Smart-Map: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging

Machine Learning (ML) algorithms have been used as an alternative to conventional and geostatistical methods in digital mapping of soil attributes. An advantage ML is their flexibility use various layers information covariates. However, come many variations that can make application by end users difficult. To fill this gap, a Smart-Map plugin, which complements Geographic Information System QGIS Version 3, was developed using modern artificial intelligence (AI) tools. generate interpolated maps, Ordinary Kriging (OK) the Support Vector (SVM) algorithm were implemented. The SVM model vector raster available covariates at time interpolation. Covariates selected based on spatial correlation measured Moran’s Index (I’Moran). evaluate performance case study conducted with data attributes collected area 75 ha, located central region state Goiás, Brazil. Performance comparisons between OK performed for sampling grids 38, 75, 112 sampled points. R2 RMSE methods. found superior prediction chemical three sample densities tested therefore recommended In study, values ranging from 0.05 0.83 0.07 12.01 predicted tested.