Silva et al. (2026) Integrating morphometric and climatic variables into the mapping of land use and vegetation cover in the Caatinga biome

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Environmental Monitoring and Assessment
• Year: 2026
• Date: 2026-09-29
• Authors: Alíbia Deysi Guedes da Silva, Sara Fernandes Flor de Souza, Rebecca Luna Lucena, João Santiago Reis
• DOI: 10.1007/s10661-026-15949-z

Research Groups

• Laboratory of Remote Sensing (LRS), Federal University of Ceará
• Department of Geography, Federal University of Ceará

Short Summary

This study evaluates a land use and land cover classification model in the Caatinga biome using machine learning techniques integrated with multiple environmental and climatic covariates. The research achieves an average global accuracy of 0.83 and a kappa index of 0.80.

Objective

• Evaluate the effectiveness of a land use and land cover classification model in the Caatinga biome using machine learning techniques integrated with multiple environmental and climatic covariates.

Study Configuration

• Spatial Scale: Regional scale, focusing on the Caatinga biome in Brazil.
• Temporal Scale: The study does not specify a particular time period, but it is implied to be a static analysis of land use and land cover patterns.

Methodology and Data

• Models used: Random Forest algorithm integrated with multiple environmental and climatic covariates on the Google Earth Engine platform.
• Data sources: Satellite imagery (presumably from Google Earth Engine) and various environmental and climatic datasets.

Main Results

• The model achieved an average global accuracy of 0.83 and a kappa index of 0.80.
• Geomorphological compartmentalization increased separability between land use classes and bare soil.
• Forest vegetation and rivers, lakes, and ocean classes showed high precision, while salt marshes and herbaceous restinga indicated inconsistencies.

Contributions

• This study provides an innovative approach to land use and land cover classification by incorporating multiple environmental and climatic covariates into a machine-learning classifier.
• The research contributes to the understanding of landscape transformations in semi-arid regions and highlights the importance of geomorphological compartmentalization in improving classification accuracy.

Funding

• Not specified in the provided text.

Citation

@article{Silva2026Integrating,
  author = {Silva, Alíbia Deysi Guedes da and Souza, Sara Fernandes Flor de and Lucena, Rebecca Luna and Reis, João Santiago},
  title = {Integrating morphometric and climatic variables into the mapping of land use and vegetation cover in the Caatinga biome},
  journal = {Environmental Monitoring and Assessment},
  year = {2026},
  doi = {10.1007/s10661-026-15949-z},
  url = {https://doi.org/10.1007/s10661-026-15949-z}
}