Evaluation and comparison of eight machine learning models in land use/land cover mapping using Landsat 8 OLI: a case study of the northern region of Iran

Abstract

Land use land cover change mapping has been used for monitoring environmental changes as an essential factor to study on the earth's surface land cover in the field of climate change phenomena such as floods and droughts. Remote sensing images have been suggested to present inexpensive and fine-scale data offering multi-temporal coverage. This tool is useful in the field of environmental monitoring, land-cover mapping, and urban planning. This study aims to evaluate eight machine learning algorithms for image classification implemented in WEKA and R programming language. Firstly, Landsat 8 OLI/TIRS Level-2 images based on eight machine learning techniques including Random Forest, Decision Table, DTNB, J48, Lazy IBK, Multilayer Perceptron, Non-Nested Generalized Exemplars (NN ge), and Simple Logistic are classified. Then, obtained results are compared in term of Overall Accuracy (OA), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) for land use land cover mapping. Among the eight machine learning algorithms used for image classification based on the training and test dataset, NN ge classifier is ranked first with values of 100, 0, and 0 for Overall Accuracy, Mean Absolute Error and Root Mean Squared Error respectively. All machine learning algorithms had an Overall Accuracy of more than 99% for the training dataset. On the other hand, for the test dataset, J48 and DTNB algorithms had the worst performance with values of 88.1188 and 76.9802 respectively for the Overall Accuracy.

Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review

“…Thus, numerous studies on the LULC modelling have been carried out using different machine-learning algorithms [14,[48][49][50][51] as well as comparing the machine-learning algorithms [52][53][54]. Furthermore, a few studies have been carried out to identify the best suited and accurate algorithm among used machine-learning classifiers for LULC mapping [52][53][54][55]. Each machine-learning technique has different types of accuracy levels.…”

Land use/land cover classification using machine learning models

“…Till today, there has been a requirement to deliver provincial land use and land cover (LULC) maps and information for a variety of purposes, including change detection [3], planning or monitoring of the urban environment [4], disaster monitoring, landscape planning, resource management, site suitability analysis and ecological studies [5] or biological investigation [6]. Traditionally, non-parametric machine-learning classifiers (ML) such as random forests (RF) and support vector machines (SVMs) [7] have been used for geographical and easy-to-use classification.…”

Land use land cover mapping using advanced machine learning classifiers

“…In the last decade, remote sensing and data science researchers have used advanced machine learning algorithms for remote sensing image classification (Jamali, 2019;Mahdianpari et al, 2017Mahdianpari et al, , 2019Rodriguez-Galiano et al, 2012;Rogan et al, 2008;Shao, Lunetta, 2012;Yeom et al, 2013). Free access satellite data such as Landsat-8 and Sentinel-2 has raised the use of image classification algorithms towards remote sensing field (Belward, Skøien, 2015;Harris, Baumann, 2015).…”

“…In the Land Use Land Cover (LULC) mapping as a sub-field of image classification, the use of advanced machine learning algorithms has gained rapid interest (Jamali, 2020a,b,c;Jamali et al, 2021a,b) information on the Land Use Land Cover (LULC. For the physical and human environment, precise and up-to-data LULC dada is a need (Jamali, 2019), where it can be used in several fields, including health, ecology (Bourgeois, Sahraoui, 2020;Kenderessy et al, 2020;Skalský et al, 2020), policy management, agriculture and disaster management (Bégué et al, 2018).…”