State-of-the-Art in Land Cover Classification and Mapping

Dear Colleagues,

Land cover classification and mapping have seen great advances methodologically and technically, with continuing improvements in conceptualization, models and methods, remote sensing science and systems, instrumentation, computer algorithms, and implementations. However, due to complexity in semantics, scale, phenology, and other characteristics inherent to land cover, there remain many challenging issues. Certain cover types (e.g., vegetation) are more difficult to classify and map than others (e.g., water bodies). Inconsistency and variability are common, even for experienced image analysts. Scientific rigor, technical sophistication, higher accuracy, and cost-effectiveness are extremely important and much needed, as are guidelines and overviews of good practice in these aspects of practice.

This Special Issue (SI), amended from its earlier theme on vegetation classification and mapping, aims to bring together multidisciplinary scientists and specialists for concerted research on concepts, models, methods, algorithms, and practicalities concerning the classification and mapping of land cover. Strategic key research foci will be thoroughly discussed with the aim of identifying bottlenecks to breakthroughs. The SI will facilitate communications among researchers and practitioners on topics of mutual interest. Such topics include, but are not limited to, the following:

• Classification system, harmonization, interoperability, and standards;
• Semantics and thematic resolution;
• Conceptualization of land cover as fields vs. objects;
• Multi-resolution, proportional, and fuzzy representations of land cover;
• Models of scale and minimum mapping units (MMU);
• Upscaling and downscaling;
• Sampling design for reference data acquisition;
• Image interpretation, interpreter variability, consistency, and quality assurance;
• Training datasets for machine learning oriented for land cover mapping;
• Spectral, spatial, and temporal features and their informativeness;
• Phenology and time series analysis;
• Statistical vs. rule-based classification methods;
• Physics-informed and explainable machine learning in land cover classification and mapping;
• Fusion of sensors, data, features, and classifiers;
• Data cubes of existing land cover products and land cover primitives;
• Well targeted re-mapping of land cover;
• Accuracy metrics and assessments for pixels, classes, and all problem domains;
• Uncertainty characterization;
• Thematic and regional case studies of cropland, grassland, shrub, forest, wetland, impervious surfaces, water bodies, and other broad cover types;
• Best practice in land cover classification and mapping.

Prof. Dr. Jingxiong Zhang
Prof. Dr. Won-Ho Nam
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.