Rapid and Automated Flood Segmentation through Landsat with Google Earth Engine Using Deep Learning Architecture
Bibliographic record
Abstract
To enhance flood mapping, a crucial need during natural disasters, the research introduces an AFSGDL model. Traditional mapping methods are often slow and can be biased due to their reliance on thresholds and manual input, leading to challenges like false readings caused by vegetation and active urban environments. The Rapid and Automated Flood Segmentation Through Landsat with Google Earth Engine Using Deep Learning Architecture (AFSGDL) model integrates various sources of remote sensing data, specifically utilising Sentinel-1 synthetic aperture radar (SAR) imagery and historical flood vectors from UNOSAT. Pre-processing steps employed radiometric calibration and cloud masking for improved dataset reliability and the Digital Elevation model (DEM). A hybrid deep learning model has been developed that integrates Convolutional Neural Networks (CNN) for enhanced data analysis and feature extraction performance, and a Residual Swin Transformer Block (RSTB) architecture was developed to capture both local details and broader contextual data. Specialised loss functions were created to mitigate class imbalances in flood and non- flood areas, enhancing overall segmentation accuracy. The following parameters are calculated with existing models MLRFM, INFLOS, and IOERD, compared with the AFSGDL model. Where the parameters are loss and dice, ROC curves analysis, RMSE curves analysis, water depth analysis, and velocity. The loss and dice of the AFSGDL model is 0.12 - 0.95, ROC curves analysis of 0.991, RMSE curves analysis of 0.078, water depth analysis of 13.0, and velocity analysis of 2.7.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".