Advanced Machine Learning Models for Remote Sensing Applications and Data Analysis—Recent Developments

Dear Colleagues,

Machine learning is being applied to remote sensing at a continuously increasing rate thanks to the rapid advancement in commercially available computational power, which has facilitated the development of advanced machine learning models, such as the deep learning models. Over the last ten years or so, deep learning models such as convolution neural networks, recurrent neural networks, generative adversarial networks and, recently, transformers have been widely used for different remote sensing applications. The development of these models has also benefited from the higher availability of publicly available remote sensing data, as the efficacy of these models depends upon the use of sufficient training data. In addition, some models have been developed that use a lower amount of data or can generate synthetic data to facilitate the training process. Machine and deep learning models have been developed for many different types of remote sensing data types, such as hyperspectral, optical, and imaging radar data. This development enables performance achievement in an automated manner that surpasses that of the traditional models on topics such as agriculture yield prediction, climate change and calamity detection and prediction, natural and man-made structure monitoring, etc. However, significant room for improvement remains in analyzing and improving the generalization ability of these models on actual test data that may differ from the training data. Another expected research direction is the use and analysis of quantum machine learning models in remote sensing. Given the increasing population and emerging climatic challenges, it is imperative to continue the development of advanced machine learning models for remote sensing.

This Special Issue is aimed at disseminating recent studies that develop new machine and deep learning models and their practical applications in remote sensing data for classification, modeling, change detection, time-series prediction, data quality improvement, etc. This topic directly falls within the scope of MDPI Remote Sensing, especially AI Remote Sensing.

Both review and original research articles are invited. This Special Issue is not only aimed at the applications of new deep learning and quantum machine learning methods to real remote sensing data, but its intended target is also novel applications and/or analyses of existing machine and deep learning models, including performance improvement with limited data, data fusion, and transfer learning. Intended application areas include, but are not limited to, land and ocean monitoring, climate and agriculture prediction, calamity prediction and assessment, structural monitoring, data post-processing for data quality improvement, etc.

Dr. Ahmed Shaharyar Khwaja
Dr. Filippo Biondi
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
• quantum machine learning
• optical data
• imaging radar data
• multispectral and hyperspectral data
• environment monitoring and prediction
• calamity prediction and detection
• agriculture monitoring and prediction
• post-calamity evaluation
• time-series for structural monitoring
• transfer learning and one-shot learning
• semi-supervised learning