AI & Deep Learning for Remote Sensing Data Fusion

Abstract

ABSTRACT Remote sensing has become an essential tool in monitoring and analyzing the Earth's surface. With the growing availability of diverse sensor data, including optical, radar, LiDAR, and multispectral images, data fusion has emerged as a critical technique to improve the quality and reliability of information extracted from these datasets. Traditional methods of data fusion often struggle with high dimensional data and complex spatial relationships. Artificial Intelligence (AI) and Deep Learning (DL) methods, especially Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers, offer advanced solutions for integrating heterogeneous remote sensing data. This paper presents a comprehensive review of recent AI and DL approaches applied to remote sensing data fusion. Key challenges, recent trends, applications, and future research directions are discussed. Experimental comparisons highlight the superiority of AI-based methods over conventional techniques in improving classification accuracy, spatial resolution, and feature extraction.

KEYWORDS: Remote sensing, Data fusion, Artificial intelligence, Deep learning, Multisensor   integration, Convolutional neural networks, Transformers