Chamoli flash floods of 7th February 2021 and recent deformation: A PSInSAR and deep learning neural network (DLNN) based perspective
Bibliographic record
Abstract
The February 7, 2021, Joshimath flood scenario was one such event that caused widespread damage and led to complete washout of the many hydroelectric power projects located on the course of Dhauliganga River. The physical monitoring and mapping of such events is a difficult task that often involves deployment of labour force in inhospitable terrains. Therefore, remote sensing techniques are used for the mapping and machine learning model-based predictions for future scenarios. Synthetic Aperture RADAR (SAR) remote sensing has been widely used over the years for accurate estimation of many natural and anthropogenic disaster events. This study utilizes Persistent Scatterer SAR interferometry (PSInSAR) technique to map the surface displacement of the 2021 flood scenario and make predictions for future displacement using a Deep Learning Neural Network (DLNN) model. 16 images of both ascending and descending pass were taken for the estimation of Line of Sight (LOS) displacement velocity mapping between January 2020 and April 2021 for Tapovan area. Further, 36 images from January 2020 to December 2022, in ascending and descending passes were used for prediction and validation of future LOS surface displacement using a DLNN model for Joshimath town to see the possible impact of February 7, 2021 event. The PSInSAR LOS displacements were found to be −1.2 cm–1.2 cm between January 1, 2020 and April 14, 2021, for Tapovan region where the floods had occurred on February 7, 2021. The predicted LOS displacement was observed to be −10 cm–10 cm for December 2022 for Joshimath town. These observations clearly indicate the impact of the event to Joshimath town and as one of the causative factors of recent observations of widespread cracks in the buildings in the region.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".