RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting
Authors: Linrui Xu, Zhongan Wang, Fei Shen, Gang Xu, Huiping Zhuang, Ming Li, Haifeng Li
Organizations: Central South University · Zhejiang University · National University of Singapore · Guangming Laboratory · South China University of Technology
Remote sensing world models aim to both explain observed changes and forecast plausible futures, two tasks that share spatiotemporal priors. Existing methods, however, typically address them separately, limiting cross-task transfer. We present RS-WorldModel, a unified world model for remote sensing that jointly handles spatiotemporal change understanding and text-guided future scene forecasting, and we build RSWBench-1.1M, a 1.1 million sample dataset with rich language annotations covering both tasks. RS-WorldModel is trained in three stages: (1) Geo-Aware Generative Pre-training (GAGP) conditions forecasting on geographic and acquisition metadata; (2) synergistic instruction tuning (SIT) jointly trains understanding and forecasting; (3) verifiable reinforcement optimization (VRO) refines outputs with verifiable, task-specific rewards. With only 2B parameters, RS-WorldModel surpasses open-source models up to 120× larger on most spatiotemporal change question-answering metrics. It achieves an FID of 43.13 on text-guided future scene forecasting, outperforming all open-source baselines as well as the closed-source Gemini-2.5-Flash Image (Nano Banana).
Figures & tables
Figure 1: RS-WorldModel: A unified world model for remote sensing that integrates spatiotemporal change understanding and future scene forecasting capabilities. (a) Qualitative comparison with leading methods. (b) Quantitative results on the RSWBench-1.1M.
Figure 2: Data construction pipeline and dataset composition. We establish a scalable pipeline to transform multi-temporal observations into high-quality instruction data, supporting understanding and forecasting tasks with strict train-test isolation.
Table 1: Comparison of dataset capabilities and scales for remote sensing understanding and generation. ✓: supported; ✗ : not supported; –: not applicable (dataset does not target this task category).
Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, 100871, China · Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · Harbin Institute of Technology, Shenzhen, China · Great Bay University, Dongguan, China +1
National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing (SBIIP), Beijing Institute of Technology, Beijing 100081, China · Advanced Research Institute of Multidisciplinary Sciences, Beijing Institute of Technology, Beijing 100081, China · School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China +5