datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
lk-dmc-landslide-warnings-docslk-dmc-landslide-warnings-chunkslandslide-prevention-italy
Pre-Landslide Risk Assessment from Sentinel-2 Imagery
Multi-image vision-language fine-tuning dataset for predicting pre-landslide
risk from Sentinel-2 spectral composites. Each sample contains six 512×512
images (one RGB + five spectral indices) paired with a structured JSON
assessment of slope hazard, human-impact exposure, and pixel-level
areas-of-interest where future failure is most likely.
Generated for fine-tuning LiquidAI/LFM2.5-VL-450M.
Dataset Summary… See the full description on the dataset page: https://huggingface.co/datasets/Sciamlab/landslide-prevention-italy.landslide-prevention-italy-2024-blind-test
Pre-Landslide Risk Assessment 2024 Blind Test
Blind test dataset for evaluating VLM-based pre-landslide risk detection on 2024
Italian landslide events. This dataset contains 29 events from January–December 2024
with no ground truth labels — designed for evaluating model predictions against
future landslide occurrences.
Generated for evaluating fine-tuned models on LiquidAI/LFM2.5-VL-450M.
Dataset Summary
Total samples
29
Split
test (blind)
Image… See the full description on the dataset page: https://huggingface.co/datasets/Sciamlab/landslide-prevention-italy-2024-blind-test.Landslide4senselandslide-sentinel2-vlm