Abstract

One of the most crucial variables in agricultural meteorology is solar radiation (Rs), although it is measured in a very limited number of weather stations due to its high cost in both installation and maintenance. Moreover, the quality of the data is usually low because of sensor failure and/or lack of calibration, which made scientists search for new approaches such as neural network models. Thus, the improvement of traditional solar radiation estimation models with minimum data availability is still needed for different purposes. In this work, several neural network models were developed and assessed (Multilayer Perceptron—MLP, Support Vector Machines—SVM, Extreme Learning Machine, Convolutional Neural Networks—CNN, and Long Short-Term Memory—LSTM) with different temperature-based input variables configurations in Southern Spain (weather station located in the Mediterranean Sea coast). The performances were analyzed using different statistical indices (Root Mean Square Error—RMSE, Mean Bias Error—MBE, and Nash-Sutcliffe model efficiency coefficient—NSE).

Highlights

  • During the last decades, an exponential increase in the Earth’s pollution has warned governments worldwide

  • Using the input configuration of 48 temperature values, Convolutional Neural Networks (CNN) performed as the best model in Root Mean Square Error (RMSE) (3.6864 MJ/m2 d) and Nash-Sutcliffe model efficiency coefficient (NSE) (0.7278), whereas the best Mean Bias Error (MBE) value (0.7238 MJ/m2 d) was carried out by Long Short-Term Memory (LSTM)

  • Concerning the input configuration of 48 temperature + 48 relative humidity values, Support Vector Machine (SVM) obtained the best performance in terms of RMSE (3.1836 MJ/m2 d) and NSE (0.7969), it was Multilayer Perceptron (MLP), the model that got the best MBE value (−0.0724 MJ/m2 d) for all the configurations

Read more

Summary

Introduction

An exponential increase in the Earth’s pollution has warned governments worldwide. One of the main measures to be adopted has been to increase the use of renewable energy, especially, the use of solar energy. In these terms, accurate estimations of solar radiation (Rs) are of high importance to estimate the available solar energy on a particular day, and to agronomical parameters such as the reference evapotranspiration (it determines the quantity of evaporated and transpired water in a hypothetical grass reference). Measuring solar radiation is more difficult than other meteorological parameters such as temperature or relative humidity, among others. When several quality control procedures [2] are applied, solar radiation usually contains the major quantity of flagged data [2,3]

Methods
Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call