Data From "The capacity of generative models to synthesize regional landslide and non-landslide remote sensing imagery under data-scarce scenarios: insights from multimodal foundation models"
Abstract
Results and datasets of the manuscript “The capacity of generative models to synthesize regional landslide and non-landslide remote sensing imagery under data-scarce scenarios: insights from multimodal foundation models”. Once the manuscript is accepted for publishment, the dataset will be updated. "Landslide Dataset.rar" is the landslide remote sensing image–semantic annotation dataset. "non-landslide Dataset.rar" is the non-landslide remote sensing image–semantic annotation dataset. "Southwest_China_Landslide.safetensors" is the best landslide LoRA which is trained on SDXL. "Southwest_China_Terrain.safetensors" is the best non-landslide LoRA which is trained on SD 1.5. "BijieDatasetEnhanced.rar" is the enhanced dataset used for downstream landslide semantic segmentation experiments.
Fields of Study & Subjects
Landslides and related hazards
Generative Adversarial Networks and Image Synthesis
Remote-Sensing Image Classification
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 16 January 2026
- Document type
- Dataset