ENVIRONMENTAL FRAGILITY BY MACHINE LEARNING ALGORITHMS

Cristiano Marcelo Pereira de Souza; Lucas Augusto Pereira Silva; Gustavo Vieira Veloso; Marcos Esdras Leite; Elpídio Inácio Fernandes Filho

doi:10.4215/rm2022.e21034

Cristiano Marcelo Pereira de Souza State University of Montes Claros, Montes Claros (MG), Brazil http://orcid.org/0000-0001-7692-1613
Lucas Augusto Pereira Silva Federal University of Uberlândia, Uberlândia (MG), Brazil http://orcid.org/0000-0001-5504-9029
Gustavo Vieira Veloso Federal University of Viçosa, Viçosa (MG), Brazil http://orcid.org/0000-0002-9451-2714
Marcos Esdras Leite State University of Montes Claros, Montes Claros (MG), Brazil http://orcid.org/0000-0002-9020-6445
Elpídio Inácio Fernandes Filho Federal University of Viçosa, Viçosa (MG), Brazil http://orcid.org/0000-0002-9484-1411

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

Abstract

The advancement of predictive models by Machine Learning Algorithms (ML) associated with environmental data enables the improvement of models of environmental fragility, which are essential tools for decision-making. This study aimed to derive a prediction of environmental fragility by testing ML associated with environmental covariates in the state of Minas Gerais. We use physical-environmental variables (soil, geology, climate, relief) with a weight of fragility for the attributes and calculation of the average to obtain a model of Potential Environmental Fragility (PEF). Subsequently, we extracted the PEF values to a 4,800-point grid, which was used to generate a new prediction by ML called PEFML. This prediction was based on testing five algorithms and a set of 105 environmental covariates. The results indicated that the best-performing PEFML prediction was the Random Forest model (R2 0.59 and RMSE 0.47), indicating a predominance of the low environmental fragility level. The PEF and PEFML models have strong correlations (0.7 Pearson); however, PEFML has stronger correlations with other environmental data. Therefore, the PEFML prediction is a robust model that captures information from covariates and has coherent spatial patterns.

Keywords: Environmental fragility model; Spatial prediction; Random Forest; Environmental planning.

Author Biographies

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.

References

AB'SÁBER, A.N. (1970). Províncias Geológicas E Domínios Morfoclimáticos No Brasil. São Paulo: Universidade de São Paulo, Instituto de Geografia, 1970. 26 p.
AMORIM, A.T., DO NASCIMENTO LOPES, E.R., DE SOUSA, J.A.P., DE CASSIA FERREIRA DA SILVA, R., DE SOUZA, J.C., LOURENÇO, R.W. (2021). Geomorphometric Environmental Fragility of a Watershed: A Multicriteria Spatial Approach. Environ. Monit. Assess., v.193, p.850.
ANJINHO, P.D.S., BARBOSA, M.A.G.A., COSTA, C.W., MAUAD, F.F. (2021). Environmental Fragility Analysis in Reservoir Drainage Basin Land Use Planning: A Brazilian Basin Case Study. Land Use Policy, v.100, p.104946.
BARROS, K.O., ALVARES SOARES RIBEIRO, C.A., MARCATTI, G.E., LORENZON, A.S., MARTINS DE CASTRO, N.L., DOMINGUES, G.F., ROMÁRIO DE CARVALHO, J., ROSA DOS SANTOS, A. (2018). Markov Chains and Cellular Automata to Predict Environments Subject to Desertification. Journal of Environmental Management, v.225, p.160-167.
BERGEN, K.J., JOHNSON, P.A., DE HOOP, M.V., BEROZA, G.C. (2019). Machine Learning for Data-Driven Discovery in Solid Earth Geoscience. Science, v.363, p.eaau0323.
BREIMAN, L. (2001). Random Forests. Machine Learning, v.45, p.5-32.
BRUNGARD, C.W., BOETTINGER, J.L., DUNIWAY, M.C., WILLS, S.A., EDWARDS, T.C. (2015). Machine Learning for Predicting Soil Classes in Three Semi-Arid Landscapes. Geoderma, v.239, p.68-83.
CALLISTO, M., GONÇALVES, J.F., LIGEIRO, R. (2016). Water Resources in the Rupestrian Grasslands of the Espinhaço Mountains. In: G.W. Fernandes (Eds.) Ecology and Conservation of Mountaintop Grasslands in Brazil. Cham: Springer International Publishing, 2016. 87-102.
CAMPOS, J.A., AIRES, U.R.V., SILVA, D.D.D., CALIJURI, M.L. (2019). Environmental Fragility and Vegetation Cover Dynamics in the Lapa Grande State Park, Mg, Brazil An Acad Bras Cienc, v.91, p.e20170940.
CORTES, C., VAPNIK, V. (1995). Support-Vector Networks. Machine Learning, v.20, p.273-297.
COSTA, E.M., DOS ANJOS, L.H.C., PINHEIRO, H.S.K., GELSLEICHTER, Y.A., MARCONDES, R.A.T. (2020). Spatial Bayesian Belief Networks: A Participatory Approach for Mapping Environmental Vulnerability at the Itatiaia National Park, Brazil. Environmental Earth Sciences, v.79, p.359.
COSTA, L.R.F. (2021). Considerações Sobre as Macrounidades Geomorfológicas Do Estado De Minas Gerais–Brasil. William Morris Davis–Revista de Geomorfologia, v.2, p.11-18.
CREPANI, E., MEDEIROS, J.D., HERNANDEZ FILHO, P., FLORENZANO, T.G., DUARTE, V., BARBOSA, C.C.F. (2001). Sensoriamento Remoto E Geoprocessamento Aplicados Ao Zoneamento Ecológico-Econômico E Ao Ordenamento Territorial. São José dos Campos: Inpe 2001. 124.
CRUZ, B.B., MANFRÉ, L.A., RICCI, D.S., BRUNORO, D., APPOLINARIO JR., L., QUINTANILHA, J.A. (2017). Environmental Fragility Framework for Water Supply Systems: A Case Study in the Paulista Macro Metropolis Area (Se Brazil). Environmental Earth Sciences, v.76, p.441-453.
DIAS, S.H.B., FILGUEIRAS, R., FERNANDES FILHO, E.I., ARCANJO, G.S., SILVA, G.H.D., MANTOVANI, E.C., CUNHA, F.F.D. (2021). Reference Evapotranspiration of Brazil Modeled with Machine Learning Techniques and Remote Sensing. PLOS ONE, v.16, p.e0245834.
FARAWAY, J. (2016). Linear Models with R. Chapman Hall. New York: Chapman and Hall, 2016. 270.
FRANCO, G.B. Fragilidade Ambiental E Qualidade Da Água Na Bacia Do Rio Almada – Bahia. 2010. 361 p.f. Doutorado - Universidade Federal de Viçosa, Viçosa, MG, 2010., 2010.
FRANCO, G.B., MARQUES, E.A.G., GOMES, R.L., CHAGAS, C.D.S., SOUZA, C.M.P., BETIM, L.S. (2011). Fragilidade Ambiental Da Bacia Hidrográfica Do Rio Almada-Bahia. Rev Geog, v.28, p.187 - 205.
GALLANT, J.C., DOWLING, T.I. (2003). A Multiresolution Index of Valley Bottom Flatness for Mapping Depositional Areas. Water Resour. Res., v.39,
GOMES, L.C., FARIA, R.M., SOUZA, E., VELOSO, G.V., SCHAEFER, C.E.G.R., FERNANDES FILHO, E.I. (2019). Modelling and Mapping Soil Organic Carbon Stocks in Brazil. Geoderma, v.340, p.337-350.
GUEVARA, Y.Z.C., SOUZA, J.J.L.L.D., VELOSO, G.V., VELOSO, R.W., ROCHA, P.A., ABRAHÃO, W.A.P., FERNANDES FILHO, E.I. (2018). Reference Values of Soil Quality for the Rio Doce Basin. Rev. Bras. Ciên. Solo v.42, p.1-16.
HASTIE, T., TIBSHIRANI, R. (1987). Generalized Additive Models: Some Applications. Journal of the American Statistical Association, v.82, p.371-386.
HEINECK, C.A., LEITE, C.A.D.S., SILVA, M., VIEIRA, V.S. (2003). Mapa Geológico Do Estado De Minas Gerais, Escala 1: 1.000. 000. Belo Horizonte: Convênio COMIG/CPRM, v.1,
HIJMANS, R.J., CAMERON, S.E., PARRA, J.L., JONES, P.G., JARVIS, A. (2005). Very High Resolution Interpolated Climate Surfaces for Global Land Areas. Int. J. Climatol., v.25, p.1965-1978.
IGLESIAS, M., UHLEIN, A. (2009). Estratigrafia Do Grupo Bambuí E Coberturas Fanerozóicas No Vale Do Rio São Francisco, Norte De Minas Gerais. Braz. J. Geol, v.39, p.256-266.
KER, J.C. (1997). Latossolos Do Brasil: Uma Revisão. Revista Geonomos, v.5, p.17 - 40.
KUHN, M., JOHNSON, K. (2013). Applied Predictive Modeling. New York: Springer, 2013. 600.
MALONE, B.P., MCBRATNEY, A.B., MINASNY, B., LASLETT, G.M. (2009). Mapping Continuous Depth Functions of Soil Carbon Storage and Available Water Capacity. Geoderma, v.154, p.138-152.
MARTINS, T.I.S., RODRIGUES, S.C. (2012). Análise E Mapeamento Dos Graus De Fragilidade Ambiental Da Bacia Do Médio-Baixo Curso Do Rio Araguari, Minas Gerais. Caderno de Geografia, v.22,
MORELLOS, A., PANTAZI, X.-E., MOSHOU, D., ALEXANDRIDIS, T., WHETTON, R., TZIOTZIOS, G., WIEBENSOHN, J., BILL, R., MOUAZEN, A.M. (2016). Machine Learning Based Prediction of Soil Total Nitrogen, Organic Carbon and Moisture Content by Using Vis-Nir Spectroscopy. Biosyst Eng, v.152, p.104-116.
MOTTA, P.E., CURI, N., FRANZMEIER, D.P. (2002). Relation of Soils and Geomorphic Surfaces in the Brazilian Cerrado. In: P. Oliveira, R.J. Marquis (Eds.) The Cerrados of Brazil: Ecology Natural History of a Neotropical Savanna. New York: Columbia University Press, 2002. 13-32.
MURRAY, A.B., LAZARUS, E., ASHTON, A., BAAS, A., COCO, G., COULTHARD, T., FONSTAD, M., HAFF, P., MCNAMARA, D., PAOLA, C., PELLETIER, J., REINHARDT, L. (2009). Geomorphology, Complexity, and the Emerging Science of the Earth's Surface. Geomorphology, v.103, p.496-505.
NUNES, W.A.G.A., KER, J.C., SCHAEFER, C.E.G.R., FERNANDES FILHO, E.I., GOMES, F.H. (2001). Relação Solo-Paisagem-Material De Origem E Gênese De Alguns Solos No Domínio Do "Mar De Morros", Minas Gerais Rev. Bras. Ciên. Solo v.25, p.341-354.
PADARIAN, J., MINASNY, B., MCBRATNEY, A.B. (2020). Machine Learning and Soil Sciences: A Review Aided by Machine Learning Tools. SOIL, v.6, p.35-52.
PESSOA, P., ATMAN, D., KIMURA, G. (2020). Environmental Problems in the Lagoa Santa Karst. In: A. S. Auler, P. Pessoa (Eds.) Lagoa Santa Karst: Brazil's Iconic Karst Region. Cham: Springer International Publishing, 2020. 283-303.
Quinlan, J.R. (1992). Learning with Continuous Classes. (Eds.), Australian joint conference on artificial intelligence, pp. 343-348.
Rcore, T. (2022). R: A Language and Environment for Statistical Computing. Vienna, Austria (2016). http://www.R-project.org/ 15 june 2022.
ROSS, J.L.S. (1994). Análise Empírica Da Fragilidade Dos Ambientes Naturais Antropizados. Revista do departamento de geografia, v.8, p.63-74.
SALGADO, A.A.R., BRAUCHER, R., COLIN, F., NALINI, H.A., VARAJÃO, A.F.D.C., VARAJÃO, C.A.C. (2006). Denudation Rates of the Quadrilátero Ferrífero (Minas Gerais, Brazil): Preliminary Results from Measurements of Solute Fluxes in Rivers and in Situ-Produced Cosmogenic 10be. J. Geochem. Explor., v.88, p.313-317.
SCOLFORO, J.R., OLIVEIRA, A., CARVALHO, L.D., MARQUES, J.J.G., LOUZADA, J.N., MELLO, C., PEREIRA, J.R., REZENDE, J.B., VALE, L.C.C. (2008). Zoneamento Ecológico-Econômico De Minas Gerais. Lavras: UFLA, 2008.
SENA, N.C., VELOSO, G.V., FILHO, E.I.F., FRANCELINO, M.R., SCHAEFER, C.E.G.R. (2020). Analysis of Terrain Attributes in Different Spatial Resolutions for Digital Soil Mapping Application in Southeastern Brazil. Geoderma Regional, p.e00268.
SILVA, L.C.L., OLIVEIRA, F.S., RAMOS, V.D.V., SCHAEFER, C.E.G. (2018). Pedodiversidade No Estado De Minas Gerais-Brasil. Caderno de Geografia, v.28, p.18-38.
SIMÕES, P.L., VALADÃO, R.C., OLIVEIRA, C.V., OLIVEIRA, F.S. (2020). Uso De Atributos Pedológicos Na Compreensão Da Gênese De Superfícies Geomorfológicas Escalonadas Da Borda Oeste Do Planalto Do Espinhaço Meridional / Minas Gerais – Brasil. Revista Brasileira de Geomorfologia, v.21,
SOUZA, C.M.P., FIGUEIREDO, N.A., COSTA, L.M., VELOSO, G.V., ALMEIDA, M.I.S., FERREIRA, E.J. (2020). Machine Learning Algorithm in the Prediction of Geomorphic Indices for Appraisal the Influence of Landscape Structure on Fluvial Systems, Southeastern - Brazil. Revista Brasileira de Geomorfologia, v.21, p.363-378.
SOUZA, C.M.P., VELOSO, G.V., MELLO, C.R., RIBEIRO, R.P., PEREIRA SILVA, L.A., LEITE, M.E., FERNANDES FILHO, E.I. (2022). Spatiotemporal Prediction of Rainfall Erosivity by Machine Learning, Minas Gerais State, Brazil. Geocart. Internat., v.37, p.1-19.
SPÖRL, C., CASTRO, E., LUCHIARI, A. (2011). Aplicação De Redes Neurais Artificiais Na Construção De Modelos De Fragilidade Ambiental. Revista do Departamento de Geografia, v.21, p.113-135.
SPRÖL, C., ROSS, J.L.S. (2006). Análise Comparativa Da Fragilidade Ambiental Com Aplicação De Três Modelos. Geousp, p.39-49.
TRICART, J. (1977). Ecodynamic. Rio de Janeiro: IBGE, 1977. 91.
UFV, CETEC, UFLA, FEAM. (2010). Mapa De Solos Do Estado De Minas Gerais. p.49.
URRIAGO-OSPINA, L.M., JARDIM, C.M., RIVERA-FERNÁNDEZ, G., KOZOVITS, A.R., LEITE, M.G.P., MESSIAS, M.C.T.B. (2021). Traditional Ecological Knowledge in a Ferruginous Ecosystem Management: Lessons for Diversifying Land Use. Environ Dev Sustain, v.23, p.2092-2121.
Usgs. (2022). Earthexplorer Disponível em:< http://earthexplorer.usgs.gov> 03 março 2022.
WANG, Z., SHI, W., ZHOU, W., LI, X., YUE, T. (2020). Comparison of Additive and Isometric Log-Ratio Transformations Combined with Machine Learning and Regression Kriging Models for Mapping Soil Particle Size Fractions. Geoderma, v.365, p.114214.
WERE, K., BUI, D.T., DICK, Ø.B., SINGH, B.R. (2015). A Comparative Assessment of Support Vector Regression, Artificial Neural Networks, and Random Forests for Predicting and Mapping Soil Organic Carbon Stocks across an Afromontane Landscape. Ecological Indicators, v.52, p.394-403.