Reference evapotranspiration of Brazil modeled with machine learning techniques and remote sensing

Santos Henrique Brant Dias; Roberto Filgueiras; Elpídio Inácio Fernandes Filho; Gemima Santos Arcanjo; Gustavo Henrique da Silva; Everardo Chartuni Mantovani; Fernando França da Cunha

doi:10.1371/journal.pone.0245834

Reference evapotranspiration of Brazil modeled with machine learning techniques and remote sensing

PLoS One. 2021 Feb 9;16(2):e0245834. doi: 10.1371/journal.pone.0245834. eCollection 2021.

Authors

Santos Henrique Brant Dias¹, Roberto Filgueiras², Elpídio Inácio Fernandes Filho³, Gemima Santos Arcanjo⁴, Gustavo Henrique da Silva², Everardo Chartuni Mantovani², Fernando França da Cunha²

Affiliations

¹ Agronomy Department, Ponta Grossa State University (UEPG), Ponta Grossa, Paraná, Brazil.
² Agricultural Engineering Department, Federal University of Viçosa (UFV), Viçosa, Minas Gerais, Brazil.
³ Soil Department, Federal University of Viçosa (UFV), Viçosa, Minas Gerais, Brazil.
⁴ Polytechnic School, Federal University of Bahia (UFBA), Salvador, Bahia, Brazil.

Abstract

Reference evapotranspiration (ETo) is a fundamental parameter for hydrological studies and irrigation management. The Penman-Monteith method is the standard to estimate ETo and requires several meteorological elements. In developing countries, the number of weather stations is insufficient. Thus, free products of remote sensing with evapotranspiration information must be used for this purpose. In this context, the objective of this study was to estimate monthly ETo from potential evapotranspiration (PET) made available by MOD16 product. In this study, the monthly ETo estimated by Penman-Monteith method was considered as the standard. For this, data from 265 weather station of the National Institute of Meteorology (INMET), spread all over the Brazilian territory, were acquired for the period from 2000 to 2014 (15 years). For these months, monthly PET values from MOD16 product for all Brazil were also downloaded. By using machine learning algorithms and information from WorldClim as covariates, ETo was estimated through images from the MOD16 product. To perform the modeling of ETo, eight regression algorithms were tested: multiple linear regression; random forest; cubist; partial least squares; principal components regression; adaptive forward-backward greedy; generalized boosted regression and generalized linear model by likelihood-based boosting. Data from 2000 to 2012 (13 years) were used for training and data of 2013 and 2014 (2 years) were used to test the models. The PET made available by the MOD16 product showed higher values than those of ETo for different periods and climatic regions of Brazil. However, the MOD16 product showed good correlation with ETo, indicating that it can be used in ETo estimation. All models of machine learning were effective in improving the performance of the metrics evaluated. Cubist was the model that presented the best metrics for r2 (0.91), NSE (0.90) and nRMSE (8.54%) and should be preferred for ETo prediction. MOD16 product is recommended to be used to predict monthly ETo, which opens possibilities for its use in several other studies.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Brazil
Hydrology / standards*
Machine Learning*
Models, Statistical*
Reference Standards
Remote Sensing Technology*
Volatilization

Grants and funding

The study was supported by the Coordination for the Improvement of Higher Education Personnel (CAPES) and National Council for Scientific and Technological Development (CNPq). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.