SOTAVerified

Flood extent forecasting

Flood extent forecasting is the task of predicting a binary 2D flood extent map (water vs no water), given input drivers and forcings. The focus is specifically on the impact and extent modeling, such that e.g. atmosphere state (such as precipitation) may be assumed as inputs, to disentangle the impact modeling from upstream challenges such as weather forecasting. This is complementary to time series forecasting of river streamflow and runoff, as well as post-hoc mapping of floods. For related work, data & benchmarks, see https://arxiv.org/abs/2409.18591.

Papers

Showing 15 of 5 papers

TitleStatusHype
Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation ForecastingCode1
MaxViT-UNet: Multi-Axis Attention for Medical Image SegmentationCode1
Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing DataCode1
Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention NetworksCode1
Semantic segmentation of crop type in Africa: A novel dataset and analysis of deep learning methodsCode0
Show:102550

No leaderboard results yet.