Spectral Unmixing of Hyperspectral Remote Sensing Imagery II

Dear Colleagues,

Hyperspectral imaging measures the objects on the Earth’s surface in hundreds or thousands of spectral channels, and offers thereby far better ability to identify the class of land cover materials which are often indistinguishable in the visible domain. However, due to the typical low spatial resolution of hyperspectral images (HSIs) and the resulting homogeneously mixed materials, the acquired spectrum of a single pixel may be a combination of the spectral signatures of multiple materials, resulting in mixed spectrum. This makes the processing, analysis and interpretation of HSIs difficult tasks. Spectral unmixing addresses this problem by identifying the constituent pure materials, also called endmembers, and their corresponding fractional abundances present in the pixel. Unmixing is an ill-posed inverse problem. Although the spectral unmixing problem has been widely studied over the last fifty years, it remains an active and important research topic in the fields of remote sensing.

The goal of this Special Issue of Remote Sensing is to track the latest progress in modelling theories, methodologies, algorithms and optimizations that are developed for the spectral unmixing of hyperspectral remote sensing images. Authors are invited to submit high-quality, original research papers on the topics including, but not limited to, the following:

• Endmember extraction;
• Estimating the number of endmembers;
• Unmixing models (linear or non-linear);
• Spectral unmixing with side information from other data sources;
• Large-scale spectral unmixing models;
• Spectral unmixing with deep learning;
• Applications of spectral unmixing;
• Blind unmixing;
• Robust unmixing to spectral variability or outlier;
• New data sets with reference data for validation of unmixing models;
• Methods of abundance estimation.

Dr. Shaoguang Huang
Prof. Dr. Hongyan Zhang
Prof. Dr. Hengchao 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. 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.