Machine learning regressors for solar radiation estimation from satellite data

Cornejo-Bueno, Laura; Casanova-Mateo, C.; Sanz-Justo, J.; Salcedo‐Sanz, Sancho

doi:10.1016/j.solener.2019.03.079

Cited by 105 publications

(39 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For overcast conditions, surface solar irradiance does not reach its maximum value in diurnal variation, and the variation is mainly caused by the persistent presence of clouds [42,43].…”

Section: Results Under Overcast Conditionsmentioning

confidence: 99%

“…For overcast conditions, surface solar irradiance does not reach its maximum value in diurnal variation, and the variation is mainly caused by the persistent presence of clouds [42,43]. Figure 6 presents the forecasted results for the selected three days (108 samples) of global solar irradiance under overcast days with a 60 min horizon.…”

Section: Results Under Overcast Conditionsmentioning

confidence: 99%

See 1 more Smart Citation

Nowcasting of Surface Solar Irradiance Using FengYun-4 Satellite Observations over China

Yang

Gao

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

The accurate prediction of surface solar irradiance is of great significance for the generation of photovoltaic power. Surface solar irradiance is affected by many random mutation factors, which means that there are great challenges faced in short-term prediction. In Northwest China, there are abundant solar energy resources and large desert areas, which have broad prospects for the development of photovoltaic (PV) systems. For the desert areas in Northwest China, where meteorological stations are scarce, satellite remote sensing data are extremely precious exploration data. In this paper, we present a model using FY-4A satellite images to forecast (up to 15–180 min ahead) global horizontal solar irradiance (GHI), at a 15 min temporal resolution in desert areas under different sky conditions, and compare it with the persistence model (SP). The spatial resolution of the FY-4A satellite images we used was 1 km × 1 km. Particle image velocimetry (PIV) was used to derive the cloud motion vector (CMV) field from the satellite cloud images. The accuracy of the forecast model was evaluated by the ground observed GHI data. The results showed that the normalized root mean square error (nRMSE) ranged from 18.9% to 21.6% and the normalized mean bias error (nMBE) ranged from 3.2% to 4.9% for time horizons from 15 to 180 min under all sky conditions. Compared with the SP model, the nRMSE value was reduced by about 6%, 8%, and 14% with the time horizons of 60, 120, and 180 min, respectively.

show abstract

“…For overcast conditions, surface solar irradiance does not reach its maximum value in diurnal variation, and the variation is mainly caused by the persistent presence of clouds [42,43].…”

Section: Results Under Overcast Conditionsmentioning

confidence: 99%

Section: Results Under Overcast Conditionsmentioning

confidence: 99%

Nowcasting of Surface Solar Irradiance Using FengYun-4 Satellite Observations over China

Yang

Gao

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…For example, Duke University Energy Data Analytics Lab researchers recently developed machine learning models that automate the identification of DG solar and wind resources using open access EO and other data 17 . Most other research in this field is primarily focused on the automation and validation of solar nowcasting and forecasting using machine learning methods based on satellite images to accurately predict fluctuating meteorological conditions and PV output (Eissa et al, 2013;Jang et al, 2016;Catalina et al, 2019;Cornejo-Bueno et al, 2019).…”

Section: State Of Researchmentioning

confidence: 99%

Using Earth Observations to Help Developing Countries Improve Access to Reliable, Sustainable, and Modern Energy

Leibrand

Sadoff

Maslak

et al. 2019

Front. Environ. Sci.

View full text Add to dashboard Cite

In this review paper, the authors identify priority areas, and opportunities for electric utilities in developing and emerging economies to incorporate Earth observation (EO) data into rural electrification planning, renewable energy resource assessment, distributed generation, grid operation and reliability, and disaster risk reduction and recovery efforts. Using a methodological framework, the authors conducted a comprehensive literature review of primary and gray literature. This paper reviews the many existing applications for EO data, such as the use of nighttime lights imagery for estimations of rural electrification, EO-derived normalized difference vegetation index (NDVI) products for vegetation monitoring for overhead transmission line management, solar radiance data for renewable energy project planning, and nowcasting for extreme weather events and other disaster monitoring. These and other applications can enhance energy security through improved governance of and access to modern and reliable electricity, renewable energy management, and disaster risk assessment in developing nations, paving the way for more sustainable social and economic development. Real-world examples of EO data use by utilities in developing and emerging economies, as well as barriers and opportunities for EO technology transfer, are discussed. Recommendations for stakeholder engagement, future EO training opportunities, and human capacity building are also presented.

show abstract

“…This limited learning of the model leads to the poor performance of the model. To overcome this problem, hybrid models has been developed such as: PLA-k-means-HGWO-RF (Liu and Sun 2019 ), ANFIS-ANN (Kumar and Kalavathi 2018 ), ECMWF-ANN (Aguiar et al 2016 ), SVM-RBF-WT (Shamshirband et al 2016 ), WT-NNMFOA-GMDHMFOA (Heydari et al 2019 ), WMIM-ELM (Cornejo-Bueno et al 2019 ), LASSO-ANN (Huang et al 2019 ) etc.…”

Section: Introductionmentioning

confidence: 99%

An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network

2021

View full text Add to dashboard Cite

Machine learning regressors for solar radiation estimation from satellite data

Cited by 105 publications

References 30 publications

Nowcasting of Surface Solar Irradiance Using FengYun-4 Satellite Observations over China

Nowcasting of Surface Solar Irradiance Using FengYun-4 Satellite Observations over China

Using Earth Observations to Help Developing Countries Improve Access to Reliable, Sustainable, and Modern Energy

An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network

Contact Info

Product

Resources

About