Land Cover and Vegetation Mapping Based on Spectral Unmixing and Multi-Source Remote Sensing Data Fusion

Dear Colleagues,

Accurate, spatially explicit characterization of land cover and vegetation is fundamental to biodiversity assessment, ecosystem monitoring, agricultural management, carbon accounting, natural-resource planning, and climate adaptation. Yet mixed pixels, spectral similarity among classes, endmember variability, differences in spatial and temporal resolution, and inconsistent observations still limit conventional classification. Spectral unmixing offers a rigorous way to estimate sub-pixel proportions of vegetation, soil, water, impervious surfaces, and other landscape components. At the same time, the growing availability of multispectral and hyperspectral imagery, synthetic aperture radar, LiDAR, thermal data, unmanned aerial vehicle observations, and dense Earth-observation time series creates new opportunities for multi-source data fusion. Integrating these complementary datasets can improve the characterization of vegetation composition, structure, phenology, stress, biomass, and change processes across heterogeneous landscapes.

This Special Issue welcomes original research, methodological studies, technical advances, and reviews that develop or apply spectral unmixing, remote-sensing data fusion, or integrated approaches for land-cover and vegetation mapping. Contributions may address endmember identification and variability, linear and nonlinear mixture modeling, cross-sensor harmonization, resolution enhancement, spatial-spectral-temporal integration, machine learning and deep learning, physics-informed methods, uncertainty analysis, independent validation, model transferability, and reproducible workflows. Studies demonstrating robust applications across forests, croplands, rangelands, wetlands, drylands, coastal zones, and urban environments are also encouraged. The topic aligns directly with the scope of Remote Sensing by emphasizing innovative algorithms, image-processing methods, sensor integration, and scientifically validated environmental applications.

Topics of interest include, but are not limited to:

• Linear, nonlinear, sparse, Bayesian, and physics-based spectral unmixing;
• Endmember extraction, optimization, spectral-library development, and variability modeling;
• Hyperspectral and multispectral unmixing for sub-pixel land-cover and vegetation-fraction estimation;
• Spatial-spectral-temporal, multi-scale, pixel-, feature-, and decision-level fusion;
• Fusion of complementary optical, radar, structural, thermal, and multi-platform observations;
• Machine learning, deep learning, geospatial artificial intelligence, and hybrid modeling;
• Cross-sensor harmonization, resolution enhancement, downscaling, and super-resolution;
• Time-series analysis of phenology, biomass, stress, disturbance, degradation, and recovery;
• Uncertainty propagation, sensitivity analysis, accuracy assessment, and independent validation;
• Model transferability and generalization across sensors, regions, seasons, and ecosystems;
• Benchmark datasets, spectral libraries, open-source tools, and reproducible workflows;
• Application and synthesis studies across forests, agriculture, rangelands, wetlands, drylands, coastal zones, and urban environments.

Dr. Hamdi A. Zurqani
Guest Editor

Dr. Abdulsalam Al-Bukhari
Guest Editor Assistant

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-anonymized 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.

• spectral unmixing
• multi-source data fusion
• land-cover mapping
• vegetation mapping
• sub-pixel analysis
• endmember variability
• hyperspectral remote sensing
• synthetic aperture radar
• LiDAR
• geospatial artificial intelligence