Reference Evapotranspiration Evaluation Using Solar Radiation Estimated by ANN and Empirical Models

Abstract

Aims: The reference evapotranspiration (ETo) estimation with Penman-Monteith or Priestley-Taylor methods requires measurements of temperature, radiation, humidity, and wind velocity. In this study, we evaluated the estimations of ETo by Penman-Monteith (ETo-PM) and Priestley-Taylor (ETo-PrT) methods using indirect methods of calculating solar radiation (Rs). Place and Duration of Study: Daily meteorological measurements from two stations in northern Greece were used for the development of solar radiation models and ETo calculation. Methodology: The indirect methods of calculating solar radiation (Rs) are based on Artificial Neural networks (ANN) technology and models using the multi-linear regression method (MLR). Three different ANN and MLR models were derived. The Hargreaves method is also used. The evaluation of the indirect Rs derived models and the ETo estimation by the two methods was performed with the use of correlation coefficients (r), root mean square error (RMSE), and efficiency (EF) indexes. Results: The statistics of ETo estimation at the two stations showed that the r and EF values, between the estimated ETo using the indirect Rs models and estimated ETo using Rs measured, were greater than 0.963 and 0.918, respectively, while the RMSE values were lower than 0.646 mm d-1. The statistics of Rs models, showed that the r and EF values were greater than 0.860 and 0.605, respectively, while the RMSE values were lower than 4.47 MJ m-2d-1. Conclusion: The results of ANN models in comparison to MLR models, when using the same input variables, are consistent between them. These findings indicate that the Penman-Monteith and Priestley-Taylor methods can accurately predict ETo using Rs values estimated indirectly through the examined methods and models.

Unlocking renewable energy potential: Harnessing machine learning and intelligent algorithms

“…Physical models simulate PV systems employing complicated equations, but they are expensive to compute and can fall short of capturing the subtleties of actual circumstances, which leads to less precise forecasts. Similar short-term variations and quick changes in meteorological conditions, which have a significant effect on solar PV generation and lead to inaccurate predictions, are also difficult for statistical techniques based on historical data patterns and statistical algorithms to capture (Antonopoulos and Antonopoulos, 2024;Marzouq et al, 2018; A. . ML models, on the other hand, can enhance accuracy by combining historical trends, incorporating real-time data, and adapting to changing circumstances (Jathar et al, 2024).…”