AI-Driven Forecasting of PM10 Concentrations in the Republic of Ireland: Integrating Machine Learning for Urban Air Quality Prediction

Aerosol Science and Engineering, Год журнала: 2025, Номер unknown

Опубликована: Май 26, 2025

Abstract This study introduces artificial intelligence models for the first time in Republic of Ireland to forecast particulate matter (PM 10 ). By integrating local environmental data with cutting-edge predictive algorithms, this research specifically targets high-impact urban areas Ireland. The not only account complex air quality temporal patterns and meteorological variables but also introduce region-specific calibrations that have been explored previous studies. Several state-of-the-art machine learning models: such as XGBoost, CatBoost, ANN, LSTM, Bi an adaptable Ensemble model are trained using available data. Interestingly, climatic a minimum impact on PM concentrations tested However, they show good correlations 2.5 NO 2 concentration levels. performance is widely accepted indicators (Coefficient Determination, Root Mean Square Error, Squared Absolute Error). Based outcome models, next 24 h presented. findings can be effectively used enhance policy decisions minimize expected rising pollution levels future.

Язык: Английский

---

Predictive Analysis of Air Quality Index (AQI) and Identification of Influential Factors Using Machine Learning Models

Springer proceedings in energy, Год журнала: 2025, Номер unknown, С. 131 - 142

Опубликована: Янв. 1, 2025

Язык: Английский

---

Thermal Load Predictions in Low-Energy Buildings: A Hybrid AI-Based Approach Integrating Integral Feature Selection and Machine Learning Models

Applied Sciences, Год журнала: 2025, Номер 15(11), С. 6348 - 6348

Опубликована: Июнь 5, 2025

A hybrid Artificial Intelligence (AI) framework centered on metamodeling, integrating simulation data with data-driven techniques, was implemented to enhance the predictive accuracy and optimization of thermal load projections in three distinct climates Morocco. Initially, 13 machine learning (ML) models were assessed predict heating cooling loads. The best-performing from this stage then selected for subsequent phase find out optimal combinations inputs In phase, an Integral Feature Selection (IFS) method employed conjunction best ML models. An extensive evaluation using advanced statistical measures performed during stage. results reveal that, each climate, numerous high-accuracy prediction pathways identified prediction, surpassing confidence level 99% R2. found here outperformed those reported by other researchers predictions Low-Energy Buildings (LEBs).

Язык: Английский

---

A novel approach to forecast dust concentration in open pit mines by integrating meteorological parameters and production intensity

Environmental Science and Pollution Research, Год журнала: 2023, Номер 30(53), С. 114591 - 114609

Опубликована: Окт. 20, 2023

Язык: Английский

---

Data analysis and preprocessing techniques for air quality prediction: a survey

Stochastic Environmental Research and Risk Assessment, Год журнала: 2024, Номер 38(6), С. 2095 - 2117

Опубликована: Март 18, 2024

Язык: Английский

---