NDWS Wildfire Spread Prediction

Tools

• NDWS_Pipeline_predict_from_library Predict next-day wildfire spread with a conditional DDPM ensemble (confidence map, uncertainty map and binary mask) on a bundled NDWS test sample, either shipped with the Space or stored in the weights repository. Returns: Tuple of (input_channels_panel_image, prediction_panel_image with previous fire, ground truth, confidence, uncertainty and binary maps, metrics_markdown_string including IoU, precision, recall and F1 when ground truth is present).
• NDWS_Pipeline_predict_from_upload Predict next-day wildfire spread from an uploaded NumPy file with a conditional DDPM ensemble, returning a confidence map (ensemble mean), an uncertainty map (standard deviation across members) and a binary fire mask. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: Tuple of (input_channels_panel_image, prediction_panel_image with previous fire, ground truth if present, confidence, uncertainty and binary maps, metrics_markdown_string).
• NDWS_Pipeline_predict_synthetic Predict next-day wildfire spread on a synthetic homogeneous scenario, where every conditioning channel is a constant 64x64 field. Useful for sensitivity analysis, e.g. sweeping wind speed with everything else held fixed. Returns: Tuple of (input_channels_panel_image, prediction_panel_image with previous fire, confidence, uncertainty and binary maps, metrics_markdown_string).

No tool matches.

As the server's own listing gives them. We never call a tool.