Does environmental data increase the accuracy of land use and land cover classification?

• Published in: International journal of applied earth observation and geoinformation Vol. 91; p. 102128
• Main Authors: Zeferino, Leiliane Bozzi, Souza, Ligia Faria Tavares de, Amaral, Cibele Hummel do, Fernandes Filho, Elpidio Inácio, Oliveira, Teogenes Senna de
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-09-2020; Elsevier
• Subjects: Accuracy; Amazon; Data mining; Image classification; Landsat; Random Forest; Accuracy; Amazon; Data mining; Landsat; Random Forest; Image classification
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2020.102128

•Environmental information together spectral data is an alternative to geolocalization of land use and land cover.•Omission and commission errors can be reduced by incorporating environmental information into spectral data.•The Random Forest algorithm is capable to identify patterns of land use and land cover distribution from a large dataset.•Soil variables are important for mapping the types and distributions of the vegetation, especially in ecotone areas in neotropical regions.
Optical image classification converts spectral data into thematic information from the spectral signature of each object in the image. However, spectral separability is influenced by intrinsic characteristics of the targets, as well as the characteristics of the images used. The classification process will present more reliable results when aspects associated with natural environments (climate, soil, relief, water, etc.) and anthropic environments (roads, constructions, urban area) begin to be considered, as they determine and guide land use and land cover (LULC). The objectives of this study are to evaluate the integration of environmental variables with spectral variables and the performance of the Random Forest algorithm in the classification of Landsat-8 OLI images, of a watershed in the Eastern Amazon, Brazil. The classification process used 96 predictive variables, involving spectral, geological, pedological, climatic and topographic data and Euclidean distances. The selection of variables to construct the predictive models was divided into two approaches: (i) data set containing only spectral variables, and (ii) set of environmental variables added to the spectral data. The variables were selected through nonlinear correlation analysis, with the Randomized Dependence Coefficient and the Recursive Feature Elimination (RFE) method, using the Random Forest classifier algorithm. The spectral variables NDVI, bands 2, 4, 5, 6 and 7 of the dry season and band 4 of the rainy season were selected in both approaches (i and ii). The Euclidean distance from the urban area, Arenosol soil class, annual precipitation, precipitation in February and precipitation of the wettest quarter were the variables selected from the auxiliary data set. This study showed that the addition of environmental data to the spectral data reduces the limitation of the latter, regarding the discrimination of the different classes of LULC, in addition to improving the accuracy of the classification. The addition of soil classes to spectral variables provided a reduction in errors for vegetation classification (Evergreen Forest and Cerrado Sensu Stricto), as it was able to inform about nutrient availability and water storage capacity. The study demonstrates that the addition of environmental variables to the spectral variables can be an alternative to improve monitoring in areas of ecotone in Neotropical regions.