Spectral Data Meets Machine Learning: From Datasets to Algorithms and Applications

Dear Colleagues,

Due to technological developments and the steadily increasing performance of the information infrastructure, spectral remote sensing systems have rapidly advanced over the last decade. Meanwhile, such systems provide data with high spatial and temporal resolutions. Simultaneously, the performance of the general information infrastructure has improved, mainly affecting the processing, storage, and transmission of data. This performance facilitates the handling of massive amounts of data resulting from the consideration of larger areas, an increasing level of detail, and the use of multi-sensor systems.

Among the methodological advancements, much progress is related to machine learning approaches for either classification or regression tasks. Access to the necessary computational resources and the increasing availability of large volumes of labeled remote sensing data enable researchers to train deeper models. Recent research addresses, for example, the development of new network architectures, opportunities for data fusion, the consideration of only small datasets, the explainability of deep learning approaches, or multi-temporal analyses.

This Special Issue welcomes papers that present innovative methodological advancements, latest results and findings of application-oriented work concerning the analysis of multispectral or hyperspectral data. Besides original work, this Special Issue is intended also to include selected papers representing an extension of work presented at the 2nd HyperMLPA workshop (http://www.spectroexpo.com/hypermlpa/).

Topics include but are not limited to:

• Spectral data processing
• New benchmark datasets
• Feature extraction, feature selection, dimensionality reduction, and data fusion
• Supervised and unsupervised machine learning
• Classification/segmentation
• Regression
• Change detection
• Deep learning approaches
• Multi-temporal analysis
• Applications for environmental monitoring and industrial processes

Dr. Sina Keller
Dr. Naoto Yokoya
Prof. Dr. Jocelyn Chanussot
Dr. Martin Weinmann
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. 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.