Dimensionality Reduction for Remote Sensing Data Analysis: A Systematic Review of Methods and Applications

Abstract

Earth observation involves collecting, analyzing, and processing an ever-growing mass of data. This planetary data is crucial for addressing relevant societal, economic, and environmental challenges, ranging from environmental monitoring to urban planning and disaster management. However, its high dimensionality entails significant feature redundancy and computational overhead limiting the effectiveness of machine learning models. Dimensionality reduction (DR) techniques, specifically feature extraction, address these challenges by preserving essential data properties while reducing redundancy and enhancing tasks in Remote Sensing (RS). The landscape of DR for RS is a diverse, disorganized, and rapidly evolving field. We offer a practical guide for this landscape by introducing a framework of DR. Using this framework, we trace the evolution of DR across the data value chain in RS. Finally, we synthesize these trends and offer perspectives for the future of DR in RS by first characterizing this shift from single-task models to unified representations, then identifying two perspectives in the foundation model era: the need for robust and interpretable DR and the potential of bridging classical DR with modern representation learning.