Deep Learning for Multi/Hyperspectral Image Analysis and Near-Surface Geophysics: Applications in Mineral Identification and Geo-Environmental Monitoring

Dear Colleagues,

The integration of deep learning into multi/hyperspectral remote sensing and near-surface geophysics represents a paradigm shift in geoscientific analysis. The weight-of-evidence method, based on binary images using statistical models, has been used to combine, process, and analyze various spatial data, such as that pertaining to remote sensing and geophysics, in the global resource sector. However, these geostatistical methods are limited in their ability to comprehensively capture the complexity and uncertainty of the Earth, making them difficult to optimize and apply in practice. In particular, they often encounter limitations in more complex scenarios when dealing with large volumes of data and broader scales. In contrast, deep learning has shown promise in leveraging a wide range of geoscience data to gain insights and solve geoscience-related problems without deep theoretical knowledge. This Special Issue explores how advanced deep learning approaches overcome traditional analytical limitations when applied to complex datasets that provide a comprehensive view of both Earth's surface and shallow subsurface environments. Multi/hyperspectral imaging captures detailed surface spectral signatures, while near-surface geophysical methods reveal underlying structures and properties, creating a powerful analytical synergy when combined. We examine cutting-edge applications in two critical domains: automated mineral identification and advanced geo-environmental monitoring. These methodologies address urgent challenges in sustainable resource management while supporting environmental protection initiatives.

This Special Issue aims to showcase cutting-edge research integrating deep learning approaches into near-surface geophysical methods and multi/hyperspectral remote sensing data to advance our understanding of complex geological and environmental systems. We seek contributions that bridge the surface–subsurface analytical divide, and especially those with particular emphasis on mineral identification and geo-environmental monitoring applications. The featured works will highlight innovative methodologies that leverage the complementary nature of spectral imaging data (providing detailed surface information) and geophysical measurements (revealing subsurface properties and structures). By synthesizing recent innovations, addressing current technical challenges, and identifying promising research directions, this Special Issue aims to accelerate the development of comprehensive analytical frameworks that can support sustainable resource management and environmental protection in an increasingly resource-constrained world.

We welcome original research articles, reviews, technical notes, and perspective papers addressing the intersection of deep learning with multi/hyperspectral remote sensing and near-surface geophysics.

Submissions may cover, but need not be limited to, the following key themes:

• Deep learning architectures for spectral–geophysical data fusion;
• Explainable AI for geoscientific interpretation;
• Comparative analyses of traditional versus deep learning approaches;
• Combinations of spectral data from different sensors/sources that are have contrasting spatial/spectral/radiometric resolutions;
• Mineral mapping and resource anomaly detection from regional to global scales;
• Geological process/environmental/geohazard monitoring;
• Three-dimensional integration of surface and sub-surface drill-core spectral data.

Yours Sincerely,

Prof. Dr. Jaehyung Yu
Dr. Young-Sun Son
Prof. Dr. Seung-Sep Kim
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• deep learning
• hyperspectral imaging
• near-surface geophysics
• mineral identification
• environmental monitoring
• data fusion
• spectral–geophysical integration
• surface–subsurface analysis
• sustainable resource management
• geoscientific AI