Add FireWx-FM input channel contract

README.md

@@ -195,6 +195,24 @@ This Hub repository is model-first. It provides the released weights, model-load
 | Data access path | Source links and roles documented in `data_sources/` |
 | Paper artifact path | Compiled PDF in `paper/`; manuscript source managed in the authors' paper workspace |
 
+### Input Channel Contract
+
+The pretrained checkpoints expect a fixed 16-channel tensor in `[channel, y, x]`
+order. Channel order matters.
+
+| Channels | Names | Source |
+|---:|---|---|
+| 0-9 | `t2m`, `d2m`, `u10`, `v10`, `cape`, `sp`, `blh`, `vis`, `prate`, `tp` | NOAA HRRR |
+| 10 | `firewx_valid` | Dynamic/input validity mask for this regional cache |
+| 11 | `static_valid` | Static reprojection validity mask |
+| 12-15 | `fuel_fbfm40`, `canopy_cover`, `housing_density`, `population` | LANDFIRE, WRC housing density, LandScan |
+
+FIRMS provides the occupancy target, not an input channel. WFIGS and MTBS are
+used for supporting event-level tasks and are not part of the 16-channel
+pretrained occupancy input. Full channel-level details are in
+`data_sources/DATA_SOURCES.md`; the same contract is available as
+`models/wildfire_fm/input_channels.json`.
+
 ---
 
 ## Hugging Face Release
@@ -204,6 +222,7 @@ This Hub repository is a model release with paper-aligned reproducibility artifa
 | Folder | Purpose | Example |
 |---|---|---|
 | `models/wildfire_fm/` | Model code, manifests, checkpoint metadata | `models/wildfire_fm/modeling_unet.py` |
+| `models/wildfire_fm/input_channels.json` | Machine-readable 16-channel input contract | `models/wildfire_fm/input_channels.json` |
 | `models/wildfire_fm/checkpoints/` | Five seeded PyTorch checkpoints | `seed_1/best_firms_prauc.pt` |
 | `paper/` | Compiled paper PDF | `wildfire_fm_evaluation_contracts.pdf` |
 | `assets/` | Hub-page visuals and final-paper previews | `selection_regret_final.png` |
@@ -254,7 +273,8 @@ Verify the public release artifacts:
 python3 scripts/reproduce_paper_outputs.py
 ```
 
-The checkpoint expects the same 16-channel gridded input described in the paper and in `data_sources/DATA_SOURCES.md`.
+The checkpoint expects the same fixed-order 16-channel gridded input described
+above and in `data_sources/DATA_SOURCES.md`.
 
 ---