EXAMINING EFFECTS OF AIR POLLUTION ON PHOTOVOLTAIC SYSTEMS VIA INTERPRETABLE RANDOM FOREST MODEL

Renewable Energy, Год журнала: 2024, Номер 232, С. 121066 - 121066

Опубликована: Окт. 1, 2024

Язык: Английский

---

Enhancing air quality index forecast with string reduction, entropy weight and similarity measure using K-means clustering for fuzzy inference system

Engineering Applications of Computational Fluid Mechanics, Год журнала: 2024, Номер 19(1)

Опубликована: Дек. 11, 2024

This study presents a novel approach to enhance air quality index (AQI) prediction using fuzzy inference system (FIS) model. A significant challenge in FIS models is the exponential increase number of rules with higher inputs, leading increased computational complexity. To address this issue, introduced string reduction entropy weight and similarity measure K-means clustering (SR-EW-SM-KMC) approach. method enhances model accuracy while reducing complexity by leveraging calculate input weights scale point factors determine linguistic values. then used form strings, elbow identifies optimal clusters for clustering. The proposed SR-EW-SM-KMC implemented within MATLAB forecast AQI both regression classification scenarios. Statistical analysis performed against traditional methods without rule (FIS-WORR) model's performance validated metrics: RMSE (0.1342), MSE (0.0180), MAE (0.0955), MAPE (0.23%) methods, (0.1315), (0.0173), (0.0954), (0.29%) FIS-WORR For classification, its assessed confusion matrix ROC analysis, achieving 99% overall compared Furthermore, comparative demonstrates that significantly outperforms existing models, confirming effectiveness accurate efficient prediction. Additionally, method's cluster determination silhouette splitting clusters, ensuring results demonstrate approach's superior reduced complexity, offering robust solution emphasises integration advanced techniques validates determination.

Язык: Английский

---

Spatiotemporal PM2.5 forecasting via dynamic geographical Graph Neural Network

Environmental Modelling & Software, Год журнала: 2025, Номер 186, С. 106351 - 106351

Опубликована: Фев. 6, 2025

Язык: Английский

---

Intelligent Seasonal Air Quality Prediction with Machine Learning Models: Enhancing Performance Through Polynomial Regression and Bayesian Optimization

Communications in computer and information science, Год журнала: 2025, Номер unknown, С. 18 - 35

Опубликована: Янв. 1, 2025

Язык: Английский

---

Comprehensive analysis of various imputation and forecasting models for predicting PM2.5 pollutant in Delhi

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Март 19, 2025

Язык: Английский

---

Forecasting the concentration of the components of the particulate matter in Poland using neural networks

Environmental Science and Pollution Research, Год журнала: 2025, Номер unknown

Опубликована: Март 21, 2025

Язык: Английский

---

Machine Learning Algorithms for Forecasting Air Quality Index: A Predictive Analysis in theTaj Trapezium Zone (TTZ) of Agra

Опубликована: Апрель 9, 2025

Clean air is vital for sustaining life, and its quality directly impacts health. As industrialization progresses populations grow, pollution has become increasingly prevalent, emerging as a significant societal challenge. Air wide-ranging negative on human health, including increased risk of early death various ailments such skin irritation., pulmonary infections, respiratory ailments, pneumonia, lung cancer, cardiac complications. The purpose this study to use machine learning algorithms predict the Taj Trapezium Zone’s index. Such predictions can inform preventive action mitigate pollution. compares four algorithmic approaches: Light Gradient Boosting Machine (LightGBM), categorical boosting (Catboost), adaptive (AdaBoost), extreme gradient (XGBoost). This algorithm’s performance evaluated based several parameters, R-SQUARE, Mean Squared Error (MSE), Root (RMSE), ((MAE).

Язык: Английский

---

Research on AQI prediction of Chengdu-Chongqing economic circle based on CNN-BiLSTM-Selfattention model

E3S Web of Conferences, Год журнала: 2025, Номер 625, С. 03017 - 03017

Опубликована: Янв. 1, 2025

Air pollution has emerged as a significant environmental challenge worldwide. The Chengdu- Chongqing economic circle is central to regional development in China. Research into predicting air quality aims support sustainable efforts China and across the globe. Due chaotic, disordered, non-stationary nature of Quality Index (AQI) data, traditional statistical forecasting models are inadequate for AQI predictions. Therefore, this study focuses on 16 cities at or above prefecture level within Chengdu-Chongqing identifies six major pollutants, including PM2.5, PM10, carbon monoxide (CO), sulfur dioxide (SO2), key contributors levels. To analyze data characteristics, K-Shape clustering method initially employed categorize circle. Following this, CNN-BiLSTM-Selfattention prediction model developed, integrating CNN, BiLSTM, Selfattention forecast both high- representative low-representative region. Additionally, performance CNN- BiLSTM-Selfattention compared with that BiLSTM model, CNN-LSTM validate its accuracy. Finally, utilized project over an eight-day period from November 12, 2023, 19, 2023. findings indicate that: (1) Utilizing technique, Chengdu Neijiang emerge high representation region, whereas Yibin Luzhou identified low representation. (2) A comparison RMSE, MSE, MAPE, MAE, R2 values four reveals demonstrates superior accuracy enhanced stability. (3) analysis suggests while certain days experience circle, overall exhibits trend towards improvement, indices most areas remaining below 3.

Язык: Английский

---

Geographically Aware Air Quality Prediction Through CNN-LSTM-KAN Hybrid Modeling with Climatic and Topographic Differentiation

Atmosphere, Год журнала: 2025, Номер 16(5), С. 513 - 513

Опубликована: Апрель 28, 2025

Air pollution poses a pressing global challenge, particularly in rapidly industrializing nations like China where deteriorating air quality critically endangers public health and sustainable development. To address the heterogeneous patterns of across diverse geographical climatic regions, this study proposes novel CNN-LSTM-KAN hybrid deep learning framework for high-precision Quality Index (AQI) time-series prediction. Through systematic analysis multi-city AQI datasets encompassing five representative Chinese metropolises—strategically selected to cover climate zones (subtropical temperate), gradients (coastal inland), topographical variations (plains mountains)—we established three principal methodological advancements. First, Shapiro–Wilk normality testing (p < 0.05) revealed non-Gaussian distribution characteristics observational data, providing statistical justification implementing Gaussian filtering-based noise suppression. Second, our multi-regional validation extended beyond conventional single-city approaches, demonstrating model generalizability distinct environmental contexts. Third, we innovatively integrated Kolmogorov–Arnold Networks (KANs) with attention mechanisms replace traditional fully connected layers, achieving enhanced feature weighting capacity. Comparative experiments demonstrated superior performance 23.6–59.6% reduction Root-Mean-Square Error (RMSE) relative baseline LSTM models, along consistent outperformance over CNN-LSTM hybrids. Cross-regional correlation analyses identified PM2.5/PM10 as dominant predictive factors. The developed exhibited robust generalization capabilities divisions (R2 = 0.92–0.99), establishing reliable decision-support platform regionally adaptive early-warning systems. This provides valuable insights addressing spatial heterogeneity modeling applications.

Язык: Английский

---

Air Quality Prediction Model Based on BP Neural Network and LSTM

Highlights in Science Engineering and Technology, Год журнала: 2025, Номер 141, С. 147 - 155

Опубликована: Май 23, 2025

This article uses monthly observation data from national level ground meteorological stations in Beijing 2014 to 2022, and LSTM model ARIMA time series predict the of air quality index factor indicators. A BP neural network is used construct a prediction for Beijing's index. By comparing predicted Air Quality Index (AQI) with actual data, accuracy model's AQI over 95%, indicating relatively accurate accuracy. It can be predicting Beijing. Provide technical support environmental governance

Язык: Английский

---