Artificial intelligence in RADAR remote sensing: advances, challenges, and future prospects

Dankan G.V.; Mary P.A.; Quevedo Lezama C.R.; Jagtap M.M.; Suneetha S. · RADAR: Remote Sensing Data Analysis with Artificial Intelligence (2025) · DOI: 10.1515/9783111572970-014

Resumen

The integration of artificial intelligence (AI) in RADAR remote sensing is revolutionizing data analysis, feature extraction, and object identification. Machine learning and deep learning models, including convolutional neural networks and recurrent neural networks, significantly enhance RADAR imagery interpretation by improving object detection, terrain classification, and noise reduction. Synthetic aperture radar (SAR), interferometric SAR (InSAR), and polarimetric RADAR benefit from AI-driven solutions that enable real-time processing, improving environmental monitoring, defense applications, and disaster response. Advanced AI techniques, such as explainable AI and generative adversarial networks, optimize feature extraction while addressing challenges like data noise, high computational costs, and lowresolution imagery. AI-driven RADAR systems are crucial for automation in selfdriving vehicles, precision agriculture, and military surveillance. This chapter explores these advancements, discussing future prospects in AI-driven RADAR sensing, including cloud computing integration and enhanced computational efficiency for real-time, large-scale applications.

Instituciones: Universidad Nacional Mayor de San Marcos