A Hybrid Approach of Air Mass Trajectory Modeling and Machine Learning for Acid Rain Estimation DOI Open Access
Chih‐Chiang Wei, Rong Huang

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3429 - 3429

Published: Nov. 28, 2024

This study employed machine learning, specifically deep neural networks (DNNs) and long short-term memory (LSTM) networks, to build a model for estimating acid rain pH levels. The Yangming monitoring station in the Taipei metropolitan area was selected as research site. Based on pollutant sources from air mass back trajectory (AMBT) of HY-SPLIT model, three possible source regions were identified: mainland China Japanese islands under northeast monsoon system (Region C), Philippines Indochina Peninsula southwest R), Pacific Ocean western high-pressure S). Data these used ANN_AMBT model. AMBT provided origin information at different altitudes, leading models 50 m, 500 1000 m (ANN_AMBT_50m, ANN_AMBT_500m, ANN_AMBT_1000m, respectively). Additionally, an ANN based only ground attributes, without (LSTM_No_AMBT), served benchmark. Due monsoon, Taiwan is prone severe events winter, often carrying external pollutants. Results showed that LSTM_AMBT_500m achieved highest percentages improvement rate (MIR), ranging 17.96% 36.53% (average 27.92%), followed by LSTM_AMBT_50m (MIR 12.94% 26.42%, average 21.70%), while LSTM_AMBT_1000m had lowest MIR (2.64% 12.26%, 6.79%). These findings indicate better capture variation trends, reduce prediction errors, improve accuracy forecasting levels during events.

Language: Английский

Prediction of air quality levels to support sustainable development goal – 11 using multiple deep learning classifiers DOI
Jana Shafi,

Ramsha Ijaz,

Yogesh Kumar

et al.

Smart and Sustainable Built Environment, Journal Year: 2025, Volume and Issue: unknown

Published: March 24, 2025

Purpose Sustainable Development Goal (SDG) 11 emphasizes the importance of monitoring air quality to develop cities that are resilient, safe and sustainable on a global scale. Particulate matter pollutants such as PM2.5 PM10 have detrimental impact both human health environment. Traditional methods for assessing often face challenges related scalability accuracy. This paper aims introduce an automated system designed predict levels (AQLs). These categorized good, moderate, unhealthy hazardous, based index. Design/methodology/approach uses dataset 8.1 million records from various US cities. The data undergoes preprocessing remove inconsistencies ensure uniformity. Scaling techniques applied standardize values across dataset. Augmentation methods, including K Nearest Neighbour, z -score normalization Synthetic Minority Oversampling Technique (SMOTE), employed balance enhance Later, used train eight deep learning models, standard, bidirectional stacked architectures. Additionally, two hybrid models also developed by combining features different Findings validation results demonstrate system’s exceptional performance. Bidirectional GRU model achieves highest accuracy 99.98%. Similarly, RNN + impressive 99.92%. Furthermore, Stacked Gated Recurrent Unit stands out, achieving perfect scores 100% precision, recall F1 score. Originality/value assessment approaches rely heavily basic statistical limited scope their datasets. In contrast, this study presents innovative methodology employs advanced By incorporating sophisticated techniques, proposed significantly enhances detection classification AQLs, setting new benchmark development objectives.

Language: Английский

Citations

0
Predicting Surface Ozone Levels in Eastern Croatia: Leveraging Recurrent Fuzzy Neural Networks with Grasshopper Optimization Algorithm DOI
Malik Braik, Alaa Sheta, Elvira Kovač-Andrić

et al.

Water Air & Soil Pollution, Journal Year: 2024, Volume and Issue: 235(10)

Published: Sept. 2, 2024

Language: Английский

Citations

2
The environmental Kuznets curve hypothesis: an ML approach to assessing economic growth and environmental sustainability using artificial neural network DOI

Yunqiu Sun,

Zhiyu Sun,

Zhiman Jiang

et al.

Soft Computing, Journal Year: 2024, Volume and Issue: 28(4), P. 3703 - 3723

Published: Jan. 27, 2024

Language: Английский

Citations

1
AI-based KNN Approaches for Predicting Cooling Loads in Residential Buildings DOI Open Access

Zhaofang Du

International Journal of Advanced Computer Science and Applications, Journal Year: 2024, Volume and Issue: 15(3)

Published: Jan. 1, 2024

Cooling Load (CL) estimation in residential buildings is crucial for optimizing energy consumption and ensuring indoor comfort. This article presents an innovative approach that leverages Artificial Intelligence (AI) techniques, particularly K-Nearest Neighbors (KNN), combination with advanced optimizers, including Dynamic Arithmetic Optimization (DAO) Wild Geese Algorithm (WGA), to enhance the accuracy of CL predictions. The proposed method harnesses power KNN, a machine-learning algorithm renowned its simplicity efficiency regression tasks. By training on historical data relevant building parameters, KNN model can make precise predictions, 768 sample considering factors such as Glazing Area, Area Distribution, Surface Orientation, Overall Height, Wall Roof Relative Compactness. Two state-of-the-art DAO WGA, are introduced refine process further. integration WGA yields robust AI-driven framework proficient constructions. not only enhances by cooling system operations but also contributes sustainable design reduced environmental impact. Through extensive experimentation validation, this study demonstrates effectiveness method, showcasing potential revolutionize buildings. results indicate hybridization optimizers promising outcomes predicting CL. high R2 value 0.996 low RMSE 0.698 demonstrate KNDA model.

Language: Английский

Citations

0
PmForecast: leveraging temporal LSTM to deliver in situ air quality predictions DOI
Maryam Rahmani, Suzanne Crumeyrolle,

Nadége Allegri-Martiny

et al.

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: 31(39), P. 51760 - 51773

Published: Aug. 10, 2024

Language: Английский

Citations

0
A Hybrid Approach of Air Mass Trajectory Modeling and Machine Learning for Acid Rain Estimation DOI Open Access
Chih‐Chiang Wei, Rong Huang

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3429 - 3429

Published: Nov. 28, 2024

This study employed machine learning, specifically deep neural networks (DNNs) and long short-term memory (LSTM) networks, to build a model for estimating acid rain pH levels. The Yangming monitoring station in the Taipei metropolitan area was selected as research site. Based on pollutant sources from air mass back trajectory (AMBT) of HY-SPLIT model, three possible source regions were identified: mainland China Japanese islands under northeast monsoon system (Region C), Philippines Indochina Peninsula southwest R), Pacific Ocean western high-pressure S). Data these used ANN_AMBT model. AMBT provided origin information at different altitudes, leading models 50 m, 500 1000 m (ANN_AMBT_50m, ANN_AMBT_500m, ANN_AMBT_1000m, respectively). Additionally, an ANN based only ground attributes, without (LSTM_No_AMBT), served benchmark. Due monsoon, Taiwan is prone severe events winter, often carrying external pollutants. Results showed that LSTM_AMBT_500m achieved highest percentages improvement rate (MIR), ranging 17.96% 36.53% (average 27.92%), followed by LSTM_AMBT_50m (MIR 12.94% 26.42%, average 21.70%), while LSTM_AMBT_1000m had lowest MIR (2.64% 12.26%, 6.79%). These findings indicate better capture variation trends, reduce prediction errors, improve accuracy forecasting levels during events.

Language: Английский

Citations

0