TY - JOUR

T1 - Machine Learning Methods of Remote Sensing Data Processing for Mapping Salt Pan Crust Dynamics in Sebkha de Ndrhamcha, Mauritania

AU - Леменкова, Полина Алексеевна

PY - 2025/6/30

Y1 - 2025/6/30

N2 - The advances in Machine Learning (ML) and computer technologies enabled to process satellite images using programming. Environmental applications that handle Remote Sensing (RS) data for spatial analysis use such an approach, for example, Python’s library scikit-learn using algorithms on pattern identification, predictions or image classification. This paper presents an ML method of satellite image processing using Geographic Resources Analysis Support System (GRASS) Geographic Information System (GIS). The aim is to classify multispectral Landsat images using ML for identification of changes in salt pans of West Mauritania, Africa over the period 2014–2023. We define 10 classes of land cover categories and perform analysis of geological, lithological and landscape setting, and then introduce the principles, algorithms and processing of the ML methods of GRASS GIS. The following classification models were employed to implement image classification with training: Random Forest (RF), Decision Tree, Gradient Boosting and Support Vector Machine (SVM). The results were compared with clustering performed by k-means and maximum likelihood discriminant analysis. The cartographic visualisation and validation was implemented through accuracy analysis. Results for the best performing SVM model with seven-band input produced an overall accuracy of 76%, for the RF model – 73%, compared to 69% for Decision Tree Classifier – 69% and for Gradient Boosting Classifier – 67%. The SVM model embedded in GRASS GIS generates robust land cover maps with good accuracy from multispectral satellite images. The paper demonstrated an ML-based automated approach to satellite image processing, which links Artificial Intelligence (AI) with cartographic tasks.

AB - The advances in Machine Learning (ML) and computer technologies enabled to process satellite images using programming. Environmental applications that handle Remote Sensing (RS) data for spatial analysis use such an approach, for example, Python’s library scikit-learn using algorithms on pattern identification, predictions or image classification. This paper presents an ML method of satellite image processing using Geographic Resources Analysis Support System (GRASS) Geographic Information System (GIS). The aim is to classify multispectral Landsat images using ML for identification of changes in salt pans of West Mauritania, Africa over the period 2014–2023. We define 10 classes of land cover categories and perform analysis of geological, lithological and landscape setting, and then introduce the principles, algorithms and processing of the ML methods of GRASS GIS. The following classification models were employed to implement image classification with training: Random Forest (RF), Decision Tree, Gradient Boosting and Support Vector Machine (SVM). The results were compared with clustering performed by k-means and maximum likelihood discriminant analysis. The cartographic visualisation and validation was implemented through accuracy analysis. Results for the best performing SVM model with seven-band input produced an overall accuracy of 76%, for the RF model – 73%, compared to 69% for Decision Tree Classifier – 69% and for Gradient Boosting Classifier – 67%. The SVM model embedded in GRASS GIS generates robust land cover maps with good accuracy from multispectral satellite images. The paper demonstrated an ML-based automated approach to satellite image processing, which links Artificial Intelligence (AI) with cartographic tasks.

KW - machine learning

KW - Random Forest

KW - Support Vector Machine

KW - GRASS GIS

KW - satellite image

KW - remote sensing

KW - saline lake

UR - https://sciendo.com/pl/article/10.2478/arsa-2025-0003

UR - https://www.mendeley.com/catalogue/2e55402e-6aad-3392-b8a0-0017d0549853/

U2 - 10.2478/arsa-2025-0003

DO - 10.2478/arsa-2025-0003

M3 - Article

VL - 60

SP - 37

EP - 69

JO - Artificial Satellites

JF - Artificial Satellites

SN - 0208-841X

IS - 2

ER -