Multi-head attention-based probabilistic CNN-BiLSTM for day-ahead wind speed forecasting

Energy, Journal Year: 2023, Volume and Issue: 278, P. 127865 - 127865

Published: May 17, 2023

Language: Английский

---

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

---

A Critical Review of RNN and LSTM Variants in Hydrological Time Series Predictions

MethodsX, Journal Year: 2024, Volume and Issue: 13, P. 102946 - 102946

Published: Sept. 12, 2024

Language: Английский

---

Interpretable predictive modelling of outlet temperatures in Central Alberta’s hydrothermal system using boosting-based ensemble learning incorporating Shapley Additive exPlanations (SHAP) approach

Energy, Journal Year: 2025, Volume and Issue: unknown, P. 134738 - 134738

Published: Jan. 1, 2025

Language: Английский

---

ITF-WPI: Image and text based cross-modal feature fusion model for wolfberry pest recognition

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 212, P. 108129 - 108129

Published: Aug. 10, 2023

Language: Английский

---

Mass Flow Rate Measurement of Pneumatically Conveyed Solids in a Square-Shaped Pipe Through Multisensor Fusion and Data-Driven Modeling

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2023, Volume and Issue: 72, P. 1 - 12

Published: Jan. 1, 2023

Online continuous measurement of the mass flow rate pneumatically conveyed solids in a square-shaped pipe is desirable for monitoring and optimizing industrial processes. However, existing techniques using single type sensor have limitations measuring because complexity dynamics due to four sharp corners pipe. This paper proposes multi-sensor fusion data-driven modelling-based method tackle this challenge. A system based on acoustic, capacitive, electrostatic sensing principles designed implemented obtain sound pressure level flow, volumetric concentration solids, velocity, respectively. Simultaneously, range statistical features obtained by performing time-domain, frequency-domain, time-frequency domain analyses all signals. The reflecting variation as well velocity volume are then fed into model. model combined convolutional neural network long short-term memory (CNN-LSTM) established, its performance compared with those back-propagation artificial network, support vector machine, CNN, LSTM models. Experimental tests were conducted laboratory-scale rig both horizontal vertical pipelines train evaluate CNN-LSTM ranging from 11 23 m/s 8 26 kg/h. outperforms other models relative error within ±1% under test conditions.

Language: Английский

---

An Overview of Emerging and Sustainable Technologies for Increased Energy Efficiency and Carbon Emission Mitigation in Buildings

Buildings, Journal Year: 2023, Volume and Issue: 13(10), P. 2658 - 2658

Published: Oct. 22, 2023

The building sector accounts for a significant proportion of global energy usage and carbon dioxide emissions. It is important to explore technological advances curtail support the transition sustainable future. This study provides an overview emerging technologies strategies that can assist in achieving decarbonization. main reviewed include uncertainty-based design, renewable integration buildings, thermal storage, heat pump technologies, sharing, retrofits, demand flexibility, data-driven modeling, improved control, grid-buildings integrated control. review results indicated these showed great potential reducing operating costs footprint. synergy among area should be explored. An appropriate combination help achieve grid-responsive net-zero which anticipated one best options simultaneously reduce emissions, consumption, costs, as well dynamic supply conditions energy-powered grids. However, unlock full collaborative efforts between different stakeholders are needed facilitate their deployment on larger wider scale.

Language: Английский

---

Machine-learning-based performance prediction of the energy pile heat pump system

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 77, P. 107442 - 107442

Published: July 25, 2023

Language: Английский

---

An analytical model for predicting outlet fluid temperatures in energy piles using soil thermal resistances

Applied Thermal Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 125557 - 125557

Published: Jan. 1, 2025

Language: Английский

---

Performance prediction of a ground source heat pump system using denoised long short-term memory neural network optimised by fast non-dominated sorting genetic algorithm-II

Geothermics, Journal Year: 2024, Volume and Issue: 120, P. 103002 - 103002

Published: March 22, 2024

Language: Английский

---