<i>Smart-Map</i>: 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 of ML algorithms is their flexibility to use various layers of information as covariates. However, ML algorithms come in many variations th...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/12/6/1350 |
| _version_ | 1797490844921495552 |
|---|---|
| author | Gustavo Willam Pereira Domingos Sárvio Magalhães Valente Daniel Marçal de Queiroz André Luiz de Freitas Coelho Marcelo Marques Costa Tony Grift |
| author_facet | Gustavo Willam Pereira Domingos Sárvio Magalhães Valente Daniel Marçal de Queiroz André Luiz de Freitas Coelho Marcelo Marques Costa Tony Grift |
| author_sort | Gustavo Willam Pereira |
| collection | DOAJ |
| description | Machine Learning (ML) algorithms have been used as an alternative to conventional and geostatistical methods in digital mapping of soil attributes. An advantage of ML algorithms is their flexibility to use various layers of information as covariates. However, ML algorithms come in many variations that can make their application by end users difficult. To fill this gap, a <i>Smart-Map</i> plugin, which complements Geographic Information System QGIS Version 3, was developed using modern artificial intelligence (AI) tools. To generate interpolated maps, Ordinary Kriging (OK) and the <i>Support Vector Machine</i> (<i>SVM</i>) algorithm were implemented. The <i>SVM</i> model can use vector and raster layers available in QGIS as covariates at the time of interpolation. Covariates in the <i>SVM</i> model were selected based on spatial correlation measured by Moran’s Index (I’Moran). To evaluate the performance of the <i>Smart-Map</i> plugin, a case study was conducted with data of soil attributes collected in an area of 75 ha, located in the central region of the state of Goiás, Brazil. Performance comparisons between OK and <i>SVM</i> were performed for sampling grids with 38, 75, and 112 sampled points. <i>R</i><sup>2</sup> and <i>RMSE</i> were used to evaluate the performance of the methods. <i>SVM</i> was found superior to OK in the prediction of soil chemical attributes at the three sample densities tested and was therefore recommended for prediction of soil attributes. In this case study, soil attributes with <i>R</i><sup>2</sup> values ranging from 0.05 to 0.83 and <i>RMSE</i> ranging from 0.07 to 12.01 were predicted by the methods tested. |
| first_indexed | 2024-03-10T00:38:53Z |
| format | Article |
| id | doaj.art-01c2b63ade4c424c9566049ec99fef81 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T00:38:53Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-01c2b63ade4c424c9566049ec99fef812023-11-23T15:10:17ZengMDPI AGAgronomy2073-43952022-06-01126135010.3390/agronomy12061350<i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary KrigingGustavo Willam Pereira0Domingos Sárvio Magalhães Valente1Daniel Marçal de Queiroz2André Luiz de Freitas Coelho3Marcelo Marques Costa4Tony Grift5Department of Agricultural Engineering, Federal University of Viçosa (UFV), Viçosa 36570-000, BrazilDepartment of Agricultural Engineering, Federal University of Viçosa (UFV), Viçosa 36570-000, BrazilDepartment of Agricultural Engineering, Federal University of Viçosa (UFV), Viçosa 36570-000, BrazilDepartment of Agricultural Engineering, Federal University of Viçosa (UFV), Viçosa 36570-000, BrazilAcademic Unit of Agrarian Sciences, Federal University Federal of Jataí (UFJ), Jataí 75804-000, BrazilDepartment of Agricultural and Biological Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USAMachine Learning (ML) algorithms have been used as an alternative to conventional and geostatistical methods in digital mapping of soil attributes. An advantage of ML algorithms is their flexibility to use various layers of information as covariates. However, ML algorithms come in many variations that can make their application by end users difficult. To fill this gap, a <i>Smart-Map</i> plugin, which complements Geographic Information System QGIS Version 3, was developed using modern artificial intelligence (AI) tools. To generate interpolated maps, Ordinary Kriging (OK) and the <i>Support Vector Machine</i> (<i>SVM</i>) algorithm were implemented. The <i>SVM</i> model can use vector and raster layers available in QGIS as covariates at the time of interpolation. Covariates in the <i>SVM</i> model were selected based on spatial correlation measured by Moran’s Index (I’Moran). To evaluate the performance of the <i>Smart-Map</i> plugin, a case study was conducted with data of soil attributes collected in an area of 75 ha, located in the central region of the state of Goiás, Brazil. Performance comparisons between OK and <i>SVM</i> were performed for sampling grids with 38, 75, and 112 sampled points. <i>R</i><sup>2</sup> and <i>RMSE</i> were used to evaluate the performance of the methods. <i>SVM</i> was found superior to OK in the prediction of soil chemical attributes at the three sample densities tested and was therefore recommended for prediction of soil attributes. In this case study, soil attributes with <i>R</i><sup>2</sup> values ranging from 0.05 to 0.83 and <i>RMSE</i> ranging from 0.07 to 12.01 were predicted by the methods tested.https://www.mdpi.com/2073-4395/12/6/1350precision agriculturegeographic information systems (GIS)geoprocessingartificial intelligencesoil mapping |
| spellingShingle | Gustavo Willam Pereira Domingos Sárvio Magalhães Valente Daniel Marçal de Queiroz André Luiz de Freitas Coelho Marcelo Marques Costa Tony Grift <i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging Agronomy precision agriculture geographic information systems (GIS) geoprocessing artificial intelligence soil mapping |
| title | <i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging |
| title_full | <i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging |
| title_fullStr | <i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging |
| title_full_unstemmed | <i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging |
| title_short | <i>Smart-Map</i>: An Open-Source QGIS Plugin for Digital Mapping Using Machine Learning Techniques and Ordinary Kriging |
| title_sort | i smart map i an open source qgis plugin for digital mapping using machine learning techniques and ordinary kriging |
| topic | precision agriculture geographic information systems (GIS) geoprocessing artificial intelligence soil mapping |
| url | https://www.mdpi.com/2073-4395/12/6/1350 |
| work_keys_str_mv | AT gustavowillampereira ismartmapianopensourceqgispluginfordigitalmappingusingmachinelearningtechniquesandordinarykriging AT domingossarviomagalhaesvalente ismartmapianopensourceqgispluginfordigitalmappingusingmachinelearningtechniquesandordinarykriging AT danielmarcaldequeiroz ismartmapianopensourceqgispluginfordigitalmappingusingmachinelearningtechniquesandordinarykriging AT andreluizdefreitascoelho ismartmapianopensourceqgispluginfordigitalmappingusingmachinelearningtechniquesandordinarykriging AT marcelomarquescosta ismartmapianopensourceqgispluginfordigitalmappingusingmachinelearningtechniquesandordinarykriging AT tonygrift ismartmapianopensourceqgispluginfordigitalmappingusingmachinelearningtechniquesandordinarykriging |