Comparison of deep neural networks for reference evapotranspiration prediction using minimal meteorological data
M.R. Sowmya, M. B. Santosh Kumar, Sooraj K. Ambat
Abstract
Evapotranspiration, the process of water loss through surface evaporation and plant transpiration, is hugely influenced by numerous meteorological variables in different climatic zones. A precise and accurate prediction of reference-evapotranspiration (ET <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> ), a crucial factor in the crop evapotranspiration estimation, facilitates efficient management of agricultural water supplies. This paper proposes an ET <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> prediction method, employing minimal meteorological data, as well as exploring the potential of deep learning to learn the time series data pattern. In this study, four variants of a deep neural network model were developed using different feature combinations of two datasets of California Irrigation Management Information System (CIMIS) weather stations in California, USA for ET <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> modeling and evaluated their predictive performance. The results showed that among the four deep neural network model variants (DnnV1, DnnV2, DnnV3, and DnnV6), the two input deep neural network, DnnV2 (RMSE =0.36 Millimeter/day and 0.52 Millimeter/day, R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.94 and 0.94) showed a comparable performance to the six input neural network, DnnV6 (RMSE =0.3 Millimeter/day and 0.43 Millimeter/day, R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> =0.96 and 0.96). However, by considering the minimalism factor in the selection of input variables, we recommend DnnV2 for ET <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> modeling.