Machine learning algorithms for land cover mapping in a Protected Natural Area

Simple item page
AudienciaPúblico en generales_ES
CoberturaMéxicoes_ES
Fecha de ingreso2026-10-05T16:33:50Z
Fecha de publicación2026-01-01
ResumenProtected natural areas contribute to biodiversity conservation and to climate change mitigation, and provide ecosystem services. Accuracy assessment information on land cover and land use distribution is essential for managing these areas, and Sentinel-2 mission data are well-suited for monitoring them. Therefore, the objective of the study was to compare the performance of four machine learning algorithms —Support Vector Machine (SVM), Random Forests (RF), Gradient-Boosted Decision Trees (GBDT), and Classification and Regression Trees (CART)—, integrating spectral indices and topographic variables. The Sentinel-2 collection and a stratified sample set were used for validation ( n = 641 ). Accuracy was assessed using area-weighted confusion matrices. A two-proportion Z -test was used to compare the algorithms globally, and a McNemar chi-square test was used to compare predictions for each class. The results showed that SVM and GBT had the highest overall accuracy, of 88 and 86, respectively. Comparison of the Z -test algorithms showed that half of the algorithm pairings were statistically different. McNemar's chi-square test showed that 46 of the comparisons by class between paired algorithms were statistically significant ( p ≤ 0.05 ). In conclusion, machine learning algorithms enable the generation of accurate land cover and land use (LCLU) maps. Its implementation in decision-making is recommended due to its ability to recognize complex patterns. Todos los textos publicados por la Revista Mexicana de Ciencias Forestales –sin excepción– se distribuyen amparados bajo la licencia Creative Commons 4.0 Atribución-No Comercial (CC BY-NC 4.0 Internacional), que permite a terceros utilizar lo publicado siempre que mencionen la autoría del trabajo y a la primera publicación en esta revista. https://creativecommons.org/licenses/by/4.0/es_ES
Doihttps://doi.org/10.29298/rmcf.v17i94.1580es_ES
URIhttps://riuat.uat.edu.mx/handle/123456789/5604
Idiomaenes_ES
EditorialNational Institute of Forestry, Agricultural and Livestock Researches_ES
RelaciónRevista Mexicana de Ciencias Forestaleses_ES
URL relacionadohttps://doi.org/10.29298/rmcf.v17i94.1580es_ES
DerechosAcceso abierto (Metadatos de producción científica)es_ES
Licenciahttp://purl.org/coar/access_right/c_abf2es_ES
FuenteRevista Mexicana de Ciencias Forestales
Palabra claveGoogle Earth Enginees_ES
Palabra claveMcNemar testes_ES
Palabra claveOlofssones_ES
Palabra claveSentinel-2Aes_ES
Palabra claveThematic reliabilityes_ES
Palabra claveZ testes_ES
TítuloMachine learning algorithms for land cover mapping in a Protected Natural Areaes_ES
Título alternativoAlgoritmos de aprendizaje automático para el mapeo de coberturas en un Área Natural Protegidaes_ES
TipoArtículoes_ES
ArbitradoHa sido Arbitradoes_ES
Autorde León, Natalia Martínez
AutorGutiérrez, Ignacio González
AutorCampanur, Xóchitl Celeste Ramíreze
AutorRodríguez, Mario Rocandio
AutorPuente, Arturo Medina
Autorde León, Natalia Martínezes_ES
AutorGutiérrez, Ignacio Gonzálezes_ES
AutorCampanur, Xóchitl Celeste Ramírezees_ES
AutorRodríguez, Mario Rocandioes_ES
AutorPuente, Arturo Medinaes_ES
InstituciónUniversidad Autónoma de Tamaulipas
InstituciónUniversidad Autónoma de Tamaulipases_ES
Número94es_ES
Rango de páginas28-53es_ES
URL relacionadahttps://doi.org/10.29298/rmcf.v17i94.1580
Tipo de artículoIndexado
Tipo de artículoIndexadoes_ES
Volumen17es_ES

Files

Collections

Documentación Cientifica