Deep Learning Methods for Remote Sensing Images and Their Applications in Ecological Resources

Dear Colleagues,

In recent years, deep learning has revolutionized the analysis of remote sensing imagery, offering unprecedented capabilities for interpreting complex spatial, spectral, and temporal patterns in ecological systems. These advanced methods—including convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and generative adversarial networks (GANs)—have demonstrated remarkable success in enhancing the accuracy, efficiency, and scalability of ecological resource monitoring. However, challenges remain in adapting these techniques to the unique characteristics of remote sensing data, such as high dimensionality, multi-modal inputs, and spatial heterogeneity. Issues like limited labeled datasets, model generalizability across diverse ecosystems, and computational demands further complicate their widespread application.

This Special Issue aims to highlight innovative research and practical applications of deep learning in leveraging remote sensing imagery for ecological resource management. We invite contributions that explore novel algorithms, models, and frameworks tailored to remote sensing data, with a focus on addressing real-world ecological challenges. Both original research and comprehensive review articles are welcome. Potential topics include, but are not limited to, the following:

• Novel deep learning architectures (e.g., Vision Transformers, Graph Neural Networks, and U-Net variants) for remote sensing image analysis.
• Self-supervised, contrastive, and semi-supervised learning to address the challenge of limited labeled data in ecological remote sensing.
• Explainable AI (XAI) and model interpretability techniques for building trust and understanding in ecological predictions.
• Deep learning-based fusion of multi-source data (e.g., optical, SAR, LiDAR, and hyperspectral) for enriched ecological information extraction.
• Deep learning for land use/land cover classification and change detection.
• Spatio-temporal deep learning models for monitoring ecosystem dynamics.
• Deep learning-based super-resolution and data enhancement for ecological monitoring.
• The application of deep learning technology in water and soil resource management.
• Big data analytics and cloud computing for ecological remote sensing.
• Analysis of deep learning technology in forest structure and biomass estimation.

Prof. Dr. Xiaodong Yu
Prof. Dr. Jianhua Ren
Dr. Xuyang Teng
Dr. Xiaohui Li
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 250 words) can be sent to the Editorial Office for assessment.

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. Sensors 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 2600 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.