Solar radiation and precipitable water modeling for Turkey using artificial neural networks

Şenkal, Ozan

doi:10.1007/s00703-015-0372-6

Cited by 21 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The maximum RMSE was found to be 2.4002% for Adana station in the testing values, while the best result was found to be 0.3633% for İzmir station in the training values. Moreover, another significant point in this table, the performance values of the training by method are generally better than the performance values of the testing Figure 6 shows a comparison between measured, ANN values for the five stations (training and testing stations) [25]. The results of own study confirms the ability of ANN method to predict solar radiation values at every pixels of the study area, throughout Turkey.…”

Section: Resultssupporting

confidence: 55%

See 1 more Smart Citation

Yapay Sinir Ağları ile Atmosferik Parametreler Kullanılarak Türkiye için Güneş Radyasyonu Modellemesi

Şenkal¹

2016

Çukurova Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Resultssupporting

confidence: 55%

“…Small scale climate stations were unable to make some meteorological atmospheric parameters observation. Using ANN, solar radiation values can be calculated for each such station [25]. …”

Section: Resultsmentioning

confidence: 99%

Yapay Sinir Ağları ile Atmosferik Parametreler Kullanılarak Türkiye için Güneş Radyasyonu Modellemesi

Şenkal¹

2016

Çukurova Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other than focusing on solar city sites with abundant solar radiation, this study purposely adopts MODIS satellite variables to model GSR since historical data related to the target variable (GSR) play a key role in helping evaluate solar energy availability. Remote sensing data have already been identified as a practical predictor for solar problems [55], so in this view, the coupling of a deep learning model with satellite-derived products is a major improvement over the use of station-based data mainly because the acquisition of satellite imagery can be feasible for inaccessible sites with no measurement infrastructure as long as a footprint is identified. For long-term forecast horizons (e.g., monthly), satellite data remain abundant for a diverse range of spatial and temporal resolutions and, recently, have been adopted in global solar radiation prediction problems [9,13].…”

Section: Deep Neural Networkmentioning

confidence: 99%

Deep Learning Neural Networks Trained with MODIS Satellite-Derived Predictors for Long-Term Global Solar Radiation Prediction

et al. 2019

View full text Add to dashboard Cite

Solar energy predictive models designed to emulate the long-term (e.g., monthly) global solar radiation (GSR) trained with satellite-derived predictors can be employed as decision tenets in the exploration, installation and management of solar energy production systems in remote and inaccessible solar-powered sites. In spite of a plethora of models designed for GSR prediction, deep learning, representing a state-of-the-art intelligent tool, remains an attractive approach for renewable energy exploration, monitoring and forecasting. In this paper, algorithms based on deep belief networks and deep neural networks are designed to predict long-term GSR. Deep learning algorithms trained with publicly-accessible Moderate Resolution Imaging Spectroradiometer (MODIS) satellite data are tested in Australia’s solar cities to predict the monthly GSR: single hidden layer and ensemble models. The monthly-scale MODIS-derived predictors (2003–2018) are adopted, with 15 diverse feature selection approaches including a Gaussian Emulation Machine for sensitivity analysis used to select optimal MODIS-predictor variables to simulate GSR against ground-truth values. Several statistical score metrics are adopted to comprehensively verify surface GSR simulations to ascertain the practicality of deep belief and deep neural networks. In the testing phase, deep learning models generate significantly lower absolute percentage bias (≤3%) and high Kling–Gupta efficiency (≥97.5%) values compared to the single hidden layer and ensemble model. This study ascertains that the optimal MODIS input variables employed in GSR prediction for solar energy applications can be relatively different for diverse sites, advocating a need for feature selection prior to the modelling of GSR. The proposed deep learning approach can be adopted to identify solar energy potential proactively in locations where it is impossible to install an environmental monitoring data acquisition instrument. Hence, MODIS and other related satellite-derived predictors can be incorporated for solar energy prediction as a strategy for long-term renewable energy exploration.

show abstract

“…Unlike geometry-based methods, the impact of data resolution has rarely been studied for data-driven approaches that attempt to recognize patterns in the relevant data for the solar radiation prediction. It may be because machine learning methods in the previous studies [e.g., 14,15] generally used solar radiation data (e.g., altitude, latitude, longitude, land surface temperature) produced at observation stations. In this case, the resolution of data may not be of importance for the prediction, as DEM data was not directly used for the modeling process.…”

Section: The Effect Of Data Resolution On Solar Irradiation Predictiomentioning

confidence: 99%

DEM-based Convolutional Neural Network Modeling for Estimation of Solar Irradiation: Comparison of the Effect of DEM Resolutions

Heo

Jung

Kim

et al. 2019

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

Recently, the use of solar panels has increased because of the growing demand for solar energy. To determine appropriate installation sites of photovoltaic (PV) panels, estimating the available solar energy at a certain area is important to predict the amount of power generation and planning PV plant operations. However, traditional data-driven approaches (e.g., machine learning) do not fully reflect the topographical characteristics of surrounding regions in the solar energy estimation, and the impact of data resolution (e.g., map scales) on the prediction accuracy has rarely been investigated. Thus, this paper presents a solar irradiation prediction model using a convolutional neural network (CNN) designed to process digital elevation map (DEM) images. Furthermore, an analysis of the impact of two different resolutions (i.e., 30 m and 60 m resolutions) on the model performance is also presented. A total of 25,000 DEM images are extracted from the national map of South Korea for both resolutions and then used as an input to train the CNN models. The results show that the CNN-based prediction models can be used to estimate the solar irradiation with high accuracy (e.g., mean square errors of 0.0018 and 0.0032 for 30 m and 60 m resolutions). It was also found that data resolution affects the performance of the CNN-based models. With an accurate estimation of the available solar energy at a certain site, the sites generating more power can potentially be evaluated and selected by searching a DEM on a large scale.

show abstract

Solar radiation and precipitable water modeling for Turkey using artificial neural networks

Cited by 21 publications

References 34 publications

Yapay Sinir Ağları ile Atmosferik Parametreler Kullanılarak Türkiye için Güneş Radyasyonu Modellemesi

Yapay Sinir Ağları ile Atmosferik Parametreler Kullanılarak Türkiye için Güneş Radyasyonu Modellemesi

Deep Learning Neural Networks Trained with MODIS Satellite-Derived Predictors for Long-Term Global Solar Radiation Prediction

DEM-based Convolutional Neural Network Modeling for Estimation of Solar Irradiation: Comparison of the Effect of DEM Resolutions

Contact Info

Product

Resources

About