Sustainable Development through Land Use Classification: A Comparative Analysis of Machine Learning Algorithms

Strategic Insights -

A new study conducted by researchers at United Arab Emirates University sheds light on the application of machine learning algorithms for land use and land cover (LULC) mapping in Al Ain city, UAE. The study utilizes a range of machine learning classifiers, including Gradient Tree Boosting (GTB), Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), within the Google Earth Engine (GEE) platform. The researchers' objective is to evaluate and compare the performance of these algorithms using Sentinel-2 imagery from 2024.

Key Takeaways:

  • The study investigated the application of machine learning algorithms for LULC mapping in Al Ain city, UAE, using Sentinel-2 imagery from 2024.
  • The researchers utilized the Gradient Tree Boosting (GTB), Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART) classifiers within the Google Earth Engine (GEE) platform.
  • The study found that Random Forest (RF) and Gradient Tree Boosting (GTB) achieved the highest overall accuracy, with Gradient Tree Boosting's Kappa coefficient slightly lower than Random Forest's.
  • The study results highlight Google Earth Engine's limitations, particularly its memory constraints, for LULC mapping in arid environments like Al Ain.
  • The research contributes to the development of LULC mapping methodologies and their applicability in a sustainable development context.
  • The study emphasizes the importance of selecting suitable machine learning algorithms and evaluating their performance using relevant metrics.

Statistics:

  • The study used Sentinel-2 imagery from 2024 for LULC mapping.
  • The researchers utilized four machine learning classifiers: Gradient Tree Boosting (GTB), Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART).
  • Random Forest achieved an overall accuracy of 92.5%, with a Kappa coefficient of 0.85.
  • Gradient Tree Boosting achieved an overall accuracy of 91.8%, with a Kappa coefficient of 0.82.
  • The study results were evaluated using user and producer accuracy metrics.

Sources:

  • NewsRx. New Research on Sustainable Development from United Arab Emirates University Summarized (Optimizing Land Use Classification Using Google Earth Engine: A Comparative Analysis of Machine Learning Algorithms). Ecology, Environment & Conservation. August 1, 2025; p 279.
  • "Optimizing Land Use Classification Using Google Earth Engine: A Comparative Analysis of Machine Learning Algorithms." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2025,X-G-2025():863-869. (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences - http://www.isprs.org/publications/annals.aspx).
  • Copernicus Publications. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.