Search

Land-use and land-cover (LULC) themes are important for many domains, especially when they process environmental and socio-economic phenomena. The evolution of a land-use database called Open Land Use (OLU) started in 2013 and was continued by adapting many user requirements. The goal of this study was to design a new version of the OLU database that would better fit the gathered user requirements collected by projects using LULC data. A formal definition of the developed data model through Unified Modeling Language (UML) class diagrams, a feature catalogue based on ISO 19110 and SQL scripts for setting up the OLU database, are the key achievements of the presented paper. The presented research provides a multi-scale open database of LULC information supporting the DestinE initiative to develop a very-high-precision digital model of the earth. The novel spatio-temporal thematic approach also lies in modular views of the OLU database.

Land use and land cover are continuously changing in today’s world. Both domains, therefore, have to rely on updates of external information sources from which the relevant land use/land cover (classification) is extracted. Satellite images are frequent candidates due to their temporal and spatial resolution. On the contrary, the extraction of relevant land use/land cover information is demanding in terms of knowledge base and time. The presented approach offers a proof-of-concept machine-learning pipeline that takes care of the entire complex process in the following manner. The relevant Sentinel-2 images are obtained through the pipeline. Later, cloud masking is performed, including the linear interpolation of merged-feature time frames. Subsequently, four-dimensional arrays are created with all potential training data to become a basis for estimators from the scikit-learn library; the LightGBM estimator is then used. Finally, the classified content is applied to the open land use and open land cover databases. The verification of the provided experiment was conducted against detailed cadastral data, to which Shannon’s entropy was applied since the number of cadaster information classes was naturally consistent. The experiment showed a good overall accuracy (OA) of 85.9%. It yielded a classified land use/land cover map of the study area consisting of 7188 km2 in the southern part of the South Moravian Region in the Czech Republic. The developed proof-of-concept machine-learning pipeline is replicable to any other area of interest so far as the requirements for input data are met.