TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models

Zhongbin Guo, Yuhao Wang, Ping Jian, Chengzhi Li, Xinyue Chen, Zhen Yang, Ertai E

Keywords: Remote Sensing, Satellite Image Time Series, Temporal Reasoning, Generative models, Change-aware Generation, Multimodal Large Language Models

TL;DR: We introduce TAMMs, a unified framework which provides a single solution to both describe historical changes and forecast future scenes, significantly outperforming prior methods on both tasks.

Abstract: Temporal Change Description (TCD) and Future Satellite Image Forecasting (FSIF) are critical, yet historically disjointed tasks in Satellite Image Time Series (SITS) analysis. Both are fundamentally limited by the common challenge of modeling long-range temporal dynamics. To explore how to improve the performance of methods on both tasks simultaneously by enhancing long-range temporal understanding capabilities, we introduce **TAMMs**, the first unified framework designed to jointly perform TCD and FSIF within a single MLLM-diffusion architecture. TAMMs introduces two key innovations: Temporal Adaptation Modules (**TAM**) enhance frozen MLLM's ability to comprehend long-range dynamics, and Semantic-Fused Control Injection (**SFCI**) mechanism translates this change understanding into fine-grained generative control. This synergistic design makes the understanding from the TCD task to directly inform and improve the consistency of the FSIF task. Extensive experiments demonstrate TAMMs significantly outperforms state-of-the-art specialist baselines on both tasks. Our dataset can be found at https://huggingface.co/datasets/IceInPot/TAMMs .

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 2802