Artificial Intelligence for Remote Sensing: Progress, Challenges, and Perspectives

Recent breakthroughs in artificial intelligence (AI), particularly in deep learning, have transformed the processing and analysis of large-scale remote sensing (RS) data. These advancements deliver remarkable performance in tasks such as imagery interpretation and quantitative inversion, significantly boosting the efficiency and reach of RS interpretation. AI extends the utility of RS data across diverse fields, including disaster monitoring, environmental protection, and urban planning, cementing its role as a cornerstone technology in RS. This review systematically explores the paradigm transfer in RS driven by AI, proposing a dual-dimensional “data–task” evolution framework that traces the transition from single-modal single-task models to multimodal multitask architectures in imagery interpretation and quantitative RS research. Specifically, architectural innovations overcome the limitations of single-sensor systems by fusing optical, synthetic aperture radar, and textual data, enabling feature reuse and enhancing cross-task synergy through collaborative mechanisms. The emergence of RS agents introduces a closed-loop intelligence paradigm—integrating multimodal perception, automated task planning, and interactive decision feedback—transforming RS interpretation from passive perception to active cognition. Despite these advances, significant challenges persist, such as data heterogeneity, edge computing limitations, and model security vulnerabilities, all of which are thoroughly assessed in this review. Looking ahead, we advocate next-generation deep learning architectures that integrate expert knowledge and human feedback to address the evolving demands of Earth observation. This review charts a clear path toward more reliable, adaptable, and intelligent RS systems, heralding a new era of AI-powered Earth observation.