On the use of Graphs for Satellite Image Time Series

2025-05-22

AI Summary

Conventional raster-based methods for Satellite Image Time Series (SITS) modeling struggle to capture dynamic spatiotemporal relationships among land objects. Method: We propose the first general graph-based SITS analysis framework. It first segments remote sensing images to extract multiscale land objects, then constructs a dynamic spatiotemporal graph explicitly encoding both spatial proximity and temporal evolution, and finally employs Graph Neural Networks (GNNs) for object-level joint spatiotemporal modeling. Contribution/Results: Unlike traditional pixel-wise static modeling, our framework unifies representation learning—from static topology to dynamic evolution. Evaluated on land cover classification and water resource forecasting, it achieves significant accuracy improvements over state-of-the-art baselines. Results demonstrate the effectiveness, generalizability, and interpretability of graph-structured representations for modeling complex Earth surface processes.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The Earth's surface is subject to complex and dynamic processes, ranging from large-scale phenomena such as tectonic plate movements to localized changes associated with ecosystems, agriculture, or human activity. Satellite images enable global monitoring of these processes with extensive spatial and temporal coverage, offering advantages over in-situ methods. In particular, resulting satellite image time series (SITS) datasets contain valuable information. To handle their large volume and complexity, some recent works focus on the use of graph-based techniques that abandon the regular Euclidean structure of satellite data to work at an object level. Besides, graphs enable modelling spatial and temporal interactions between identified objects, which are crucial for pattern detection, classification and regression tasks. This paper is an effort to examine the integration of graph-based methods in spatio-temporal remote-sensing analysis. In particular, it aims to present a versatile graph-based pipeline to tackle SITS analysis. It focuses on the construction of spatio-temporal graphs from SITS and their application to downstream tasks. The paper includes a comprehensive review and two case studies, which highlight the potential of graph-based approaches for land cover mapping and water resource forecasting. It also discusses numerous perspectives to resolve current limitations and encourage future developments.

Problem

• Using graphs to analyze complex satellite image time series
• Modeling spatio-temporal interactions for pattern detection in SITS
• Developing graph-based methods for land cover and water forecasting

Innovation

• Graph-based techniques for satellite image analysis
• Object-level spatio-temporal graph construction
• Land cover mapping and water forecasting applications