Special Issue "Operational Land Cover/Land Use Mapping"
Deadline for manuscript submissions: closed (31 August 2020).
Interests: remote sensing; 3D point cloud processing; classification; machine learning; land cover mapping
Interests: machine learning; data fusion; image processing; land cover mapping; urban; agriculture
Interests: signal processing; image processing; pattern recognition; remote sensing; kernel methods
Interests: computer vision; large scale computing; machine learning
Interests: land use land cover mapping; remote sensing; classification; machine learning; deep learning; very high resolution imagery; historical images
Special Issues and Collections in MDPI journals
Interests: geospatial data modeling and updating; spatial relation; global land cover mapping; SDGs monitoring
Special Issues and Collections in MDPI journals
Land cover/land use (LC/LU) description is the core information layer for many interdisciplinary scientific and environmental studies. Accurate and up-to-date maps over large areas are mandatory baselines. A significant number of public policies, from global to local scales, are driven by such knowledge, such as climate change mitigation, reduction of risks and threats, sustainable development, and urban planning. After decades of methodological developments, remote sensing through automatic Earth-Observation (EO) image analysis has been widely recognised as the most feasible approach to derive LC/LU information, in particular in operational contexts, especially because, in recent years, the advent of EO satellite missions with short revisit times and increased spatial resolution, such as Landsat and Copernicus programs, has led to an unprecedented amount of images of a heterogeneous physical nature. Today, LU/LC mapping is cast as a supervised classification problem based on one or several of these data sources.
Operational LC/LU mapping is opposed to experimental mapping. It focuses on process upscaling and reliable product delivery within a predefined time schedule. In terms of research, it consists of several key issues:
- Automatic and semi-automatic data processing: for fusion, classification, and post-processing tasks. Manual intervention for training set design or hyperparameter tuning should also be prescribed, but crowdsourcing-based solutions are, for instance, encouraged.
- Versatility and reproducibility of processing chains, involving easy transfer to other areas without manual intervention. Such methods should not be site-specific, but rather both locally relevant and globally consistent. Transparency should be reinforced. Methods can leverage efficiently human inputs.
- Upscaling: LC/LU maps should be accurate at large scales, and processing chains (training and prediction steps) should be tailored to handle very large areas.
- Continuous monitoring and change detection: these techniques allow one to switch ontologies over time, which is a relevant part of monitoring and change detection work, as LU/LC class definitions change over time.
- Optimal exploitation of existing data sources: with the new era of free and open-access data (proliferation of images, vector data, existing LC/LU maps) and software, a trade-off has to be found between multiple sources and scalability in an operational framework.
- Rigorous accuracy assessment protocols: these have been barely investigated and implemented so far. This is highly intertwined with land change assessment.
This Special Issue aims at collecting new developments and methodologies, best practices, and applications related to operational land cover/land use mapping. We welcome submissions that provide the community with the most recent advancements on all aspects mentioned above.
Dr. Clément Mallet
Dr. Nesrine Chehata
Dr. Mathieu Fauvel
Dr. Lionel Gueguen
Dr. Arnaud Le Bris
Dr. Chen Jun
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 papers will be 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 2400 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.
- Land cover/land use mapping
- Regional/national mapping
- Multi-source fusion
- Accuracy assessment