Ensemble Machine Learning of Gradient Boosting (XGBoost, LightGBM, CatBoost) and Attention-Based CNN-LSTM for Harmful Algal Blooms Forecasting

Toxins, Journal Year: 2023, Volume and Issue: 15(10), P. 608 - 608

Published: Oct. 10, 2023

Harmful algal blooms (HABs) are a serious threat to ecosystems and human health. The accurate prediction of HABs is crucial for their proactive preparation management. While mechanism-based numerical modeling, such as the Environmental Fluid Dynamics Code (EFDC), has been widely used in past, recent development machine learning technology with data-based processing capabilities opened up new possibilities prediction. In this study, we developed evaluated two types learning-based models prediction: Gradient Boosting (XGBoost, LightGBM, CatBoost) attention-based CNN-LSTM models. We Bayesian optimization techniques hyperparameter tuning, applied bagging stacking ensemble obtain final results. result was derived by applying optimal techniques, applicability evaluated. When predicting an technique, it judged that overall performance can be improved complementing advantages each model averaging errors overfitting individual Our study highlights potential emphasizes need incorporate latest into important field.

Language: Английский

---

Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction

Alexandria Engineering Journal, Journal Year: 2025, Volume and Issue: 118, P. 664 - 680

Published: Jan. 29, 2025

Language: Английский

---

Early bruise detection, classification and prediction in strawberry using Vis-NIR hyperspectral imaging

Food Control, Journal Year: 2024, Volume and Issue: 167, P. 110794 - 110794

Published: Aug. 10, 2024

Language: Английский

---

Predictive models of beetroot solar drying process through machine learning algorithms

Renewable Energy, Journal Year: 2023, Volume and Issue: 219, P. 119522 - 119522

Published: Oct. 26, 2023

Language: Английский

---

Employing machine learning for advanced gap imputation in solar power generation databases

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 11, 2024

This research evaluates the application of advanced machine learning algorithms, specifically Random Forest and Gradient Boosting, for imputation missing data in solar energy generation databases their impact on size green hydrogen production systems. The study demonstrates that model notably excels harnessing to optimize production, achieving superior prediction accuracy with mean absolute error (MAE) 0.0364, squared (MSE) 0.0097, root (RMSE) 0.0985, a coefficient determination (R2) 0.9779. These metrics surpass those obtained from baseline models including linear regression recurrent neural networks, highlighting potential accurate significantly enhance efficiency output renewable findings advocate integration robust methods design operation photovoltaic systems, contributing reliability sustainability resource management. Furthermore, this makes significant contributions by showcasing comparative performance traditional handling gaps, emphasizing practical implications optimizing By providing detailed analysis validation models, work offers valuable insights future advancements technology.

Language: Английский

---

Development of machine learning based model for low-temperature PEM fuel cells

Computers & Chemical Engineering, Journal Year: 2024, Volume and Issue: 188, P. 108754 - 108754

Published: June 12, 2024

Language: Английский

---

Solar energy prediction through machine learning models: A comparative analysis of regressor algorithms

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0315955 - e0315955

Published: Jan. 2, 2025

Solar energy generated from photovoltaic panel is an important source that brings many benefits to people and the environment. This a growing trend globally plays increasingly role in future of industry. However, it intermittent nature potential for distributed system use require accurate forecasting balance supply demand, optimize storage, manage grid stability. In this study, 5 machine learning models were used including: Gradient Boosting Regressor (GB), XGB (XGBoost), K-neighbors (KNN), LGBM (LightGBM), CatBoost (CatBoost). Leveraging dataset 21045 samples, factors like Humidity, Ambient temperature, Wind speed, Visibility, Cloud ceiling Pressure serve as inputs constructing these solar energy. Model accuracy meticulously assessed juxtaposed using metrics such coefficient determination (R 2 ), Root Mean Square Error (RMSE), Absolute (MAE). The results show model emerges frontrunner predicting energy, with training values R value 0.608, RMSE 4.478 W MAE 3.367 testing 0.46, 4.748 3.583 W. SHAP analysis reveal ambient temperature humidity have greatest influences on panel.

Language: Английский

---

Deep learning approaches for robust prediction of large-scale renewable energy generation: A comprehensive comparative study from a national context

Intelligent Data Analysis, Journal Year: 2025, Volume and Issue: unknown

Published: March 19, 2025

Precise forecasting of renewable energy generation is crucial for ensuring grid stability and enhancing the efficiency management systems. This research develops rigorously evaluates a range deep learning models—such as Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Gated Units (GRUs), Bidirectional LSTM (BiLSTM) architectures—for predicting solar, wind, total production at national scale. These models are systematically benchmarked against traditional machine approaches gradient boosting methods to determine their predictive capabilities. The findings demonstrate that incorporating memory mechanisms consistently surpass conventional methods, with BiLSTM standing out most precise dependable model. Furthermore, study investigates fully connected artificial neural networks (ANNs) ConvLSTM2D models, reinforcing advantages memory-based architectures in modeling temporal relationships. By introducing robust framework large-scale forecasting, this represents considerable leap forward compared techniques. results highlight transformative potential improving accuracy, thereby facilitating more effective planning smooth integration into power grids.

Language: Английский

---

Forecasting rooftop photovoltaic solar power using machine learning techniques

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 3616 - 3630

Published: March 22, 2025

Language: Английский

---

Unlocking renewable energy potential: Harnessing machine learning and intelligent algorithms

International Journal of Renewable Energy Development, Journal Year: 2024, Volume and Issue: 13(4), P. 783 - 813

Published: June 7, 2024

This review article examines the revolutionary possibilities of machine learning (ML) and intelligent algorithms for enabling renewable energy, with an emphasis on energy domains solar, wind, biofuel, biomass. Critical problems such as data variability, system inefficiencies, predictive maintenance are addressed by integration ML in systems. Machine improves solar irradiance prediction accuracy maximizes photovoltaic performance sector. help to generate electricity more reliably enhancing wind speed forecasts turbine efficiency. efficiency biofuel production optimizing feedstock selection, process parameters, yield forecasts. Similarly, models biomass provide effective thermal conversion procedures real-time management, guaranteeing increased operational stability. Even enormous advantages, quality, interpretability models, computing requirements, current systems still remain. Resolving these issues calls interdisciplinary cooperation, developments computer technology, encouraging legislative frameworks. study emphasizes vital role promoting sustainable efficient giving a thorough present applications highlighting continuing problems, outlining future prospects

Language: Английский

---