A Novel Dataset for Flood Detection Robust to Seasonal Changes in Satellite Imagery
Preprint
Abstract
This study introduces a novel dataset for segmenting flooded areas in satellite images. After reviewing 77 existing benchmarks utilizing satellite imagery, we identified a shortage of suitable datasets for this specific task. To fill this gap, we collected satellite imagery of the 2019 Midwestern USA floods from Planet Explorer by Planet Labs (Image \c{opyright} 2024 Planet Labs PBC). The dataset consists of 10 satellite images per location, each containing both flooded and non-flooded areas. We selected ten locations from each of the five states: Iowa, Kansas, Montana, Nebraska, and South Dakota. The dataset ensures uniform resolution and resizing during data processing. For evaluating semantic segmentation performance, we tested state-of-the-art models in computer vision and remote sensing on our dataset. Additionally, we conducted an ablation study varying window sizes to capture temporal characteristics. Overall, the models demonstrated modest results, suggesting a requirement for future multimodal and temporal learning strategies. The dataset will be publicly available on .Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- RemoteCLIP: A Vision Language Foundation Model for Remote SensingIEEE Transactions on Geoscience and Remote Sensing, 2024
- UANet: An Uncertainty-Aware Network for Building Extraction From Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2024
- CaBuAr: California burned areas dataset for delineation [Software and Data Sets]IEEE Geoscience and Remote Sensing Magazine, 2023
- HR-GLDD: a globally distributed dataset using generalized deep learning (DL) for rapid landslide mapping on high-resolution (HR) satellite imageryEarth System Science Data, 2023
- SDSC-UNet: Dual Skip Connection ViT-Based U-Shaped Model for Building ExtractionIEEE Geoscience and Remote Sensing Letters, 2023
- Cross-domain landslide mapping from large-scale remote sensing images using prototype-guided domain-aware progressive representation learningISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Calving fronts and where to find them: a benchmark dataset and methodology for automatic glacier calving front extraction from synthetic aperture radar imageryEarth System Science Data, 2022
- Combining Deep Semantic Segmentation Network and Graph Convolutional Neural Network for Semantic Segmentation of Remote Sensing ImageryRemote Sensing, 2020