Solar Radiation Forecasting Based on the Hybrid CNN-CatBoost Model

Kim, Hyojeoung; Park, Su‐Jin; Park, Hee-Jun; Son, Heung-Gu; Kim, Sahm

doi:10.1109/access.2023.3243252

Cited by 22 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, compared with the single crop coefficient model, the machine learning model can use the entire data set for training, minimize information loss, and still provide high prediction accuracy in the case of missing variables. Kim et al [32] proposed a CNN-CatBoost hybrid model solar radiation prediction method and concluded that the prediction accuracy and stability of this hybrid model is better than the single model of CNN and CatBoost; Niu et al [33] introduced a machine learning method based on wavelet packet denoising and CatBoost for weather forecasting. Using a feature selection and spatio-temporal feature addition to improve forecasting performance, the results show that the CatBoost model combined with wavelet packet denoising can achieve shorter convergence time and higher forecasting accuracy than forecasting models using deep learning or machine learning algorithms alone.…”

Section: Discussionmentioning

confidence: 99%

A Hybrid Prediction Model for CatBoost Tomato Transpiration Rate Based on Feature Extraction

Tong,

Zhang,

et al. 2023

Agronomy

View full text Add to dashboard Cite

The growth and yield of crops are highly dependent on irrigation. Implementing irrigation plans that are tailored to the specific water requirements of crops can enhance crop yield and improve the quality of tomatoes. The mastery and prediction of transpiration rate (Tr) is of great significance for greenhouse crop water management. However, due to the influence of multiple environmental factors and the mutual coupling between environmental factors, it is challenging to construct accurate prediction models. This study focuses on greenhouse tomatoes and proposes a data-driven model configuration based on the Competitive adaptive reweighted sampling (CARS) algorithm, using greenhouse environmental sensors that collect six parameters, such as air temperature, relative humidity, solar radiation, substrate temperature, light intensity, and CO2 concentration. In response to the differences in crop transpiration changes at different growth stages and time stages, the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm was used to identify three characteristic intervals: florescence stage, fruiting stage daytime, and fruiting stage night-time. Based on this, a greenhouse tomato Tr prediction model (CARS-CatBoost model) based on the CatBoost machine learning algorithm was constructed. The experimental verification shows that the coefficient of determination (R2) of the constructed CARS-CatBoost single model for the whole growth stage is 0.92, which is higher than the prediction accuracy of the traditional single crop coefficient model (R2 = 0.54). Among them, the prediction accuracy at night during the fruiting stage is the highest, and the Root Mean Square Error (RMSE) drops to 0.427 g·m−2·h−1. This study provides an intelligent prediction method based on the zonal modeling of crop growth characteristics, which can be used to support precise irrigation regulation of greenhouse tomatoes.

show abstract

Section: Discussionmentioning

confidence: 99%

A Hybrid Prediction Model for CatBoost Tomato Transpiration Rate Based on Feature Extraction

Tong,

Zhang,

et al. 2023

Agronomy

View full text Add to dashboard Cite

show abstract

“…Although their combined approach enhanced forecasting performance, the complexity of integrating various forecasting models may pose challenges for implementation and interpretation operations. Kim et al [12] applied a Hybrid CNN-CatBoost Model for solar radiation forecasting, achieving high accuracy. However, the validation of this model is limited to specific weather conditions, potentially constraining its generalizability to diverse environmental settings.…”

Section: In-depth Review Existing Modelsmentioning

confidence: 99%

Design of an Iterative Method for Optimizing Solar Power Systems using Quad LSTM with IoT Integration Operations

Swapna Choudhary

2024

jes

View full text Add to dashboard Cite

The growing necessity for sustainable energy solutions underscores the critical need for optimizing solar power systems. Existing methodologies predominantly focus on static strategies with limited adaptability to dynamic environmental and operational conditions, often resulting in suboptimal performance and inefficiency. This research introduces a comprehensive, integrated framework employing Internet of Things (IoT) technologies alongside advanced machine learning and deep learning methodologies to enhance solar power system efficiency and reliability levels. The proposed model integrates four key components: predictive maintenance using Support Vector Machines (SVM) for enhanced anomaly detection, solar power forecasting via Quad Long Short-Term Memory (QLSTM) neural networks, dynamic load balancing through Reinforcement Learning with Deep Q-learning, and the integration with smart grids employing Decentralized Multi-Agent Systems (MAS) with Auction-Based Mechanisms. Each method is selected based on its suitability to address specific challenges within the solar power domain: SVMs for their effectiveness in high-dimensional anomaly detection, QLSTMs for their superior temporal pattern recognition in forecasting, Deep Q-learning for its adaptability in dynamic load management, and MAS for efficient decentralized energy resource coordination operations. The implementation of these methodologies demonstrates significant advancements over traditional approaches. Predictive maintenance facilitated by SVMs leads to a 20% reduction in maintenance costs, while QLSTM-based forecasting achieves a 95% accuracy rate, thereby enhancing grid management and reducing revenue losses. Moreover, reinforcement learning optimizes energy utilization, decreasing wastage and system downtime by 10% and 5% respectively. Lastly, the MAS framework promotes a 20% increase in energy trading efficiency, yielding a 10% reduction in transaction costs and bolstering grid resilience levels. This work represents a significant leap forward in solar power optimization, offering a scalable, efficient, and intelligent framework that paves the way for more sustainable and reliable energy systems. The integration of IoT with machine learning and deep learning presents a paradigm shift in renewable energy management, marking a critical step toward achieving global sustainability objectives..

show abstract

“…Compared to the popular bagging (i.e., Random Forest) and other boosting (i.e., Extreme Gradient Boost, Light Gradient Boosting Machine) methods, CB returns reliable performance with fewer hyperparameters, which is claimed as the advantage of the ordered boosting tree approach and the L2 parameter regularization parameter (Prokhorenkova et al, 2018). The novel decision tree approaches introduced in CB help reduce overestimation, and improve prediction accuracy for any given dataset (Fan et al, 2018;Kim et al, 2023). In this study, we validate the performance of CB machine learning in (1) evaluating the relationship between environmental and ecological factors and the distribution of Indo-Pacific eels (A. marmorata) in central Vietnam and (2) comparison with a multivariate linear model to estimate the growth of Indo-Pacific eel (A. marmorata) in length across different stages of development.…”

Section: Introductionmentioning

confidence: 99%

Detection And Growth Estimation Of Indo–Pacific Eel (Anguilla marmorata Quoy & Gaimard, 1824) Using Machine Learning In Central Vietnam

Huyen,

Thang,

Linh

2024

JAZ

View full text Add to dashboard Cite

Context. The Indo-Pacific eel (Anguilla marmorata) is a widely distributed and commercially valuable species across ecological regions worldwide. Overfishing and habitat loss are leaving the Indo-Pacific eel in a risky situation and raising a high demand for conservation. Previous research has found relationships between the Indo-Pacific eel's migration patterns and environmental factors. However, there is still a need to advance the discovery of its spatial distribution by using diverse environmental and ecological datasets and modelling its growth in terms of different environmental characterizations. Aims & Methods. Here, we compared machine learning (ML) CatBoost (CB) and the multivariate linear model to investigate the relationship between spatial distribution, Indo-Pacific eel development stages, and environmental factors in central Vietnam. Key results. Our results show that CB detected the Indo-Pacific eel at high accuracy (Overall Accuracy (OA) = 0.9, F1 = 0.88, AUC = 0.97) and estimated the total length at different confidence levels (R2 ranging from 0.51 to 0.70), demonstrating superior performance to the multivariate linear model. Conclusions & implications.This study highlights the potential use of ML models in species distribution mapping and modelling growth patterns to support conservation efforts of Indo-Pacific eels in their natural habitats.

show abstract

Solar Radiation Forecasting Based on the Hybrid CNN-CatBoost Model

Cited by 22 publications

References 25 publications

A Hybrid Prediction Model for CatBoost Tomato Transpiration Rate Based on Feature Extraction

A Hybrid Prediction Model for CatBoost Tomato Transpiration Rate Based on Feature Extraction

Design of an Iterative Method for Optimizing Solar Power Systems using Quad LSTM with IoT Integration Operations

Detection And Growth Estimation Of Indo–Pacific Eel (Anguilla marmorata Quoy & Gaimard, 1824) Using Machine Learning In Central Vietnam

Contact Info

Product

Resources

About