Machine Learning for Pan Evaporation Modeling in Different Agroclimatic Zones of the Slovak Republic (Macro-Regions)

Abstract

Global climate change is likely to influence evapotranspiration (ET); as a result, many ET calculation methods may not give accurate results under different climatic conditions. The main objective of this study is to verify the suitability of machine learning (ML) models as calculation methods for pan evaporation modeling on the macro-regional scale. The most significant PE changes in the different agroclimatic zones of the Slovak Republic were compared, and their considerable impacts were analyzed. On the basis of the agroclimatic zones, 35 meteorological stations distributed across Slovakia were classified into six macro-regions. For each of the meteorological stations, 11 variables were applied during the vegetation period in the years from 2010 to 2020 with a daily time step. The performance of eight different ML models—the neural network (NN) model, the autoneural network (AN) model, the decision tree (DT) model, the Dmine regression (DR) model, the DM neural network (DM NN) model, the gradient boosting (GB) model, the least angle regression (LARS) model, and the ensemble model (EM)—was employed to predict PE. It was found that the different models had diverse prediction accuracies in various geographical locations. In this study, the results of the values predicted by the individual models are compared.

Evaluation the Performance of Three Types of Two-Source Evapotranspiration Models in Urban Woodland Areas

“…where C c and C s are determined using Equations ( 8) and (9). R s , R c , and R b represent intermediate variables, which were estimated using Equations ( 10)-( 12); r sc represents the canopy resistance (m/s); r ac and r as represent the resistance of the canopy and soil boundary layer (m/s), respectively; r aa represents the aerodynamic resistance (m/s); r ss represents the surface resistance (m/s).…”

“…Evapotranspiration (ET) and latent heat flux play an important role in the terrestrial hydrological cycle and in the balance of energy [1][2][3][4]. The estimation of ET and its components (soil evaporation (E) and vegetation transpiration (T)) is important for an understanding of the water and energy transport process in the soil-plant-atmosphere continuum (SPAC) [5][6][7][8][9]. Approximately 55% of the world's population lives in an urban region, and this percentage will continue to increase in the future [10].…”