With the rapid development of earth observation technology and the increasing variety of remote sensing sensors, single-modal remote sensing data can no longer meet the demands of the applications. Compared with single-modal remote sensing data, the information provided by multimodal remote sensing data has redundancy, complementarity, and cooperation [1], in which the redundancy of multimodal remote sensing data means that they provide the same representation, description, or interpretation results for the environment or targets; complementarity indicates that the information comes from different degrees of freedom and is mutually independent; cooperation means that different sensors have dependencies on other information during observation and information processing. Therefore, fusing information from multiple modalities of data sources can enhance the performance of interpretation tasks. Currently, limited by relevant datasets, methods for multimodal remote sensing image registration, and appropriate data fusion strategies, research related to joint intelligent interpretation of multimodal remote sensing images is still in its infancy. Therefore, this section takes multimodal remote sensing image classification as an example to analyze and study various steps from dataset construction to the completion of multimodal remote sensing image classification.