remotesensing-logo

Journal Browser

Journal Browser

Advances in Satellite-Based Land Cover Mapping and Monitoring

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Engineering Remote Sensing".

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 9480

Special Issue Editors


E-Mail Website
Guest Editor
UK Centre for Ecology & Hydrology, Lancaster Site, Library Avenue, Bailrigg, Lancaster LA1 4AP, UK
Interests: landscape ecology; computational methods; modelling; remote sensing; land cover monitoring

E-Mail Website
Guest Editor
Specto Natura Ltd., 9 College Road, Impington, Cambride CB24 9PL, UK
Interests: large-scale land cover mapping and monitoring; land cover meta-standards; remote sensing of land surface processes

Special Issue Information

Dear Colleagues,

Satellite-based Earth Observation (EO) is now in its seventh decade! The first satellite images of the Earth came from America’s Earth Explore 6 in 1959 and, since then, the technological progress has been impressive. However, until recently, access to the satellite images needed for large-scale land cover mapping has been very challenging. Images have been infrequent, expensive, and stored in independent, distributed government and private archives. Having located and obtained a collection of images, specialist skills were then needed to prepare for analysis. Analysis was typically performed on local machines with a limited processing capacity. The full potential of satellite-EO for land-cover analyses could not be realised.

The tide began to turn in 2008 when the USGS allowed access to its Landsat archive, thus providing free access to sub-30-m spatial-resolution data. Since 2014, the EU’s Copernicus programme has launched a fleet of Sentinel satellites, all of which provide images with full, free and open access, with some satellites providing a similar or better spatial resolution to Landsat and increased revisit frequency. Detailed global views of the land surface are, therefore, now freely available every few days. Cloud-based services provide centralized, straightforward access to vast collections of analysis-ready satellite images, which can be combined with sophisticated analysis tools through high-powered scalable processing abilities. Image access and processing constraints are now rarely a problem, and opportunities for innovative land cover research have never been greater. Major barriers have come down, but others remain.

Ground data are essential in the interpretation of satellite images and validation of the results. Observations are needed from widespread, often difficult-to-access locations, so they are expensive to collect. Many landscapes are dynamic and require regular updates. Consequently, ground data are often either inadequately available or not available at all. Scientists and service providers have had to compromise, making use of data collected for alternative purposes, which are often too sparse, out of date and require semantic translations. Potential solutions are crowd-sourced data, manipulation and re-use of old data, using information from historical maps and creative ways to expand the reach of geographically limited collections.

Once satellite and ground data are available, there are many ways to describe land cover. This has led to product heterogeneity, bringing compatibility and comparability issues, which limit key applications. For example, this is most important when monitoring large-scale land cover change in response to changes in climate and land use. The development of land-cover and land-use meta-language standards and semantic translation tools has the potential to harmonise cross-border inventories to support continental and global challenges.

In this Special Issue, we want to tap into the amazing research and development that is currently underway in land-cover mapping. In particular, we are seeking to expand the understanding of operational systems for large-scale, and even global, land-cover mapping and monitoring. In the last 12 months, a number of regional and global land cover products have been released, which provide real possibilities in land-cover mapping today and in the future.

Therefore, in this Special Issue, we are particularly interested in state-of-the-art submissions that cover the following:

  • The use of analysis-ready image collections and cloud computing services;
  • Highly automated operational systems;
  • Near-real-time land-cover mapping;
  • Methods for overcoming the shortage of adequate training and validation data;
  • Tools for harmonising disparate land cover and ground data collections to support continental-to-global-scale land-cover analyses;
  • Land-cover change detection;
  • Any other novel and innovative developments in the field of EO-based land-cover mapping.

Dr. R. Daniel Morton
Dr. Geoff Smith
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 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 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.

Keywords

  • land cover
  • land use
  • change detection
  • operational systems
  • cloud processing
  • semantic translation
  • Earth Observation

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

31 pages, 8843 KiB  
Article
Operational Use of EO Data for National Land Cover Official Statistics in Lesotho
by Lorenzo De Simone, William Ouellette and Pietro Gennari
Remote Sens. 2022, 14(14), 3294; https://doi.org/10.3390/rs14143294 - 8 Jul 2022
Cited by 2 | Viewed by 3835
Abstract
The Food and Agriculture Organization of the United Nations (FAO) is building a land cover monitoring system in Lesotho in support of ReNOKA (‘we are a river’), the national program for integrated catchment management led by the Government of Lesotho. The aim of [...] Read more.
The Food and Agriculture Organization of the United Nations (FAO) is building a land cover monitoring system in Lesotho in support of ReNOKA (‘we are a river’), the national program for integrated catchment management led by the Government of Lesotho. The aim of the system is to deliver land cover products at a national level on an annual basis that can be used for global reporting of official land cover statistics and to inform appropriate land restoration policies. This paper presents an innovative methodology that has allowed the production of five standardized annual land cover maps (2017–2021) using only a single in situ dataset gathered in the field for the reference year, 2021. A total of 10 land cover classes are represented in the maps, including specific features, such as gullies, which are under close monitoring. The mapping approach developed includes the following: (i) the automatic generation of training and validation datasets for each reporting year from a single in situ dataset; (ii) the use of a Random Forest Classifier combined with postprocessing and harmonization steps to produce the five standardized annual land cover maps; (iii) the construction of confusion matrixes to assess the classification accuracy of the estimates and their stability over time to ensure estimates’ consistency. Results show that the error-adjusted overall accuracy of the five maps ranges from 87% (2021) to 83% (2017). The aim of this work is to demonstrate a suitable solution for operational land cover mapping that can cope with the scarcity of in situ data, which is a common challenge in almost every developing country. Full article
(This article belongs to the Special Issue Advances in Satellite-Based Land Cover Mapping and Monitoring)
Show Figures

Figure 1

21 pages, 5452 KiB  
Article
Spatially Stratified and Multi-Stage Approach for National Land Cover Mapping Based on Sentinel-2 Data and Expert Knowledge
by Hugo Costa, Pedro Benevides, Francisco D. Moreira, Daniel Moraes and Mário Caetano
Remote Sens. 2022, 14(8), 1865; https://doi.org/10.3390/rs14081865 - 13 Apr 2022
Cited by 18 | Viewed by 4029
Abstract
Portugal is building a land cover monitoring system to deliver land cover products annually for its mainland territory. This paper presents the methodology developed to produce a prototype relative to 2018 as the first land cover map of the future annual map series [...] Read more.
Portugal is building a land cover monitoring system to deliver land cover products annually for its mainland territory. This paper presents the methodology developed to produce a prototype relative to 2018 as the first land cover map of the future annual map series (COSsim). A total of thirteen land cover classes are represented, including the most important tree species in Portugal. The mapping approach developed includes two levels of spatial stratification based on landscape dynamics. Strata are analysed independently at the higher level, while nested sublevels can share data and procedures. Multiple stages of analysis are implemented in which subsequent stages improve the outputs of precedent stages. The goal is to adjust mapping to the local landscape and tackle specific problems or divide complex mapping tasks in several parts. Supervised classification of Sentinel-2 time series and post-classification analysis with expert knowledge were performed throughout four stages. The overall accuracy of the map is estimated at 81.3% (±2.1) at the 95% confidence level. Higher thematic accuracy was achieved in southern Portugal, and expert knowledge significantly improved the quality of the map. Full article
(This article belongs to the Special Issue Advances in Satellite-Based Land Cover Mapping and Monitoring)
Show Figures

Figure 1

Back to TopTop