cs.AINov 6, 2026

LandslideFM: A Foundation Model Towards Unified Landslide Perception and Understanding

Authors: Shanwen Wang, Sirui Wang, Xin Sun, Jungong Han

Organizations: Faculty of Data Science, City University of Macau, 999078, SAR Macao, China · Data Science in Earth Observation, Technical University of Munich, Munich, 80333, Germany · Department of Automation, Tsinghua University, Beijing, 100084, China

Abstract

Intelligent landslide detection is essential for disaster prevention. However, existing models primarily focus on isolated visual tasks, require extensive labeled data, and lack deep analytical and scene-understanding capabilities. To address these limitations, we propose LandslideFM, the first unified foundation model that connects visual perception tasks with contextual interpretation of landslides. Specifically, LandslideFM adapts to multiple visual tasks via a Source-Agreement Graduated Trust semi-supervised learning framework that leverages limited labeled data alongside abundant unlabeled data. Furthermore, predicted landslide regions provide explicit spatial guidance to a Vision-Language Model adapted through parameter-efficient fine-tuning, enabling comprehensive landslide reasoning. To support training and evaluation in this domain, we also present LandslideVL, the first benchmark for intelligent landslide analysis, combining visual imagery and newly introduced textual prompts. Comprehensive experiments across public datasets and LandslideVL demonstrate that LandslideFM achieves superior quantitative and qualitative performance. Most importantly, LandslideFM surpasses general-purpose VLMs in specialized landslide reasoning and scene analysis. Our code is released at https://github.com/wangshanwen001/LandslideFM.

Figures & tables

Explore similar work

CardsList
  1. LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

    Jun 17, 2026Chengfu Liu, Dongyang Hou, Junwu Xiang +5landslide detectionSemantic Segmentation

  2. EarthLD: Towards Unified Open-World Landslide Understanding via Vision-Language Guided Diffusion Models

    Sep 1, 2026Yuanchao Su, Lianru Gao, Mengying Jiang +3landslide detectionOpen-Set Recognition