STURM-FloodDepth: A deep learning pipeline for mapping urban flood depth using street-level and oblique aerial imagery
Bibliographic record
Abstract
Flooding remains one of the most frequent and damaging natural disasters, intensified by climate change and urbanization. High-resolution real-time flood depth observations at the urban scale remain spatially sparse, thus alternative data sources are required to support risk assessment and emergency response. This study introduces STURM-FloodDepth, a deep learning pipeline to estimate and map urban flood depths using street-level and oblique aerial imagery. The workflow consists of two sequential modules: A. flood depth estimation, proceeding through vehicle detection (YOLO-World and SAHI), contextual cropping, super-resolution enhancement (EDSR), and flood level classification (fine-tuned ResNet-50); and B. georeferencing and mapping, proceeding through orthographic reference image construction, feature matching (SuperGlue), homography estimation (RANSAC), geospatial projection and mapping, conversion and export to GeoJSON. The classifier achieved AUC values ranging from 0.78 to 0.98 across all classes. Real-world qualitative validation confirmed its accuracy in operational conditions. STURM-FloodDepth is a modular, scalable, sensor-agnostic tool for urban flood monitoring, with applications for urban resilience, disaster management, and smart city. The framework is released as an open-source tool to foster further research and operational deployments.
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 | 0.001 |
| 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 | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".