FRAGILIDAD AMBIENTAL MEDIANTE ALGORITMOS DE APRENDIZAJE AUTOMÁTICO

Autores/as

DOI:

https://doi.org/10.4215/rm2022.e21034

Resumen

El avance de los modelos predictivos mediante Machine Learning Algorithms (ML) asociados a datos ambientales permite mejorar los modelos de fragilidad ambiental, que son herramientas fundamentales para la toma de decisiones. Este estudio tuvo como objetivo derivar una predicción de la fragilidad ambiental mediante la prueba de ML asociado con covariables ambientales en el estado de Minas Gerais. Se utilizaron variables físico-ambientales (suelo, geología, clima, relieve) con peso de fragilidad para los atributos y cálculo de la media para obtener un modelo de Fragilidad Ambiental Potencial (PEF). Posteriormente, extrajimos los valores de PEF a una cuadrícula de 4800 puntos, que se utilizó para generar una nueva predicción de ML, llamada PEFML. Esta predicción se basó en la prueba de cinco algoritmos y un conjunto de 105 covariables ambientales. Los resultados indicaron que la predicción PEFML con mejor desempeño fue el modelo Random Forest (R2 0.59 y RMSE 0.47), indicando un predominio del bajo nivel de fragilidad ambiental. Los modelos PEF y PEFML muestran fuertes correlaciones (0,7 Pearson); sin embargo, PEFML tiene correlaciones más fuertes con otros datos ambientales. Por lo tanto, la predicción PEFML es un modelo robusto que captura información de covariables y tiene patrones espaciales coherentes.

Palabras-llave: Modelos de fragilidad ambiental; predicción espacial; Random Forest; Planificación ambiental.



Biografía del autor/a

  • Cristiano Marcelo Pereira de Souza, State University of Montes Claros, Montes Claros (MG), Brazil

    PhD in Soils and Plant Nutrition from the Federal University of Viçosa (2018); Currently, Postdoctoral Researcher in Geography at the State University of Montes Claros. He participates in the Graduate Program in Geography (master's degree) at Unimontes, teaching disciplines in the master's degree: pedology, watersheds, scientific writing, and reading landscapes. He received a scholarship from different development agencies, such as: CNPq, CAPES, FAPEMIG, FAPESB, CENTEV-UFV. He served as a collaborating researcher at UFV from 2018 to 2020 in an extension project linked to the Geography department. He has experience in the field of physical geography, pedology, geomorphology, agronomy, geology. Working mainly on the following topics: soil-landscape relationship, GIS, modeling with machine learning algorithms, landscape dynamics, geoenvironmental mapping, watershed management, and studies of basins with structural control

  • Lucas Augusto Pereira Silva, Federal University of Uberlândia, Uberlândia (MG), Brazil
    PhD student in Geography at the Federal University of Uberlândia - UFU. Works in the area of Physical Geography, with emphasis on the following topics: environmental analysis with remote sensing applications, geoprocessing and machine learning, studies in biogeography and the influence of climate change scenarios (past and future) on the dynamics of land use and land cover and vegetation domains in semi-arid regions.
  • Gustavo Vieira Veloso, Federal University of Viçosa, Viçosa (MG), Brazil

    PhD in Soil Science and Plant Nutrition at the Federal University of Viçosa. He has experience in the area of Agricultural and Soil Engineering, with emphasis on Machine Learning, Modeling, Data Analysis, Time Series, Machine Design, Geochemistry, Geostatistics, Statistics is Electronics. Working mainly on the following topics: Machine Learning, Modeling, Data Analysis, Time Series and Statistics. 

  • Marcos Esdras Leite, State University of Montes Claros, Montes Claros (MG), Brazil

    Professor at the Department of Geosciences State University of Montes Claros-UNIMONTES. Professor of the Graduate Program in Geography/ UNIMONTES and the Graduate Program in Social Development/ UNIMONTES. Graduated in Geography/Unimontes. PhD in Geography from the Federal University of Uberlândia - UFU. Has experience in teaching and research in Geography, with emphasis on Geotechnologies. Coordinator of the Geoprocessing Laboratory/UNIMONTES. He completed a doctoral technical internship at Universidade Nova de Lisboa with a FAPEMIG scholarship (2008). Editor of Cerrados Magazine (2015 to 2016). Editor of Social Development Magazine (2013 to 2015). Member and coordinator of the Chamber of Applied Social Sciences - CSA/FAPEMIG (2017 to 2020). Member of CODEMA from Montes Claros/MG (2019 to 2021). Coordinator PPGEO/Unimontes (2018 to 2021). Coordinator of PPGDS/Unimontes (Current).

  • Elpídio Inácio Fernandes Filho, Federal University of Viçosa, Viçosa (MG), Brazil

    PhD in Agronomy (Soils and Plant Nutrition) from the Federal University of Viçosa (1996). He is currently a Professor at the Federal University of Viçosa. He has experience in the area of Agronomy, with an emphasis on Pedometry. Working mainly on the following topics: Expert systems, Agricultural fitness, Geographic information systems, software development.

Publicado

2023-02-15

Número

Sección

Artigos