A Framework for Actual Evapotranspiration Assessment and Projection Based on Meteorological, Vegetation and Hydrological Remote Sensing Products

As the most direct indicator of drought, the dynamic assessment and prediction of actual evapotranspiration (AET) is crucial to regional water resources management. This research aims to develop a framework for the regional AET evaluation and prediction based on multiple machine learning methods and multi-source remote sensing data, which combines Boruta algorithm, Random Forest (RF), and Support Vector Regression (SVR) models, employing datasets from CRU, GLDAS, MODIS, GRACE (-FO), and CMIP6, covering meteorological, vegetation, and hydrological variables. To verify the framework, it is applied to grids of South America (SA) as a case. The results meticulously demonstrate the tendency of AET and identify the decisive role of T, P, and NDVI on AET in SA. Regarding the projection, RF has better performance in different input strategies in SA. According to the accuracy of RF and SVR on the pixel scale, the AET prediction dataset is generated by integrating the optimal results of the two models. By using multiple parameter inputs and two models to jointly obtain the optimal output, the results become more reasonable and accurate. The framework can systematically and comprehensively evaluate and forecast AET; although prediction products generated in SA cannot calibrate relevant parameters, it provides a quite valuable reference for regional drought warning and water allocating.

[1]  Bingfang Wu,et al.  Regional Actual Evapotranspiration Estimation with Land and Meteorological Variables Derived from Multi-Source Satellite Data , 2020, Remote. Sens..

[2]  Stephen P. Good,et al.  Hydrologic connectivity constrains partitioning of global terrestrial water fluxes , 2015, Science.

[3]  Antonio Berti,et al.  Assessing reference evapotranspiration by the Hargreaves method in north-eastern Italy , 2014 .

[4]  Veronika Eyring,et al.  Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization , 2015 .

[5]  Feng-Min Li,et al.  Impacts of climate change and human activities on grassland vegetation variation in the Chinese Loess Plateau. , 2019, The Science of the total environment.

[6]  C. Azorín-Molina,et al.  Spatio‐temporal variability of droughts in Bolivia: 1955–2012 , 2015 .

[7]  Edward J. Zipser,et al.  Recent developments on the South American monsoon system , 2012 .

[8]  A multivariate assessment of climate change projections over South America using the fifth phase of the Coupled Model Intercomparison Project , 2021, International Journal of Climatology.

[9]  Rasmus Fensholt,et al.  Combining the triangle method with thermal inertia to estimate regional evapotranspiration — Applied to MSG-SEVIRI data in the Senegal River basin , 2008 .

[10]  M. Gocić,et al.  Analysis of changes in meteorological variables using Mann-Kendall and Sen's slope estimator statistical tests in Serbia , 2013 .

[11]  Sylvain Arlot,et al.  Comments on: A random forest guided tour , 2016 .

[12]  Yan Li,et al.  Weekly soil moisture forecasting with multivariate sequential, ensemble empirical mode decomposition and Boruta-random forest hybridizer algorithm approach , 2019, CATENA.

[13]  Carlos Gershenson,et al.  Wind speed forecasting for wind farms: A method based on support vector regression , 2016 .

[14]  Lin Lin,et al.  Two-layer random forests model for case reuse in case-based reasoning , 2015, Expert Syst. Appl..

[15]  Sancho Salcedo-Sanz,et al.  Short term wind speed prediction based on evolutionary support vector regression algorithms , 2011, Expert Syst. Appl..

[16]  P. Jones,et al.  Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset , 2020, Scientific Data.

[17]  J. Bravo,et al.  Climate change impacts on South American water balance from a continental-scale hydrological model driven by CMIP5 projections , 2020, Climatic Change.

[18]  Xining Zhao,et al.  The spatial and temporal evolution of the actual evapotranspiration based on the remote sensing method in the Loess Plateau. , 2019, The Science of the total environment.

[19]  Jingshan Yu,et al.  Variation in Reference Evapotranspiration over the Tibetan Plateau during 1961–2017: Spatiotemporal Variations, Future Trends and Links to Other Climatic Factors , 2020, Water.

[20]  T. McMahon,et al.  Estimating actual, potential, reference crop and pan evaporation using standard meteorological data: a pragmatic synthesis , 2013 .

[21]  S. Marofi,et al.  Topography and Land Cover Effects on Snow Water Equivalent Estimation Using AMSR-E and GLDAS Data , 2019, Water Resources Management.

[22]  Wei Xia,et al.  Distribution of Actual Evapotranspiration over Qaidam Basin, an Arid Area in China , 2013, Remote. Sens..

[23]  Jan Verbesselt,et al.  Trend Change Detection in NDVI Time Series: Effects of Inter-Annual Variability and Methodology , 2013, Remote. Sens..

[24]  Ting Yang,et al.  Does actual cropland water consumption change with evaporation potential in the Lower Yellow River? , 2021 .

[25]  R. Balling,et al.  Regional Variability in Drought as a Function of the Atlantic Multidecadal Oscillation , 2016 .

[26]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

[27]  S. Zwart,et al.  COMPARATIVE ANALYSIS OF THE PYSEBAL MODEL AND LYSIMETER FOR ESTIMATING ACTUAL EVAPOTRANSPIRATION OF SOYBEAN CROP IN ADANA, TURKEY , 2020, International Journal of Engineering and Geosciences.

[28]  M. Dettinger,et al.  The key role of dry days in changing regional climate and precipitation regimes , 2014, Scientific Reports.

[29]  Xi Chen,et al.  Analysis on impacts of hydro-climatic changes and human activities on available water changes in Central Asia. , 2020, The Science of the total environment.

[30]  Jonas Ardö,et al.  Improving evapotranspiration in a land surface model using biophysical variables derived from MSG/SEVIRI satellite , 2012 .

[31]  Ximing Cai,et al.  Climate change impacts on global agricultural water deficit , 2013 .

[32]  G. C. Sediyama,et al.  Geostatistical improvements of evapotranspiration spatial information using satellite land surface and weather stations data , 2013, Theoretical and Applied Climatology.

[33]  K. Riahi,et al.  The roads ahead: Narratives for shared socioeconomic pathways describing world futures in the 21st century , 2017 .

[34]  Minha Choi,et al.  Inter-comparison of evapotranspiration datasets over heterogeneous landscapes across Australia , 2020, Advances in Space Research.

[35]  Oliver L. Phillips,et al.  Intensification of the Amazon hydrological cycle over the last two decades , 2013 .

[36]  Francesco Granata,et al.  Evapotranspiration evaluation models based on machine learning algorithms—A comparative study , 2019, Agricultural Water Management.

[37]  Evaluation and projection of mean surface temperature using CMIP6 models over East Africa , 2021 .

[38]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[39]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[40]  Danielle J. Marceau,et al.  Remote sensing and the measurement of geographical entities in a forested environment. 1. The scale and spatial aggregation problem , 1994 .

[41]  K. Bharadwaj,et al.  Determination of crop-coefficients and estimation of evapotranspiration of rapeseed using lysimeter and different reference evapotranspiration models ABHIJIT SARMA* and KRISHNA BHARADWAJ , 2020 .

[42]  S. Moghim.  Assessment of Water Storage Changes Using GRACE and GLDAS , 2020, Water Resources Management.

[43]  S. Shukla,et al.  Support vector machine based modeling of evapotranspiration using hydro-climatic variables in a sub-tropical environment , 2015 .

[44]  Alicia M. Kinoshita,et al.  Estimating Evapotranspiration in a Post-Fire Environment Using Remote Sensing and Machine Learning , 2018, Remote. Sens..

[45]  S. Mehdizadeh,et al.  Modeling daily reference evapotranspiration via a novel approach based on support vector regression coupled with whale optimization algorithm , 2020, Agricultural Water Management.

[46]  Yan Zeng,et al.  Estimation of Actual Evapotranspiration Distribution in the Huaihe River Upstream Basin Based on the Generalized Complementary Principle , 2018, Advances in Meteorology.

[47]  Kun Ren,et al.  Binary Grey Wolf Optimization-Regularized Extreme Learning Machine Wrapper Coupled with the Boruta Algorithm for Monthly Streamflow Forecasting , 2021, Water Resources Management.

[48]  Peter B. Vose,et al.  Amazon Basin: A System in Equilibrium , 1984, Science.

[49]  Minha Choi,et al.  Stand-alone uncertainty characterization of GLEAM, GLDAS and MOD16 evapotranspiration products using an extended triple collocation approach , 2018 .

[50]  T. Rodrigues,et al.  Temporal trend changes in reference evapotranspiration contrasting different land uses in southern Amazon basin , 2021 .

[51]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[52]  Xin Liu,et al.  Introduce canopy temperature to evaluate actual evapotranspiration of green peppers using optimized ENN models , 2020 .

[53]  S. Cosentino,et al.  Dry matter and qualitative characteristics of alfalfa as affected by harvest times and soil water content , 2011 .

[54]  S. Rehana,et al.  Development of hydro-meteorological drought index under climate change – Semi-arid river basin of Peninsular India , 2021 .

[55]  Zhizhong Wang,et al.  Model optimizing and feature selecting for support vector regression in time series forecasting , 2008, Neurocomputing.

[56]  I. Hůnová,et al.  Long-term trends in nitrogen oxides at different types of monitoring stations in the Czech Republic. , 2020, The Science of the total environment.

[57]  Jingshan Yu,et al.  Differences in Reference Evapotranspiration Variation and Climate-Driven Patterns in Different Altitudes of the Qinghai–Tibet Plateau (1961–2017) , 2021, Water.

[58]  Fernando França da Cunha,et al.  Soil water content and actual evapotranspiration predictions using regression algorithms and remote sensing data , 2020 .

[59]  Xiufeng He,et al.  Multi‐model and multi‐sensor estimations of evapotranspiration over the Volta Basin, West Africa , 2015 .

[60]  Shi Hu,et al.  Attribution of Long-Term Evapotranspiration Trends in the Mekong River Basin with a Remote Sensing-Based Process Model , 2021, Remote. Sens..

[61]  Szilárd Szabó,et al.  Estimation of crop evapotranspiration through spatial distributed crop coefficient in a semi-arid environment , 2019, Agricultural Water Management.

[62]  Chong-Yu Xu,et al.  Comparison of seven models for estimation of evapotranspiration and groundwater recharge using lysimeter measurement data in Germany , 2005 .