Estimation of daily global solar radiation using wavelet regression, ANN, GEP and empirical models: A comparative study of selected temperature-based approaches

Sharifi, Sayed Saber; Rezaverdinejad, Vahid; Nourani, Vahid

doi:10.1016/j.jastp.2016.10.008

Cited by 72 publications

(28 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, meteorological data-based models using empirical correlations depend on the most common meteorological elements including cloud cover, sunshine duration, temperature, and relative humidity, making them the most commonly examined and widely used models around the world, especially the sunshine-based and temperature-based models [6,11]. The primary sunshinebased model can be traced back toÅngström model, using sunshine duration and clear sky radiation data to estimate [11,13,14]. Prescott [15] suggested using the extraterrestrial radiation to replace clear sky radiation and presented theÅngström-Prescott (AP) model.…”

Section: Advances In Meteorologymentioning

confidence: 99%

Comparative Analysis of Global Solar Radiation Models in Different Regions of China

Zhang

Cui

Feng

et al. 2018

Advances in Meteorology

View full text Add to dashboard Cite

Complete and accurate global solar radiation ( ) data at a specific region are crucial for regional climate assessment and crop growth modeling. The objective of this paper was to evaluate the capability of 12 solar radiation models based on meteorological data obtained from 21 meteorological stations in China. The results showed that the estimated and measured daily had statistically significant correlations ( < 0.01) for all the 12 models in 7 subzones of China. The Bahel model showed the best performance for daily estimation among the sunshine-based models, with average 2 of 0. , and average NS of 0.696, respectively. On monthly scale,Ögelman model showed the best performance among the sunshine-based models, with average RE of 5.66%. The BC model showed the best performance among the temperature-based models, with average RE of 8.26%. Generally, the sunshine-based models were more accurate than the temperature-based models. Overall, the Bahel model is recommended to estimate daily ,Ögelman model is recommended to estimate monthly average daily in China when the sunshine duration is available, and the BC model is recommended to estimate both daily and monthly average daily when only temperature data are available.

show abstract

Section: Advances In Meteorologymentioning

confidence: 99%

Comparative Analysis of Global Solar Radiation Models in Different Regions of China

Zhang

Cui

Feng

et al. 2018

Advances in Meteorology

View full text Add to dashboard Cite

show abstract

“…GEP is an extension of GP [43] developed by Ferreira [44] that create computer program to investigate a relationship between input and output variables. GEP are developed to find a better solution for a particular problem to solve the under-study phenomena [45]. Application of GEP requires several steps.…”

Section: Models Structure and Applicationmentioning

confidence: 99%

Evaluation of Machine Learning Techniques for Daily Reference Evapotranspiration Estimation

Niaghi¹,

Hassanijalilian²,

Shiri³

2019

Preprint

View full text Add to dashboard Cite

The ASCE-EWRI reference evapotranspiration (ETo) equation is recommended as a standardized method for reference crop ETo estimation. However, various climate data as input variables to the standardized ETo method are considered limiting factors in most cases and restrict the ETo estimation. This paper assessed the potential of different machine learning (ML) models for ETo estimation using limited meteorological data. The ML models used to estimate daily ETo included Gene Expression Programming (GEP), Support Vector Machine (SVM), Multiple Linear Regression (LR), and Random Forest (RF). Three input combinations of daily maximum and minimum temperature (Tmax and Tmin), wind speed (W) with Tmax and Tmin, and solar radiation (Rs) with Tmax and Tmin were considered using meteorological data during 2003-2016 from six weather stations in the Red River Valley. To understand the performance of the applied models with the various combinations, station, and yearly based tests were assessed with local and spatial approaches. Considering the local and spatial approaches analysis, the LR and RF models illustrated the lowest rate of improvement compared to GEP and SVM. The spatial RF and SVM approaches showed the lowest and highest values of the scatter index as 0.333 and 0.457, respectively. As a result, the radiation-based combination and the RF model showed the best performance with higher accuracy for all stations either locally or spatially, and the spatial SVM and GEP illustrated the lowest performance among models and approaches.

show abstract

“…The genes are specified as sub‐expression trees (Hoseinian, Faradonbeh, Abdollahzadeh, Rezai, & Soltani‐Mohammadi, ; Kaboli, Fallahpour, Selvaraj, & Rahim, ; Mirabbasi, Kisi, Sanikhani, & Gajbhiye Meshram, ). The GEP algorithm has been used by some researchers in various sciences; such as estimation of the porosity effect on predicting compressive and flexural strength (Emamian & Eskandari‐Naddaf, ), prediction of energy and exergy analysis (Şencan Şahin, Kovacı, & Dikmen, ), estimation of soil temperature in a semiarid region (Behmanesh & Mehdizadeh, ), estimation of daily global solar radiation (Sharifi, Rezaverdinejad, & Nourani, ).…”

Section: Introductionmentioning

confidence: 99%

Mathematical model for mint drying kinetics prediction by freeze‐drying process: Gene expression programming

Kovacı

Dikmen

Şahin

2020

J Food Process Engineering

View full text Add to dashboard Cite

The drying ratio (DR) and the moisture ratio (MR) are the main drying characteristics properties which play an important role in the drying conditions. Therefore, it has been crucial for the accurate estimation of the selection of drying conditions needed for improving optimal drying process. In this study, DR and MR values have been experimentally determined, and these characteristics have been predicted as mathematical expressions by using gene expression programming (GEP). The outcomes of present study have been pointed out that the developed GEP models have been estimating target values with an acceptable accuracy guaranteed by using different statistical techniques. The R2 values have been denoted 0.973 and 0.972, whereas the RMSE values have been determined as 0.032324 and 0.013146 for developed models of DR and MR, respectively. The χ2values have been specified 0.001306 and 0.000194 for developed models of DR and MR, respectively. The developed nonlinear equations could be evaluated in areas you need to accurate and quick estimation of drying characteristics such as drying rate and moisture rate of mint. Practical Applications Mint drying kinetics (DR and MR) at different pressure of 30, 50, and 80 kPa and temperature of 40, 50, and 60°C have been experimentally studied. GEP model has been developed to predict this drying kinetics in the freeze‐drying process. Developed model can be evaluated in areas where you need to accurate and quick estimation of drying characteristics such as drying rate and moisture rate of mint.

show abstract

Estimation of daily global solar radiation using wavelet regression, ANN, GEP and empirical models: A comparative study of selected temperature-based approaches

Cited by 72 publications

References 70 publications

Comparative Analysis of Global Solar Radiation Models in Different Regions of China

Comparative Analysis of Global Solar Radiation Models in Different Regions of China

Evaluation of Machine Learning Techniques for Daily Reference Evapotranspiration Estimation

Mathematical model for mint drying kinetics prediction by freeze‐drying process: Gene expression programming

Contact Info

Product

Resources

About