Hybrid Neural Network Based Models for Evapotranspiration Prediction Over Limited Weather Parameters

Abstract

Evapotranspiration can be used to estimate the amount of water required by agriculture projects and green spaces, playing a key role in water management policies that combat the hydrological drought, which assumes a structural character in many countries. In this context, this work presents a study on reference evapotranspiration (ET o ) estimation models, having as input limited meteorological parameters, namely: temperature, humidity, and wind. Since solar radiation (SR) is an important parameter in the determination of ET o , SR estimation models are also developed. These ET o and SR estimation models compare the use of Artificial Neural Networks (ANN), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), and hybrid neural network models such as LSTM-ANN, RNN-ANN and GRU-ANN. Two main approaches were taken for ET o estimation: (i) directly use those algorithms to estimate ET o , and (ii) estimate solar radiation first and then use that estimation together with other meteorological parameters in a method that predicts ET o . For the later case, two variants were implemented: the use of the estimated solar radiation as (ii.1) a feature of the neural network regressors, and (ii.2) the use of FAO-56PM method to compute ET o , which has solar radiation as one of the input parameters. Using experimental data collected from a weather station (WS) located in Vale do Lobo (Portugal), the later approach achieved the best result with a coefficient of determination (R 2 ) of 0.977. The developed model were then applied to data from eleven stations located in Colorado (USA), with very distinct climatic conditions, showing similar (R 2 > 0.95) results to the ones for which the models were initially designed, proving a good generalization. As a final notice, the reduced-set features were carefully selected so that they are compatible with free online weather forecast services.

Performance Evaluation of Five Machine Learning Algorithms for Estimating Reference Evapotranspiration in an Arid Climate

“…The outputs of this research support the presented study. The study conducted by Vaz et al [58] employed machine learning and deep neural networks to construct a model for evapotranspiration, utilizing only a limited number of weather variables, including temperature, humidity, and wind. The presented research coincides with this research, as both establish the Random forest algorithm's potential to provide satisfactory outputs for ET o estimation.…”

Experimental Investigation of a Convection - Improved Solar Salt Evaporation System

“…Relative humidity values are represented as percentages, while the temperature values are in degrees Celsius. During the experiment, the wind speed was not constant-wind speed is affected by evapotranspiration, ambient relative humidity, and temperatures-and is valued in meters per second [17]- [20]. The annual solar daily radiation and wind speed in Bangkalan are presented in Fig.…”

Leveraging Large Language Models for Sensor Data Retrieval

“…This case study focuses on demonstrating the usefulness and feasibility of the proposed retrieval approach for predicting evapotranspiration. Evapotranspiration is the loss of moisture from a surface by direct evaporation together with the loss of water by transpiration of vegetation, i.e., combined processes that move water from the Earth's surface into the atmosphere [47]. The prediction of evapotranspiration is crucial for estimating the amount of water required by agriculture projects, thus necessitating a variety of data sources, including data collected from weather stations [47].…”