Global horizontal and direct normal solar irradiance modeling by the machine learning methods XGBoost and deep neural networks with CNN-LSTM layers: a case study using the GOES-16 satellite imagery

Rocha, Paulo Alexandre Costa; Santos, Victor Oliveira

doi:10.1007/s40095-022-00493-6

Cited by 29 publications

(20 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [86], SHAP analysis showed that forecasting streamflow relies on important precipitation data, besides streamflow inputs, often influencing the mode positively. In Ekmekcio glu et al [87] and Aydin and Iban [88], SHAP analysis showed that precipitation may affect the forecasted result differently depending on the ML model used, which is an expected behavior since different ML approaches process data differently, resulting in different results for an identical task [33,48,49,89].…”

Section: Discussionmentioning

confidence: 98%

“…To overcome the physics-based models' limitations, data-driven models were employed using machine learning (ML) approaches. Researchers studied this paradigm because ML models are simpler, require fewer input parameters, have superior processing times, can solve non-linear relations, and identify the complex relationships between input and output parameters [5,24,33,34].…”

Section: Introductionmentioning

confidence: 99%

“…Another viable approach for DNN models is combining them, resulting in a hybrid model. These models can reach better forecasting results in time-series problems [33,48,49]. A hybrid model was developed by [19], where an attention layer was embedded in the LSTM model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Graph-Based Deep Learning Model to Predict Flooding with Validation on a Case Study on the Humber River

Oliveira Santos,

Costa Rocha,

Scott

et al. 2023

Water

Self Cite

View full text Add to dashboard Cite

Floods are one of the most lethal natural disasters. It is crucial to forecast the timing and evolution of these events and create an advanced warning system to allow for the proper implementation of preventive measures. This work introduced a new graph-based forecasting model, namely, graph neural network sample and aggregate (GNN-SAGE), to estimate river flooding. It then validated the proposed model in the Humber River watershed in Ontario, Canada. Using past precipitation and stage data from reference and neighboring stations, the proposed GNN-SAGE model could estimate the river stage for flooding events up to 24 h ahead, improving its forecasting performance by an average of 18% compared with the persistence model and 9% compared with the graph-based model residual gated graph convolutional network (GNN-ResGated), which were used as baselines. Furthermore, GNN-SAGE generated smaller errors than those reported in the current literature. The Shapley additive explanations (SHAP) revealed that prior data from the reference station was the most significant factor for all prediction intervals, with seasonality and precipitation being more influential for longer-range forecasts. The findings positioned the proposed GNN-SAGE model as a cutting-edge solution for flood forecasting and a valuable resource for devising early flood-warning systems.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Graph-Based Deep Learning Model to Predict Flooding with Validation on a Case Study on the Humber River

Oliveira Santos,

Costa Rocha,

Scott

et al. 2023

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…XGBoost is a supervised learning algorithm proposed by Li in 2019 [57]. XGBoost can predict samples with high uncertainty by creating multiple decision trees [58]. The process of evaluating the suitability of photovoltaic power plant construction is as follows:…”

Section: The Principle Of the Xgboost Distributed Gradient-boosting L...mentioning

confidence: 99%

Evaluation of Site Suitability for Photovoltaic Power Plants in the Beijing–Tianjin–Hebei Region of China Using a Combined Weighting Method

Liang,

Chen,

Chen

et al. 2023

Land

View full text Add to dashboard Cite

As the construction of photovoltaic power plants continues to expand, investors have placed great importance on the suitability assessment of site selection. In this study, we have developed a multi-level evaluation system and proposed an AHP–XGBoost–GIS comprehensive evaluation model for assessing site suitability in the Beijing–Tianjin–Hebei region. The findings revealed that approximately 48,800 km2 (21.59% of the total area) constituted a suitable area in this region, surpassing previous research results. Generally suitable areas accounted for the largest proportion at 35.89%. Suitable areas in Beijing and Tianjin were relatively limited, with most of them concentrated in Baoding City, Zhangjiakou City, and Chengde City on the northwest side of the “Yanshan-Taihang Mountains”, where there are ample wastelands with gentle slopes conducive to constructing photovoltaic power plants southeast of the “Yanshan-Taihang Mountains”, and solar radiation conditions were better. However, ecological and economic factors restricted suitable areas resulting in smaller coverage including cities such as Handan, Xingtai, Qinhuangdao, and Tangshan, among others. This study successfully overcame limitations associated with traditional subjective evaluation methods by providing decision support for regional energy allocation planning and spatial planning efforts, as well as environmental protection endeavors.

show abstract

“…Several statistical approaches, such as analysis methods and statistical techniques, are feasible options for estimating solar radiation using a range of meteorological factors. [7][8][9] Artificial neural network (ANN) technology has recently received much attention as a computational approach that provides an alternative and integrated modelling method, given its ability to deal with complex and ill-defined problems in many scientific fields. In the meteorological field, many researchers have studied the use of single neural network (SNN) models for predicting global solar radiation, as seen in the literature.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Hourly Global Solar Radiation: Comparison of Neural Networks / Bootstrap Aggregating

Dahmani

Ammi

Hanini

et al. 2023

Kemija U Industriji

View full text Add to dashboard Cite

This research work explores the use of single neural networks and bootstrap aggregated neural networks for predicting hourly global solar radiation. A database of 3606 data points were from the Renewable Energies Development Center, radiometric station 'Shems' of Bouzareah. The single neural networks and bootstrap aggregated neural networks were built together. The precision and durability of neural network models generated with an incomplete quantity of training datasets were improved using bootstrap aggregated neural networks. To produce numerous sets of training data points, the training data was re-sampled utilising bootstrap resampling by replacement. A neural network model was built for each of the data points. The individual neural network models were then combined to produce the bootstrap aggregated neural networks. The experimental and predicted values of global solar radiation were compared, and lower root mean squared errors (68.3968 and 62.4856 Wh m −2 ) were discovered during the testing phases for single neural networks and bootstrap aggregated neural networks, respectively. The results of these models show that the bootstrap aggregated neural networks model is more accurate and robust than single neural networks.

show abstract

Global horizontal and direct normal solar irradiance modeling by the machine learning methods XGBoost and deep neural networks with CNN-LSTM layers: a case study using the GOES-16 satellite imagery

Cited by 29 publications

References 54 publications

A New Graph-Based Deep Learning Model to Predict Flooding with Validation on a Case Study on the Humber River

A New Graph-Based Deep Learning Model to Predict Flooding with Validation on a Case Study on the Humber River

Evaluation of Site Suitability for Photovoltaic Power Plants in the Beijing–Tianjin–Hebei Region of China Using a Combined Weighting Method

Prediction of Hourly Global Solar Radiation: Comparison of Neural Networks / Bootstrap Aggregating

Contact Info

Product

Resources

About