article · IEEE Access
Earth observation data offers valuable spatial insights, yet processing massive volumes of satellite imagery remains technically demanding. To address data gaps in Morocco, six supervised machine learning algorithms were evaluated for land cover classification using Landsat 8 satellite imagery on Google Earth Engine. The algorithms, including Support Vector Machine, Random Forest, Classification and Regression Trees, Minimum Distance, Decision Tree, and Gradient Tree, were tested to categorise water, built-up land, cultivated ground, sandy areas, barren land, and forests. Performance was evaluated using accuracy indicators such as overall accuracy and Kappa coefficients. Minimum Distance emerged as the most effective algorithm, initially achieving an accuracy of 0.93, whereas Support Vector Machine performed least well at 0.74. Incorporating environmental spectral indices like NDVI, NDBI, BSI, and MNDWI generally improved classification results, confirming Minimum Distance as a rapid, accurate approach for mapping challenging terrains.
Accurate and up-to-date land cover maps are vital for urban planning, environmental monitoring, and resource management. Cloud-based analysis of satellite imagery reduces the computing and storage barriers typically associated with large geospatial datasets. Demonstrating that simpler classifiers such as Minimum Distance can outperform more complex models allows planners and researchers to generate reliable geographic assessments of inaccessible or extensive regions more rapidly.
This applied research demonstrates an automated mapping approach that could assist urban planning authorities, environmental protection agencies, and geospatial analytics companies. Because it relies on free cloud infrastructure and standard satellite imagery, the methodology appears close to practical deployment for regional monitoring, though the abstract does not describe a packaged software product or commercial enterprise.
AI-generated from the published abstract. Always read the original work before citing.
Earth observation data have proven to be a valuable resource of quantitative information that is more consistent in time and space than traditional land-based surveys. Remote sensing plays a vital role in collecting data in many aspects of life, whether scientific, economic, or political. Land cover information plays a very important role in supporting urban planning and decision making and provides many opportunities for mapping and monitoring urban areas. Multiple data sources exist, including satellite data of different resolutions ranging from very high to medium resolution, as well as aerial and drone image acquisitions. Today, accurate land cover information is in high demand and the use of satellite imagery and remote sensing techniques for planning and development is becoming a common study conducted by many researchers to find practical solutions to the many problems affecting our planet. The recovery, management, and analysis of these large amounts of satellite imagery pose considerable challenges. The classification of satellite images is a very popular and complex topic. In classification studies over the last decade, researchers have been frequently studying only those three machine learning algorithms RF, CART and SVM applied on cities or countries except Morocco which poses a great lack of information on the land use of Morocco. To solve these challenges, six machine learning algorithms were applied and compared to each other based on several evaluation metrics and then, to avoid the problems of data download and storage space, we used Google Earth Engine, a geospatial processing platform that operates in the cloud. It provides free access to substantial satellite data and free computations to monitor, visualize, and analyze environmental features at the petabyte scale. In this paper, we used Landsat 8 satellite data to perform a land cover classification of Morocco, applying machine learning algorithms, which is a subfield of artificial intelligence. This paper proposes an experimental study of six supervised machine learning algorithms, namely Support Vector Machine (SVM), Random Forest (RF), Classification and Regression Trees (CART), Minimum Distance (MD), Decision Tree (DT) and Gradient Tree (GTB), in order to classify the water areas, built-up areas, cultivated areas, sandy areas, barren areas and forest areas on the Moroccan territory to deduce at the end the best performing classifier which has a higher accuracy. The classification results are displayed using a set of accuracy indicators, including overall accuracy (OA), Kappa, user accuracy (UA) and producer accuracy (PA). We obtained a best accuracy of 0.93 for the minimum distance (MD) algorithm, but the worst result is 0.74 for the support vector machine (SVM) algorithm. To improve these results, we added different indices such as normalized difference vegetation index (NDVI), normalized difference accumulation index (NDBI), bare soil index (BSI) and modified normalized difference water index (MNDWI). In general, the addition of these indices improves accuracy. When comparing these classifiers before and after the addition of these indices, Minimum Distance yields nearly 93% better accuracy. Therefore, we conclude that it was the best performing classifier among the other classifiers that can quickly produce more accurate land cover maps, especially for hard-to-reach areas.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2023.3293828
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
