", "end": "2026-10-14T11:00Z", "family": "Obstruction", "description": "One single measurement: CV.2, CV.4 and CV.8 are rejected, their curves are missing, the recognition error of the reference BG.3.1 jumps strongly while staying under its threshold, and CV.6, F4.2 and F4.6 make a corr jump that comes back at the next measurement. Cause: a passage in front of the bottom of the scene and of BG.3.1, deduced from the signature (several low targets and a reference hit together for one measurement; no image at that minute, the station takes one per hour). The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-41", "start": "2026-10-15T01:45Z", "end": "2026-10-15T02:45Z", "family": "No data", "description": "Two measurements are missing half an hour apart, with a single measurement between them, for all sensors, around two in the morning: all curves have a gap; the image of two o'clock exists nonetheless. The power metrics of the station are empty over the whole month. This one-measurement night gap, around 02:00 UTC, falls at the same measurement on FLORIDA and SNCF01 on 09, 14 and 15/10, and only on them; other stations have the same night gap around the same hour on other weeks (JUNGFRAU and NORDEND in early September): a common cause outside the station, at night, is probable; it is not established. Nothing to do on the station if it does not get worse.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-42", "start": "2026-10-15T05:15Z", "end": "2026-10-15T05:45Z", "family": "Displacement", "description": "One-measurement jump that lasts: on the 15th in the early morning, from one measurement to the next, the raw positions of all sensors, references included, jump together in the image (the tilt of the camera makes a step, which the pose then keeps), and the recognition error of P4, P7 and of the references R1, R2 goes up a notch. The compensation does not absorb it entirely: corr_y of P4, P5, P7, CV.1 and of the reference R1 drops at once, that of R2 rises, and these levels mostly remain on the following days. No image at that moment; cause not established (a jolt of the camera or of its mount, deduced from the pose). Relative to the overall movement, the targets move together with the camera, without moving relative to one another; the references R1 and R2 do not quite follow it, hence the remainder on the corrected curves. This is not an established movement of the structure: to be watched, on the camera and mount side.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-43", "start": "2026-10-15T08:15Z", "end": "2026-10-15T15:45Z", "family": "Visibility", "description": "By day (15/10): the corrected curves of all targets fluctuate much more than at night, from one measurement to the next, especially CV.2, CV.4, F4.2, BG.3, CV.6, CV.9, with one-measurement jumps that come back at once, and CV.2, CV.4 (sometimes F4.2) are rejected at times, their curves having gaps; their recognition error varies strongly by day. At night everything becomes calm again. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the whole scene, by day only), not visible on the images; the rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-44", "start": "2026-10-15T08:45Z", "end": "2026-10-15T22:45Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (15/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon and the evening; the night outage falls before the return. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-45", "start": "2026-10-15T22:45Z", "end": "2026-10-16T04:00Z", "family": "No data", "description": "No measurement for any sensor for several hours, on the night of 15 to 16, all curves are missing; no image either. The power metrics of the station are empty over the whole month. The gap starts at the same hour, around 23:00, on the nine stations that were measuring then (LENZSPITZE has its first measurements only in the middle of that night, WILDSTRUBEL is already stopped), and their metrics stop at the same time on most of them; measurements and metrics resume at different hours depending on the station, most in late morning. JUNGFRAU, whose metrics continue, accumulates unsent entries all night, sent in late morning, and its night measurements are nonetheless missing from the data: a common cause outside the stations (transmission or reception of the data), not an outage of the stations; it is not established. The curves are missing over the range; nothing to do on the station if it does not repeat.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-46", "start": "2026-10-16T07:00Z", "end": "2026-10-17T07:30Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (16/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and all night, until the start of the next morning. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-47", "start": "2026-10-16T08:15Z", "end": "2026-10-16T13:30Z", "family": "Visibility", "description": "By day (16/10): the corrected curves of all targets fluctuate much more than at night, from one measurement to the next, especially CV.2, CV.4, F4.2, BG.3, CV.6, CV.9, with one-measurement jumps that come back at once, and CV.2, CV.4 (sometimes F4.2) are rejected at times, their curves having gaps; their recognition error varies strongly by day. At night everything becomes calm again. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the whole scene, by day only), not visible on the images; the rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-48", "start": "2026-10-16T11:30Z", "end": "2026-10-16T12:00Z", "family": "Obstruction", "description": "CV.4 makes a very large jump in corr_x and corr_y for the time of one measurement, its raw position jumping by several pixels, while CV.2 is rejected; everything comes back at the next measurement. Cause: probably a passage hiding these low targets, the system locking onto another spot; deduced (no image at that moment). The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-49", "start": "2026-10-16T13:30Z", "end": "2026-10-16T14:00Z", "family": "No data", "description": "One measurement is missing for all sensors, all curves have a gap; no image at that moment. The power metrics of the station are empty over the whole month. The same gap occurs at the same time on the other stations that measure at that time (FLORIDA, JUNGFRAU, NORDEND): a common cause outside the station (transmission or reception of the data), not a station failure; it is not established. The curves are missing over the range; nothing to do on the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-50", "start": "2026-10-16T14:15Z", "end": "2026-10-16T14:45Z", "family": "No data", "description": "One measurement is missing for all sensors, all curves have a gap; no image at that moment. The power metrics of the station are empty over the whole month. The same gap occurs at the same time on the other stations that measure at that time (CLARIDEN, FLORIDA, LENZSPITZE, NORDEND): a common cause outside the station (transmission or reception of the data), not a station failure; it is not established. The curves are missing over the range; nothing to do on the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-100", "start": "2026-10-16T15:45Z", "end": "2026-10-16T16:15Z", "family": "Obstruction", "description": "One single measurement: the CV, F4 and P targets are rejected and their curves are missing; the references BG.3.1 and R1 are rejected too, the compensation retains none of them, and the targets that stayed under their threshold, BG.2, BG.3 and F4.5, jump strongly in corr_x and corr_y for the time of the measurement, as does the reference R2. Everything comes back at the next measurement. Cause: a train passing in front of the targets and the references, seen blurred across the whole lower scene on the 16:00 image. The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-52", "start": "2026-10-17T07:30Z", "end": "2026-10-18T07:45Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (17/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and all night, until the start of the next morning; the rejections of F4.2 that night, labelled separately, do not affect the references and do not distort the pose. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-53", "start": "2026-10-17T08:00Z", "end": "2026-10-17T16:45Z", "family": "Visibility", "description": "By day (17/10): the corrected curves of all targets fluctuate much more than at night, from one measurement to the next, especially CV.2, CV.4, F4.2, BG.3, CV.6, CV.9, with one-measurement jumps that come back at once, and CV.2, CV.4 (sometimes F4.2) are rejected at times, their curves having gaps; their recognition error varies strongly by day. At night everything becomes calm again. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the whole scene, by day only), not visible on the images; the rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-54", "start": "2026-10-17T09:45Z", "end": "2026-10-17T10:15Z", "family": "Obstruction", "description": "CV.2 makes a very large jump in corr_x and corr_y for the time of one measurement, its raw position jumping by several pixels: another spot was taken for the target; CV.4 is rejected; everything comes back at the next measurement. Cause: a blurry, bright object passes in front of the bottom of the scene and hides CV.2 and CV.1, seen on the 10:00 image (thumbnails). The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-101", "start": "2026-10-18T07:45Z", "end": "2026-10-18T15:45Z", "family": "Visibility", "description": "By day (18/10): the corrected curves of all targets fluctuate much more than at night, from one measurement to the next, especially CV.2, CV.4, F4.2, BG.3, CV.6, CV.9, with one-measurement jumps that come back at once, and CV.2, CV.4 (sometimes F4.2) are rejected at times, their curves having gaps; their recognition error varies strongly by day. At night everything becomes calm again. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the whole scene, by day only), not visible on the images; the rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-56", "start": "2026-10-18T07:45Z", "end": "2026-10-19T00:00Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (18/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and the evening. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-59", "start": "2026-10-18T20:00Z", "end": "2026-10-18T20:30Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, no image at that moment; deduced from the signature, the same as that of the trains seen on the images of the other passages. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-102", "start": "2026-10-19T07:15Z", "end": "2026-10-20T12:45Z", "family": "Displacement", "description": "On 19/10, an overcast day (images of 08:00 and 13:00, no sun on the wall), the camera moves in the morning and does not come back: its pan and tilt drop and its scale rises, then stay at their new level in the afternoon and at night, until the outage of 20/10. At the same time the targets move apart from each other in the image (residual relative to the overall movement): corr_x of P5, P6 and P7 rises and that of P2 drops clearly, and corr_y of P5 rises, through the afternoon and the night, while the residual of the compensation rises from late morning and the recognition error of the reference R1 from the late afternoon. No return before the outage; after it, on 21/10, P2 and P5 are still near their new levels. Not the daily thermal cycle: no sun, the pose does not come back, no temperature is available. Cause not established (a camera or reference movement that the compensation does not follow, or a movement of the scene). Movement of the structure not established: to monitor; part of the month-long drift labelled separately.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-61", "start": "2026-10-19T09:00Z", "end": "2026-10-19T10:15Z", "family": "No data", "description": "Several consecutive measurements are missing for all sensors, for an hour, all curves are missing; no image either. The power metrics of the station are empty over the whole month. The same gap occurs at the same time on the other stations that measure at that time (CLARIDEN, FLORIDA, JUNGFRAU, LENZSPITZE, NIEDERHORN, NORDEND): a common cause outside the station (transmission or reception of the data), not a station failure; it is not established. The curves are missing over the range; nothing to do on the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-63", "start": "2026-10-19T20:45Z", "end": "2026-10-19T21:15Z", "family": "No data", "description": "One measurement is missing for all sensors, all curves have a gap; no image at that moment. The power metrics of the station are empty over the whole month. The same gap occurs at the same time on the other stations that measure at that time (CLARIDEN, FLORIDA, JUNGFRAU, LENZSPITZE, NIEDERHORN, NORDEND): a common cause outside the station (transmission or reception of the data), not a station failure; it is not established. The curves are missing over the range; nothing to do on the station. The hourly metrics of BREITHORN, MICHIGAN and NEBRASKA are also missing at 21:00.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-103", "start": "2026-10-20T04:45Z", "end": "2026-10-20T08:00Z", "family": "Visibility", "description": "At night on 20/10, before dawn, the reference R1 is less well seen: its recognition error rises a notch at once and stays high until mid-morning, and its measured position slides alone in the image (the targets do not move relative to the overall movement). The compensation follows it: corr_y of P7, P6 and P5 rises together clearly for a few hours, while the reference R2 moves the other way, then everything comes back as the position of R1 returns, around eight. The train passage of that morning, labelled separately, falls inside. Nothing in front of R1 on the night images of 05:00, 06:00 and 07:00 (its spot whole, same place); the night is one of poor visibility for several faint targets (CV.6 rejected all night, F4.2 at times). Cause deduced: the reference less well seen in the night of poor visibility, not an obstacle. Do not trust the small shift of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-104", "start": "2026-10-20T05:30Z", "end": "2026-10-20T06:00Z", "family": "Obstruction", "description": "One single measurement: the CV, F4 and P targets are rejected and their curves are missing; the references BG.3.1 and R1 are rejected too, the compensation retains none of them, and the targets that stayed under their threshold, BG.2, BG.3, F4.5 and F4.6, jump strongly in corr_x and corr_y for the time of the measurement, as does the reference R2. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, deduced from the signature, the same as that of the train seen on the 16:00 image of 16/10 (no image at that minute). It falls inside the episode of the reference R1 of that morning, labelled separately. The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-66", "start": "2026-10-20T12:45Z", "end": "2026-10-21T10:00Z", "family": "No data", "description": "Measurements are missing intermittently, then an outage of about twenty hours. No measurement for any sensor, all curves are missing; no image either. The power metrics of the station are empty over the whole month: the cause is not established (acquisition, power or transmission). If long outages repeat, check the power and the transmission of the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-67", "start": "2026-10-21T10:00Z", "end": "2026-10-21T15:45Z", "family": "Visibility", "description": "By day (21/10): the corrected curves of all targets fluctuate much more than at night, from one measurement to the next, especially CV.2, CV.4, F4.2, BG.3, CV.6, CV.9, with one-measurement jumps that come back at once, and CV.2, CV.4 (sometimes F4.2) are rejected at times, their curves having gaps; their recognition error varies strongly by day. At night everything becomes calm again. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the whole scene, by day only), not visible on the images; the rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-105", "start": "2026-10-21T10:00Z", "end": "2026-10-21T19:30Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (21/10, sunny, between two measurement outages): in late morning the pan of the camera drops and its scale rises, then the camera comes back in the afternoon and its tilt rises in the evening. The compensation absorbs most of it, but not all: in the late afternoon and the evening, with the tilt rising, corr_x of P5 and P7 dips clearly below its level of the morning, then they come back at the isolated measurement after the gap. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-69", "start": "2026-10-21T19:30Z", "end": "2026-10-22T10:30Z", "family": "No data", "description": "Night outage, one single isolated measurement at the start. No measurement for any sensor, all curves are missing; no image either. The power metrics of the station are empty over the whole month: the cause is not established (acquisition, power or transmission). If long outages repeat, check the power and the transmission of the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-14T0645_2026-10-22T1030"}
{"id": "SNCF01-106", "start": "2026-10-04T08:45Z", "end": "2026-10-04T16:30Z", "family": "Visibility", "description": "By day (04/10), sunny day (cast shadows on the wall on the image of 12:00): the corrected curves of the low targets fluctuate from one measurement to the next beyond their noise, mostly CV.4 (corr_x and corr_y), F4.2, BG.2, BG.3, with one-measurement jumps that come back at once; late in the morning, BG.3, F4.2, BG.2 and the P targets jump together in corr_x for one measurement; CV.2 and CV.4 are rejected at times (missing points). At night everything is calm again. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast, which makes the spots tremble (a fast noise, by day only, with the recognition error of these low targets rising), nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-9", "start": "2026-10-04T09:00Z", "end": "2026-10-05T06:30Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (04/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and all night, until the start of the next morning. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-10", "start": "2026-10-05T06:30Z", "end": "2026-10-06T07:15Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (05/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and all night, until the start of the next morning. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-107", "start": "2026-10-05T07:00Z", "end": "2026-10-05T15:15Z", "family": "Visibility", "description": "By day (05/10), sunny day (cast shadows on the image of 12:00): the corrected curves of the low targets fluctuate from one measurement to the next beyond their noise, the most strongly of the batch: CV.4 and CV.2 in both columns, F4.2, BG.3, and in late morning the corr_y of P1, P2, P3 jump together for one or two measurements; CV.2, CV.4 and F4.2 are rejected at times (missing points). Calm again before nightfall; the train of 16:00 is labelled apart. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast, which makes the spots tremble (a fast noise, by day only, with the recognition error of these low targets rising), nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-12", "start": "2026-10-05T15:45Z", "end": "2026-10-05T16:15Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, a train passing, blurred, in front of the wall and the targets, seen on the 16:00 image. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-108", "start": "2026-10-06T07:00Z", "end": "2026-10-06T13:15Z", "family": "Visibility", "description": "By day (06/10), sunny morning (cast shadows on the image of 12:00): the corrected curves of the low targets fluctuate beyond their noise, mostly CV.4 in corr_x, F4.2 in both columns and CV.2, with one-measurement jumps that come back at once; CV.2 and CV.4 are rejected at times (missing points). The other targets stay within their noise; calm again from early afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast, which makes the spots tremble (a fast noise, by day only, with the recognition error of these low targets rising), nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-109", "start": "2026-10-06T07:15Z", "end": "2026-10-07T03:00Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (06/10), sunny day (cast shadows on the image of 12:00): from the morning, the pan and the tilt of the camera drop strongly and its scale rises, until early afternoon; they come back slowly in the afternoon, the evening and the first half of the night. The compensation absorbs only part of it: corr_x of P7 rises clearly, with corr_y of P6 and P7, while corr_x of P1 drops and that of P5 rises; the curves come back to their night level late in the evening, the pose in the night. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-110", "start": "2026-10-07T07:30Z", "end": "2026-10-08T04:15Z", "family": "Thermal displacement", "description": "Weak daytime thermal cycle (07/10), overcast day (image of 12:00): in the morning, the pan and the tilt of the camera drop a little and its scale rises a little, then the camera stays in that position all afternoon; it comes back in the evening and all night, beyond its position of the previous night, until early on the 8th. The corrected curves follow, less than on the sunny days: corr_x of P5 and P7 rises, corr_y of P7 and P6 too, corr_x of P1 drops; P7 comes back late in the evening, P5 only after midnight. The three train passages of the day (13:00, 16:00, 19:45) are labelled apart. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-111", "start": "2026-10-07T12:45Z", "end": "2026-10-07T13:15Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 except F4.5 and F4.6, and all the P) are rejected and their curves are missing; the references are affected too (R1 rejected, BG.3.1 just under its threshold and left out), the compensation retains none of them; the targets that stayed under the threshold jump a little beyond their noise, BG.3 in corr_x, F4.5 and F4.6 in corr_y. Everything comes back at the next measurement. Cause seen: a train passing in front of the wall and the targets, blurred, on the image of 13:00. The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-18", "start": "2026-10-07T15:45Z", "end": "2026-10-07T16:15Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, a train passing in front of the targets, seen on the 16:00 image. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-19", "start": "2026-10-07T19:30Z", "end": "2026-10-07T20:00Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, no image at that moment; deduced from the signature, the same as that of the trains seen on the images of the other passages. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-20", "start": "2026-10-08T06:45Z", "end": "2026-10-08T16:30Z", "family": "Visibility", "description": "By day (08/10): the corrected curves of all targets fluctuate much more than at night, from one measurement to the next, especially CV.2, CV.4, F4.2, BG.3, CV.6, CV.9, with one-measurement jumps that come back at once, and CV.2, CV.4 (sometimes F4.2) are rejected at times, their curves having gaps; their recognition error varies strongly by day. At night everything becomes calm again. Deduced cause: heat shimmer from the air heated above the tracks (a fast noise over the whole scene, by day only), not visible on the images; the rejections of CV.2 and CV.4, low targets, may also come from passages, not seen. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-21", "start": "2026-10-08T08:15Z", "end": "2026-10-09T04:30Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (08/10), weak by day and prolonged at night: from the morning, the pan and the tilt of the camera drop a little and its scale rises; in the evening, the camera rises beyond its position of the previous night and comes back to it only on the morning of the 9th. The corrected curves follow, poorly compensated: corr_y of P5, P6, P7, P4 moves away from its night level during the day; in the evening and at night, corr_x of P1, P5, P6, P7 exceeds its level of the previous night in the other direction, until the morning of the 9th. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-22", "start": "2026-10-09T01:45Z", "end": "2026-10-09T02:15Z", "family": "No data", "description": "One measurement is missing, for all sensors, around two in the morning: all curves have a gap; no image at that moment. The power metrics of the station are empty over the whole month. This one-measurement night gap, around 02:00 UTC, falls at the same measurement on FLORIDA and SNCF01 on 09, 14 and 15/10, and only on them; other stations have the same night gap around the same hour on other weeks (JUNGFRAU and NORDEND in early September): a common cause outside the station, at night, is probable; it is not established. Nothing to do on the station if it does not get worse.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-23", "start": "2026-10-09T07:00Z", "end": "2026-10-10T06:00Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (09/10), with no return in the evening: in the morning, the pan and the tilt of the camera drop and its scale rises, then the camera stays in that position all afternoon and evening; it comes back only slowly during the night, on the morning of the 10th. The corrected curves follow, poorly compensated: corr_x of P1, P2, P5, P6, P7 moves away from its night level during the day, stays away in the evening and comes back only on the morning of the 10th. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-25", "start": "2026-10-10T01:45Z", "end": "2026-10-10T02:15Z", "family": "No data", "description": "One measurement is missing, for all sensors, around two in the morning: all curves have a gap; the image of that moment exists nonetheless. The power metrics of the station are empty over the whole month. This one-measurement night gap, around 02:00 UTC, falls at the same measurement on FLORIDA and SNCF01 on 09, 14 and 15/10, and only on them (that night, on SNCF01 alone); other stations have the same night gap around the same hour on other weeks (JUNGFRAU and NORDEND in early September): a common cause outside the station, at night, is probable; it is not established. Nothing to do on the station if it does not get worse.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-26", "start": "2026-10-10T07:00Z", "end": "2026-10-11T08:30Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (10/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and all night, until the start of the next morning. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-112", "start": "2026-10-10T07:00Z", "end": "2026-10-10T13:00Z", "family": "Visibility", "description": "By day (10/10), sunny morning (cast shadows on the image of 12:00): the corrected curves of the low targets fluctuate beyond their noise, mostly CV.4 in both columns, CV.9 and CV.2 in corr_y, F4.2 and F4.5, and in mid-morning BG.3, P2, P3 jump together in corr_x for one measurement; they come back at once. Calm again from early afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast, which makes the spots tremble (a fast noise, by day only, with the recognition error of these low targets rising), nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-113", "start": "2026-10-11T10:00Z", "end": "2026-10-11T15:30Z", "family": "Visibility", "description": "By day (11/10), overcast day (image of 12:00), the weakest agitation of the batch that still crosses the noise: CV.4 in corr_y, F4.2, CV.2, and P1, P2 in corr_y make a few one-measurement jumps just beyond their noise, coming back at once; the train of 14:15 is labelled apart. Calm at night. Deduced cause: a weak shimmer of the air above the tracks by day, the same signature as on the sunny days, much weaker; nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-114", "start": "2026-10-11T08:30Z", "end": "2026-10-12T02:45Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (11/10), overcast day (image of 12:00): from the morning, the pan and the tilt of the camera drop and its scale rises, until early afternoon; they come back in the late afternoon, the evening and the first half of the night, beyond their position of the previous night. The compensation absorbs part of it: corr_x of P7 rises clearly, with corr_y of P6 and P5, while corr_x of P1 drops; the curves are back at their night level in the evening, the pose in the night. The train of 14:15 is labelled apart. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-115", "start": "2026-10-11T14:00Z", "end": "2026-10-11T14:30Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and all the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold, BG.2, BG.3 and F4.5, jump strongly in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references; the camera takes its image on the hour, none at that measurement; deduced from the signature, the same as that of the trains seen on the images of the other passages. The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-116", "start": "2026-10-12T06:30Z", "end": "2026-10-12T07:00Z", "family": "Obstruction", "description": "One single measurement, early in the morning: CV.8 and F4.2 go above their threshold (CV.6 too), their curves are missing, and the recognition error of most CV and F4 targets and of the reference BG.3.1 rises; CV.4, left under its threshold with its recognition error dropping, jumps clearly in corr_x for that measurement, and comes back at the next one. The references hold, the other targets stay within their noise. Cause deduced from the signature: a partial passage in front of the low targets, CV.4 latching onto a light or a reflection; no image at that measurement (the camera takes one on the hour). The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-117", "start": "2026-10-12T07:30Z", "end": "2026-10-12T14:45Z", "family": "Visibility", "description": "By day (12/10), sunny day (cast shadows on the image of 12:00): the corrected curves of the low targets fluctuate beyond their noise, mostly CV.4 in both columns, F4.2, CV.2, F4.5, F4.6, and in mid-morning BG.3, F4.2, F4.6, P2, P3, P4, P6 jump together in corr_x for one measurement; they come back at once; CV.2 and CV.4 are rejected at times (missing points). Calm again in the afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast, which makes the spots tremble (a fast noise, by day only, with the recognition error of these low targets rising), nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-33", "start": "2026-10-12T08:00Z", "end": "2026-10-14T04:00Z", "family": "Thermal displacement", "description": "Thermal cycle of 12 and 13/10, as one single episode: on the 12th, from the morning, the pan and the tilt of the camera drop and its scale rises; during the night from 12 to 13, the camera comes back only in part, and the corrected curves do not come back: corr_x of P1, P5, P6, P7 and corr_y of P4, P5, P6, P7 stay away from their night level all night, while the recognition error of the P rises a little; on the 13th, a second daytime dip is added to it, then everything comes back on the evening of the 13th and during the night, on the morning of the 14th. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the night without return is not explained, no temperature being available. Nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-118", "start": "2026-10-12T15:45Z", "end": "2026-10-12T16:15Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and all the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold, BG.2, BG.3 and F4.5, jump strongly in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause seen: a train passing in front of the wall and the targets, blurred, on the image of 16:00. The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-35", "start": "2026-10-13T01:45Z", "end": "2026-10-13T02:15Z", "family": "No data", "description": "One measurement is missing, for all sensors, around two in the morning: all curves have a gap; no image at that moment. The power metrics of the station are empty over the whole month. This one-measurement night gap, around 02:00 UTC, falls at the same measurement on FLORIDA and SNCF01 on 09, 14 and 15/10, and only on them (that night, on SNCF01 alone); other stations have the same night gap around the same hour on other weeks (JUNGFRAU and NORDEND in early September): a common cause outside the station, at night, is probable; it is not established. Nothing to do on the station if it does not get worse.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-119", "start": "2026-10-13T07:45Z", "end": "2026-10-13T14:00Z", "family": "Visibility", "description": "By day (13/10), sun and clouds (image of 12:00): the corrected curves of the low targets fluctuate beyond their noise, mostly CV.4 in corr_x, F4.2, F4.6, CV.2, and around midday P1, P2 and F4.2 jump together in corr_x for one measurement; they come back at once. Calm again in the afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast, which makes the spots tremble (a fast noise, by day only, with the recognition error of these low targets rising), nothing in front of the targets on the images. Do not trust the small movements of these curves over the range; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-37", "start": "2026-10-14T01:15Z", "end": "2026-10-14T01:45Z", "family": "No data", "description": "One measurement is missing, for all sensors, around two in the morning: all curves have a gap. The power metrics of the station are empty over the whole month. This one-measurement night gap, around 02:00 UTC, falls at the same measurement on FLORIDA and SNCF01 on 09, 14 and 15/10, and only on them; other stations have the same night gap around the same hour on other weeks (JUNGFRAU and NORDEND in early September): a common cause outside the station, at night, is probable; it is not established. Nothing to do on the station if it does not get worse.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-04T0000_2026-10-14T0645"}
{"id": "SNCF01-70", "start": "2026-10-22T10:30Z", "end": "2026-10-22T13:30Z", "family": "No data", "description": "Between two outages, on 22/10 in late morning, measurements are missing intermittently: only a few isolated measurements arrive. No measurement for any sensor between them, all curves are missing; no image either. The power metrics of the station are empty over the whole month: the cause is not established (acquisition, power or transmission). If long outages repeat, check the power and the transmission of the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-120", "start": "2026-10-22T10:30Z", "end": "2026-10-22T15:30Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (22/10), over a few measurements between outages, under an overcast sky (13:30 and 14:00 images): the pan of the camera is low and its scale high until early afternoon, at their extreme at 13:30, then they begin to come back at the isolated 15:30 measurement, the tilt staying low. The corrected curves keep it: the corr_x of P5 and P7 and the corr_y of P6 stay clearly above their level of the previous evening all day, flat, and P7 starts to come back at 15:30, when the corrections of the references also shift a little. Deduced cause: the camera and its mount move with the heat of the day (camera pose), the compensation absorbing only part of it; the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-73", "start": "2026-10-22T15:00Z", "end": "2026-10-25T08:30Z", "family": "No data", "description": "One measurement is missing on 22/10 in the afternoon, then, after a single isolated measurement, an outage of nearly three days, until the morning of 25/10. No measurement for any sensor, all curves are missing; no image either. The power metrics of the station are empty over the whole month: the cause is not established (acquisition, power or transmission). If long outages repeat, check the power and the transmission of the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-121", "start": "2026-10-25T08:30Z", "end": "2026-10-25T13:15Z", "family": "Visibility", "description": "By day (25/10, from the resumption of the measurements), in the sun (sunny morning with passing clouds on the images of 09:00 to 13:00, sharp shadows on the wall): the corrected curves of the targets fluctuate from one measurement to the next much more than at night, with one-measurement jumps that come back at once, above all CV.4, F4.2, F4.6, CV.9 and P1, and the noisy F4.3;; CV.2 and CV.4 are rejected at times, their curves having gaps. The recognition error of most sensors, the references included, varies strongly from one measurement to the next, which it does not do at night nor on the overcast days (22/10, 26/10), when the curves stay calm. The jumps stop after 13:00, when the sky clouds over (14:00 image). Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast making the spots tremble (a fast noise over the whole scene, sunny hours only), not a nuisance seen on the images. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-75", "start": "2026-10-25T08:30Z", "end": "2026-10-25T22:15Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (25/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon and the evening; measurements resumed in the morning after the outage. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-122", "start": "2026-10-25T23:30Z", "end": "2026-10-26T00:00Z", "family": "Obstruction", "description": "At night (25/10 23:45), for the time of one measurement, the CV targets (CV.1, CV.2, CV.4, CV.5, CV.8, CV.9) and F4.2 are rejected together, their curves are missing; the recognition error of the references BG.3.1 and R1 and of P5 and P7 rises without crossing the threshold, and P7, left under its threshold, jumps clearly in corr_x for that measurement: its point is wrong. The other targets do not move; everything comes back at the next measurement. Cause: probably a passage in front of this part of the scene, deduced from the signature (no image at that moment, the images being on the hour). The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-123", "start": "2026-10-26T08:15Z", "end": "2026-10-26T22:00Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (26/10), under an overcast sky (12:00 image): from the morning, the pan and the tilt of the camera drop and its scale rises, less than on the sunny days, with no return before the 22:00 outage: the pan keeps dropping in the evening. The corrected curves keep part of it: the corr_x of P7 and P5 move clearly away from their night level during the day, P7 most at 10:00 when the tilt drops at once; in the evening they move further, during the episode labelled separately (Visibility). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-78", "start": "2026-10-26T14:30Z", "end": "2026-10-26T15:15Z", "family": "No data", "description": "Two measurements are missing for all sensors, all curves are missing; no image either. The power metrics of the station are empty over the whole month. The same gap occurs at the same time on the other stations that measure at that time (CLARIDEN, FLORIDA, JUNGFRAU, LENZSPITZE, NIEDERHORN, NORDEND), and their metrics are also missing at the same minutes: a common cause outside the station (transmission or reception of the data), not a station failure; it is not established. The curves are missing over the range; nothing to do on the station. The hourly metrics of BREITHORN, MICHIGAN and NEBRASKA are also missing at 15:00.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-124", "start": "2026-10-26T15:15Z", "end": "2026-10-26T22:00Z", "family": "Visibility", "description": "In late afternoon and in the evening (26/10), from the resumption after the common gap of 15:00 until the 22:00 outage: the corr_x of P5 and P6 and the corr_y of P6 rise steadily and clearly, while the corr_y of P4, P3, P1 and the corr_x of P1 go down, instead of coming back as on the other evenings; the camera pose does not come back either (the pan drops, the scale rises again) and the registration residual is at its highest of the range. From 17:00 the recognition error of the reference R2, of BG.3.1 and of P1, P3, CV.1, F4.2 rises markedly; F4.2 then CV.8 are rejected for a while, and at 18:15 most CV and F4 targets rise together. The night images of 16:00 to 21:00 show nothing clear, the scene as on the night before. After the outage, on 28/10, the curves are back at their level. Cause not established: references less well seen (a visibility drop over the scene is likely) that skew the compensation. Do not trust the curves over the range.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-80", "start": "2026-10-26T22:00Z", "end": "2026-10-28T07:15Z", "family": "No data", "description": "Outage of more than a day, with a single isolated measurement on 27/10 at 14:00. No measurement for any sensor, all curves are missing; no image either. The power metrics of the station are empty over the whole month: the cause is not established (acquisition, power or transmission). If long outages repeat, check the power and the transmission of the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-82", "start": "2026-10-28T07:30Z", "end": "2026-10-28T22:45Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (28/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon and the evening; measurements resumed in the morning after the outage. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-125", "start": "2026-10-28T08:00Z", "end": "2026-10-28T14:45Z", "family": "Visibility", "description": "By day (28/10), in the sun (full sun on the 12:00 image, sharp shadows on the wall): the corrected curves of the targets fluctuate from one measurement to the next much more than at night, with one-measurement jumps that come back at once, above all CV.4 and CV.2, then P2, P3 and CV.1;; CV.2 and CV.4 are rejected at times, their curves having gaps. The recognition error of most sensors, the references included, varies strongly from one measurement to the next, which it does not do at night nor on the overcast days (22/10, 26/10), when the curves stay calm. The jumps start in mid-morning, once the sun is on the scene, and stop in mid-afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast making the spots tremble (a fast noise over the whole scene, sunny hours only), not a nuisance seen on the images. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-83", "start": "2026-10-28T10:15Z", "end": "2026-10-28T10:45Z", "family": "Obstruction", "description": "CV.2 makes a very large jump in corr_x and corr_y for the time of one measurement, its raw position jumping by several pixels: another spot was taken for the target; CV.4 is rejected; everything comes back at the next measurement. Cause: probably a passage, like on 17/10 at 10:00; deduced (no image at that moment). The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-84", "start": "2026-10-28T21:00Z", "end": "2026-10-28T21:30Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, no image at that moment; deduced from the signature, the same as that of the trains seen on the images of the other passages. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-85", "start": "2026-10-28T22:30Z", "end": "2026-10-28T23:00Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, no image at that moment; deduced from the signature, the same as that of the trains seen on the images of the other passages. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-126", "start": "2026-10-29T07:45Z", "end": "2026-10-29T23:15Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (29/10), sunny day (12:00 image): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon and the evening, the pan reaching its night level late in the evening. The corrected curves follow the same cycle, poorly compensated: the corr_y of P5 and P6 and the corr_x of P7, P6 and P5 move clearly away from their night level during the day, then come back gradually in the evening. Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-127", "start": "2026-10-29T10:45Z", "end": "2026-10-29T15:30Z", "family": "Visibility", "description": "By day (29/10), in the sun (full sun on the 12:00 image, sharp shadows on the wall): the corrected curves of the targets fluctuate from one measurement to the next much more than at night, with one-measurement jumps that come back at once, above all CV.4, F4.2, CV.6, BG.3 and BG.2;; CV.2 and CV.4 are rejected at times, their curves having gaps. The recognition error of most sensors, the references included, varies strongly from one measurement to the next, which it does not do at night nor on the overcast days (22/10, 26/10), when the curves stay calm. The jumps start late in the morning and stop in mid-afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast making the spots tremble (a fast noise over the whole scene, sunny hours only), not a nuisance seen on the images. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-88", "start": "2026-10-29T14:45Z", "end": "2026-10-29T15:15Z", "family": "No data", "description": "One measurement is missing for all sensors, all curves have a gap, although the 15:00 image exists. The power metrics of the station are empty over the whole month. The same gap occurs at the same time on the other stations that measure at that time (CLARIDEN, LENZSPITZE, NORDEND): a common cause outside the station (transmission or reception of the data), not a station failure; it is not established. The curves are missing over the range; nothing to do on the station.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-89", "start": "2026-10-30T08:00Z", "end": "2026-10-31T07:45Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (30/10): from the morning, the pan and the tilt of the camera drop and its scale rises, then they slowly come back in the afternoon, the evening and all night, until the start of the next morning. The corrected curves follow the same cycle, poorly compensated: corr_x of P7, P5, P6 and corr_y of P5, P6, P7, P4 move away from their night level during the day then come back, partly all at once at nightfall, when the recognition error also comes back (the lighting plays a part). Deduced cause: the camera and its mount move with the heat of the day (camera pose); the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-128", "start": "2026-10-30T09:15Z", "end": "2026-10-30T15:30Z", "family": "Visibility", "description": "By day (30/10), in the sun (full sun on the 12:00 image, sharp shadows on the wall): the corrected curves of the targets fluctuate from one measurement to the next much more than at night, with one-measurement jumps that come back at once, above all CV.2, then F4.2, CV.6, F4.6, F4.5 and CV.4;; CV.2 and CV.4 are rejected at times, their curves having gaps. The recognition error of most sensors, the references included, varies strongly from one measurement to the next, which it does not do at night nor on the overcast days (22/10, 26/10), when the curves stay calm. The jumps start in mid-morning and stop in mid-afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast making the spots tremble (a fast noise over the whole scene, sunny hours only), not a nuisance seen on the images. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-91", "start": "2026-10-30T17:45Z", "end": "2026-10-30T18:15Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, a lit train passing: on the 18:00 night image, most of the spots have disappeared and large bright spots appear. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-92", "start": "2026-10-30T18:15Z", "end": "2026-10-30T18:45Z", "family": "Obstruction", "description": "One single measurement: most targets (the CV, the F4 and some of the P) are rejected and their curves are missing; the references are affected too (BG.3.1 and R1 rejected), the compensation retains none of them, and the targets that stayed under the threshold (BG.2, BG.3, F4.5 and some P) jump in corr_x and corr_y for the time of the measurement. Everything comes back at the next measurement. Cause: a passage in front of the targets and the references, no image at that moment; deduced from the signature, the same as that of the trains seen on the images of the other passages. The structure is not moving: point to ignore, nothing to do.", "review": "2026-11-17", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-129", "start": "2026-10-30T21:15Z", "end": "2026-10-30T22:00Z", "family": "Obstruction", "description": "Two measurements, at night (30/10): at 21:30, CV.2 is rejected, its curve is missing; the recognition error of the reference BG.3.1 rises markedly without crossing its threshold, the camera pose jumps (pan), and P3 clearly, P1 and BG.3 a little, jump in corr_x for the time of the measurement. At 21:45, F4.2 is rejected alone, its curve is missing; everything then comes back. Cause: probably a passage in front of the bottom of the scene and the reference BG.3.1, deduced from the signature, weaker than that of the trains (no image at that moment, the images being on the hour). The structure is not moving: point to ignore, nothing to do.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-130", "start": "2026-10-31T07:45Z", "end": "2026-11-01T00:00Z", "family": "Thermal displacement", "description": "Daytime thermal cycle (31/10), sunny day (12:00 and 13:00 images): from the morning, the pan and the tilt of the camera drop and its scale rises; at 12:30 the tilt also makes a step, labelled separately (Displacement). In the afternoon and the evening the pan and the scale come back slowly, the tilt only partly. The corrected curves follow the cycle, poorly compensated: the corr_y of P6, P5 and P4 and the corr_x of P7 and P5 move clearly away from their night level during the day; in the evening P7 comes back, but the corr_y of P6 and P5 stays clearly above its level of the previous nights until the end of the range. Deduced cause: the camera and its mount move with the heat of the day (camera pose), plus the step of the camera; the structure, a masonry wall, is not supposed to move like that. No temperature is available to confirm it. Normal, nothing to do; see the step of 12:30.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-131", "start": "2026-10-31T08:15Z", "end": "2026-10-31T16:00Z", "family": "Visibility", "description": "By day (31/10), in the sun (full sun on the 12:00 and 13:00 images, sharp shadows on the wall): the corrected curves of the targets fluctuate from one measurement to the next much more than at night, with one-measurement jumps that come back at once, above all CV.4, P2, CV.2 and P1, then BG.3 and F4.2;; CV.2 and CV.4 are rejected at times, their curves having gaps. The recognition error of most sensors, the references included, varies strongly from one measurement to the next, which it does not do at night nor on the overcast days (22/10, 26/10), when the curves stay calm. The jumps start in the morning and stop in late afternoon. Deduced cause: heat shimmer, the air heated by the sun above the tracks and the ballast making the spots tremble (a fast noise over the whole scene, sunny hours only), not a nuisance seen on the images. Do not trust the small movements of these curves by day; this is not a movement of the structure.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}
{"id": "SNCF01-132", "start": "2026-10-31T12:15Z", "end": "2026-10-31T12:45Z", "family": "Displacement", "description": "Step of the camera at 12:30 on 31/10, in full sun (12:00 and 13:00 images): the tilt of the camera jumps at once, far more steeply than in its daily cycle, and all the sensors, references and targets, shift together in the image; the targets move relative to each other only a little. The compensation does not erase it all: the corr_y of P6, P7, P5 and P3 steps up clearly at that measurement and stays there all afternoon. The tilt does not come back to its earlier night level, and the corr_y of P6 and P5 stays clearly above its level of the previous nights until the end of the range; at 17:00 the corrections of the references BG.3.1, R1 and R2 also shift relative to each other and stay. Cause not established (the camera or its mount moving in the sun is likely). It is not a movement of the structure; the camera is to be monitored, and the level of the following nights checked.", "analysis": "SNCF01_2026-10-22T1030_2026-11-01T0000"}