Several models to estimate daily global solar irradiation: adjustment and evaluation

Santos, Cícero Manoel dos; Teramoto, Érico Tadao; Souza, Amaury de; Aristone, Flávio; Ihaddadène, Razika

doi:10.1007/s12517-021-06603-8

Cited by 5 publications

(7 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also reported that these temperature‐based models could predict GSR with reasonable accuracy for the said climatic region of China. Santos et al 35 developed four groups of models based on air temperature to predict GSR for Campo Grande, Brazil. The four groups are empirical models group consisting of 10 models, linear regression models consisting of 6 models, artificial neural network (ANN) models, and support vector machine (SVM) models comprising six models.…”

Section: Literature Reviewmentioning

confidence: 99%

Development of machine learning models based on air temperature for estimation of global solar radiation in India

Husain

Khan

2021

Env Prog and Sustain Energy

View full text Add to dashboard Cite

The designing of solar thermal systems need accurate information on global solar radiation (GSR). In the present study, six machine learning models, for example, random forest, k‐nearest neighbors, Gaussian process regression, support vector machine, multilayer perception, and XGBoost, are developed for GSR prediction with only air temperature as input for different climatic zones of India. The performance of machine learning models is also compared with some well‐known empirical models. The results show that generally, the performance of the machine learning models is better than empirical models, though, for a few climatic zones, empirical models give a better prediction. The top‐performing models are k‐nearest neighbors and XGBoost. Thus, we highly recommend temperature‐based models to predict GSR in the regions of India where only air temperature data are available. The accurate information of future GSR can be easily obtained by combining future air temperature forecasts with KNN/XGBoost models. These models can be extremely helpful in designing solar thermal systems in those regions where solar radiation facility is not available.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Development of machine learning models based on air temperature for estimation of global solar radiation in India

Husain

Khan

2021

Env Prog and Sustain Energy

View full text Add to dashboard Cite

show abstract

“…The importance of studying HEs and meteorological droughts jointly is that HE events can be predicted from knowledge of previous meteorological droughts, mainly due to the fact that dry events can increase the number of hot days in the summer [14]. In addition, several authors have stated that the increase in frequency (F), duration (D) and intensity (I) of HEs in summer may exacerbate both the frequency and the evolution of meteorological drought [7,[15][16][17][18][19], and when HEs and meteorological drought show significant concurrence (SC); that is, significant correlation, the damage to agriculture and other economic sectors is worse than that of a single phenomenon [17,[20][21][22][23]. In the Mexican region of Sinaloa, a large increase in the F, D and I, and frequency and evolution of meteorological drought is expected; i.e., in the coming years the annual mean temperature in northwestern Mexico will increase significantly (up to 2.5ºC) and the mean annual precipitation decrease (up to 20%) [24].…”

Section: Introductionmentioning

confidence: 99%

Hot Extremes and Climatological Drought Indicators in the Transitional Semiarid-Subtropical Region of Sinaloa, Northwest Mexico

Cárdenas¹,

Ruacho²,

Montoya³

et al. 2022

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

The main goal of this study was to explore the historical and recent spatial concurrence between the frequency (F), duration (D) and intensity (I) of hot extremes (HEs) and the frequency and evolution of meteorological drought in the region of Sinaloa. Based on the values of daily maximum temperature (Tmax) and precipitation obtained from CLImate COMputing for the interval April-October of a historical period and a recent period , the HE and the standardized precipitation index (SPI) were calculated on one-month (SPI-1) and four-month (SPI-4) timescales. Spearman rank correlation coefficients (Sr) were used to obtain the significant concurrences (SCs) between HEs and SPI-1, and HEs and SPI-4. El Quelite weather station showed the highest historical SCs between HEs and SPI-1 (−0.66≤Sr≤−0.57). Jaina is the only station that showed SCs with all four indicators of HEs and SPI-4 (−0.47≤Sr≤−0.34). In this study, the concurrence between HEs and SPI-1, and HEs and SPI-4 was determined for the first time. These are phenomena that can decrease the crop yield, particularly for rainfed crops such as maize, sesame and sorghum in the region commonly known as "the breadbasket of Mexico".

show abstract

“…This energy source is the principal source for life on Earth and is the most plentiful renewable energy source [2]. As reported by dos Santos et al (2021) [3], global solar irradiation is an important variable for applications related to the dimensioning of photovoltaic cells, and solar concentrators, among others. This property can be used to approximate and comprehend other linked components such as diffuse solar irradiation, among others [3].…”

Section: Introductionmentioning

confidence: 99%

“…As reported by dos Santos et al (2021) [3], global solar irradiation is an important variable for applications related to the dimensioning of photovoltaic cells, and solar concentrators, among others. This property can be used to approximate and comprehend other linked components such as diffuse solar irradiation, among others [3]. Solar irradiation data are essential to know the performance of solar energy systems [4] and, according to dos Santos et al (2021) [3], for different applications, it is necessary to assess the solar resource through the data available on ground level.…”

Section: Introductionmentioning

confidence: 99%

“…This property can be used to approximate and comprehend other linked components such as diffuse solar irradiation, among others [3]. Solar irradiation data are essential to know the performance of solar energy systems [4] and, according to dos Santos et al (2021) [3], for different applications, it is necessary to assess the solar resource through the data available on ground level. Global solar irradiation is the most relevant variable in renewable energy applications to model the dimension and photovoltaic systems [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications

Puga-Gil,

Astray,

Barreiro

et al. 2022

Mathematics

View full text Add to dashboard Cite

Global solar irradiation is an important variable that can be used to determine the suitability of an area to install solar systems; nevertheless, due to the limitations of requiring measurement stations around the entire world, it can be correlated with different meteorological parameters. To confront this issue, different locations in Rias Baixas (Autonomous Community of Galicia, Spain) and combinations of parameters (month and average temperature, among others) were used to develop various machine learning models (random forest -RF-, support vector machine -SVM- and artificial neural network -ANN-). These three approaches were used to model and predict (one month ahead) monthly global solar irradiation using the data from six measurement stations. Afterwards, these models were applied to seven different measurement stations to check if the knowledge acquired could be extrapolated to other locations. In general, the ANN models offered the best results for the development and testing phases of the model, as well as for the phase of knowledge extrapolation to other locations. In this sense, the selected ANNs obtained a mean absolute percentage error (MAPE) value between 3.9 and 13.8% for the model development and an overall MAPE between 4.1 and 12.5% for the other seven locations. ANNs can be a capable tool for modelling and predicting monthly global solar irradiation in areas where data are available and for extrapolating this knowledge to nearby areas.

show abstract

Several models to estimate daily global solar irradiation: adjustment and evaluation

Cited by 5 publications

References 67 publications

Development of machine learning models based on air temperature for estimation of global solar radiation in India

Development of machine learning models based on air temperature for estimation of global solar radiation in India

Hot Extremes and Climatological Drought Indicators in the Transitional Semiarid-Subtropical Region of Sinaloa, Northwest Mexico

Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications

Contact Info

Product

Resources

About