Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning

Soil erosion presents substantial environmental and economic challenges, especially in areas prone to land degradation. This study assesses the use of Machine Learning (ML) methods—Support Vector Machines (SVM) and Generalized Linear Models (GLM)—to model Soil Erosion Susceptibility (SES) in the Sa...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Ramdhan Olii, Sartan Nento, Nurhayati Doda, Rizky Selly Nazarina Olii, Haris Djafar, Ririn Pakaya
Format: Article
Language:English
Published: Universitas Gadjah Mada 2025-05-01
Series:Journal of the Civil Engineering Forum
Subjects:
Online Access:https://journal.ugm.ac.id/v3/JCEF/article/view/19581
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427047959494656
author Muhammad Ramdhan Olii
Sartan Nento
Nurhayati Doda
Rizky Selly Nazarina Olii
Haris Djafar
Ririn Pakaya
author_facet Muhammad Ramdhan Olii
Sartan Nento
Nurhayati Doda
Rizky Selly Nazarina Olii
Haris Djafar
Ririn Pakaya
author_sort Muhammad Ramdhan Olii
collection DOAJ
description Soil erosion presents substantial environmental and economic challenges, especially in areas prone to land degradation. This study assesses the use of Machine Learning (ML) methods—Support Vector Machines (SVM) and Generalized Linear Models (GLM)—to model Soil Erosion Susceptibility (SES) in the Saddang Watershed, Indonesia. It incorporates environmental, hydrological, and topographical factors to improve prediction accuracy. The approach includes multi-source geospatial data collection, erosion inventory mapping, and relevant factor selection. SVM and GLM were applied to classify SES, with performance evaluated using accuracy, AUC, and precision metrics. Results show SVM classified 40.59% of the area as moderately susceptible and 38.50% as low susceptibility. GLM identified 24.55% as very low and 38.59% as low susceptibility. Both models demonstrated high accuracy (SVM: 87.4%, GLM: 87.2%) and strong AUC values (SVM: 0.916, GLM: 0.939), though GLM showed better specificity and recall. Feature importance analysis highlights that GLM favors hydrological factors like river proximity and drainage density, while SVM balances across various environmental inputs. These findings affirm the value of ML-based geospatial modeling for SES assessment, supporting interventions such as reforestation and erosion control. SVM is suitable for localized planning, whereas GLM offers strategic-level insights. This research contributes to advancing environmental modeling by embedding domain knowledge into ML frameworks, and suggests future work integrate real-time remote sensing and more sophisticated models for broader SES prediction.
format Article
id doaj-art-bef4842ec966421bbbd61fa430db038a
institution Kabale University
issn 2581-1037
2549-5925
language English
publishDate 2025-05-01
publisher Universitas Gadjah Mada
record_format Article
series Journal of the Civil Engineering Forum
spelling doaj-art-bef4842ec966421bbbd61fa430db038a2025-08-20T03:29:09ZengUniversitas Gadjah MadaJournal of the Civil Engineering Forum2581-10372549-59252025-05-0111210.22146/jcef.19581Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine LearningMuhammad Ramdhan Olii0Sartan Nento1Nurhayati Doda2Rizky Selly Nazarina Olii3Haris Djafar4Ririn Pakaya5Department of Civil Engineering, Engineering Faculty, Universitas Gorontalo, Gorontalo, INDONESIADepartment of Civil Engineering, Engineering Faculty, Universitas Gorontalo, Gorontalo, INDONESIADepartment of Civil Engineering, Engineering Faculty, Universitas Gorontalo, Gorontalo, INDONESIADepartment of Architecture, Engineering Faculty, Universitas Gorontalo, Gorontalo, INDONESIASulawesi II River Basin Center, Gorontalo, INDONESIADepartment of Public Health, Public Health Faculty, Universitas Gorontalo, Gorontalo, INDONESIA Soil erosion presents substantial environmental and economic challenges, especially in areas prone to land degradation. This study assesses the use of Machine Learning (ML) methods—Support Vector Machines (SVM) and Generalized Linear Models (GLM)—to model Soil Erosion Susceptibility (SES) in the Saddang Watershed, Indonesia. It incorporates environmental, hydrological, and topographical factors to improve prediction accuracy. The approach includes multi-source geospatial data collection, erosion inventory mapping, and relevant factor selection. SVM and GLM were applied to classify SES, with performance evaluated using accuracy, AUC, and precision metrics. Results show SVM classified 40.59% of the area as moderately susceptible and 38.50% as low susceptibility. GLM identified 24.55% as very low and 38.59% as low susceptibility. Both models demonstrated high accuracy (SVM: 87.4%, GLM: 87.2%) and strong AUC values (SVM: 0.916, GLM: 0.939), though GLM showed better specificity and recall. Feature importance analysis highlights that GLM favors hydrological factors like river proximity and drainage density, while SVM balances across various environmental inputs. These findings affirm the value of ML-based geospatial modeling for SES assessment, supporting interventions such as reforestation and erosion control. SVM is suitable for localized planning, whereas GLM offers strategic-level insights. This research contributes to advancing environmental modeling by embedding domain knowledge into ML frameworks, and suggests future work integrate real-time remote sensing and more sophisticated models for broader SES prediction. https://journal.ugm.ac.id/v3/JCEF/article/view/19581Soil Erosion Susceptibility (SES)Geospatial ModellingMachine Learning (ML)Support Vector Machines (SVM)Generalized Linear Models (GLM)
spellingShingle Muhammad Ramdhan Olii
Sartan Nento
Nurhayati Doda
Rizky Selly Nazarina Olii
Haris Djafar
Ririn Pakaya
Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning
Journal of the Civil Engineering Forum
Soil Erosion Susceptibility (SES)
Geospatial Modelling
Machine Learning (ML)
Support Vector Machines (SVM)
Generalized Linear Models (GLM)
title Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning
title_full Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning
title_fullStr Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning
title_full_unstemmed Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning
title_short Transformation of Geospatial Modelling of Soil Erosion Susceptibility Using Machine Learning
title_sort transformation of geospatial modelling of soil erosion susceptibility using machine learning
topic Soil Erosion Susceptibility (SES)
Geospatial Modelling
Machine Learning (ML)
Support Vector Machines (SVM)
Generalized Linear Models (GLM)
url https://journal.ugm.ac.id/v3/JCEF/article/view/19581
work_keys_str_mv AT muhammadramdhanolii transformationofgeospatialmodellingofsoilerosionsusceptibilityusingmachinelearning
AT sartannento transformationofgeospatialmodellingofsoilerosionsusceptibilityusingmachinelearning
AT nurhayatidoda transformationofgeospatialmodellingofsoilerosionsusceptibilityusingmachinelearning
AT rizkysellynazarinaolii transformationofgeospatialmodellingofsoilerosionsusceptibilityusingmachinelearning
AT harisdjafar transformationofgeospatialmodellingofsoilerosionsusceptibilityusingmachinelearning
AT ririnpakaya transformationofgeospatialmodellingofsoilerosionsusceptibilityusingmachinelearning