A PM2.5 Concentration Prediction in High-Cost and Low-Cost Wireless Sensor Networks Using Neural Networks DOI
Marko Marković,

Đorđe Nešković,

Lara Kašca

и другие.

2021 15th International Conference on Advanced Technologies, Systems and Services in Telecommunications (TELSIKS), Год журнала: 2023, Номер unknown, С. 151 - 154

Опубликована: Окт. 25, 2023

Due to its increasing impact on human health, air pollution is becoming a progressively important topic in modern society. Particulate matter with diameter of 2.5 μm cited as one the main pollutants. Thus, prediction concentration these particles presents very research topic. Therefore, this paper, we observed Deep Learning based spatial realized by using installed high-cost sensors and/or low-cost sensors, which are simulated. Based obtained analysis results, proposal was made employ completely or partially, distributed Neural Networks, instead currently used wireless sensor network for PM2.5 measuring. It shown that way can lower complexity, datasets and time training without loss (or even gain) quality.

Язык: Английский

Application of the Lasso regularisation technique in mitigating overfitting in air quality prediction models DOI Creative Commons
Abbas Pak,

Abdullah Kaviani Rad,

Mohammad Javad Nematollahi

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 2, 2025

Язык: Английский

Процитировано

4
Long-Term Retrospective Predicted Concentration of PM2.5 in Upper Northern Thailand Using Machine Learning Models DOI Creative Commons
Sawaeng Kawichai, Patumrat Sripan, Amaraporn Rerkasem

и другие.

Toxics, Год журнала: 2025, Номер 13(3), С. 170 - 170

Опубликована: Фев. 27, 2025

This study aims to build, for the first time, a model that uses machine learning (ML) approach predict long-term retrospective PM2.5 concentrations in upper northern Thailand, region impacted by biomass burning and transboundary pollution. The dataset includes PM10 levels, fire hotspots, critical meteorological data from 1 January 2011 31 December 2020. ML techniques, namely multi-layer perceptron neural network (MLP), support vector (SVM), multiple linear regression (MLR), decision tree (DT), random forests (RF), were used construct prediction models. best was selected considering root mean square error (RMSE), (MPE), relative (RPE) (the lower, better), coefficient of determination (R2) bigger, better). Our found model-based RF technique using PM10, CO2, O3, air pressure, rainfall, humidity, temperature, wind direction, speed performs when predicting concentration with an RMSE 6.82 µg/m3, MPE 4.33 RPE 22.50%, R2 0.93. this research could further studies effects on human health related issues.

Язык: Английский

Процитировано

2
Trend-attribute forecasting of hourly PM2.5 trends in fifteen cities of Central England applying optimized machine learning feature selection DOI
David A. Wood

Journal of Environmental Management, Год журнала: 2024, Номер 356, С. 120561 - 120561

Опубликована: Март 12, 2024

Язык: Английский

Процитировано

8
A novel ensemble machine learning method for accurate air quality prediction DOI
Murat Emeç, Mustafa Yurtsever

International Journal of Environmental Science and Technology, Год журнала: 2024, Номер unknown

Опубликована: Май 6, 2024

Язык: Английский

Процитировано

7
Apply a deep learning hybrid model optimized by an Improved Chimp Optimization Algorithm in PM2.5 prediction DOI Creative Commons
Ming Wei,

Xiaopeng Du

Machine Learning with Applications, Год журнала: 2025, Номер unknown, С. 100624 - 100624

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
Explainable deep learning hybrid modeling framework for total suspended particles concentrations prediction DOI
Sujan Ghimire, Ravinesh C. Deo, Ningbo Jiang

и другие.

Atmospheric Environment, Год журнала: 2025, Номер unknown, С. 121079 - 121079

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
PM 2.5 Concentration 7-days Prediction in the Beijing-Tianjin-Hebei Region Using a Novel Stacking Framework DOI Creative Commons

Xintong Gao,

Xiaohong Wang,

Fuping Li

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Фев. 17, 2025

Abstract High-precision prediction of near-surface PM2.5 concentration is an significant theoretical prerequisite for effective monitoring and prevention air pollution, also provides guiding suggestions health risk control. In view the fact that control variables existing models are mostly dependent on influencing factors at near-surface, it often difficult to fully explore continuous spatio-temporal characteristics in PM2.5. this study, MODIS remote sensing-derived Aerosol Optical Depth (AOD) daily data, atmospheric environment ground station data meteorological introduced identify strong correlation factors. A highly robust seven-day model constructed based Stacking algorithm combined with various machine learning methods improve generalisation ability model; estimation integrated compared analyzed LSTM, RF KNN models. The results demonstrated basis RF-LSTM-Stacking exhibited a better fit, R², RMSE, MAE values 0.95, 7.74 µg/m³, 6.08 respectively. This approach improved accuracy by approximately 17% single model. Based was evident LSTM-RF model, fusion-based algorithm, significantly enhanced provided reference predicting early warning monitoring.

Язык: Английский

Процитировано

0
Nationwide Machine Learning-Ensemble PM2.5 Mapping Prediction and Forecasting Models in South Korea with High Spatiotemporal Resolution and Health Risk Estimation-Based Evaluations DOI Creative Commons
Seoyeong Ahn, Ayoung Kim, Yeonseung Chung

и другие.

Environment & Health, Год журнала: 2025, Номер unknown

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0
Mapping trends and analyzing key themes in low-cost sensors for air quality monitoring DOI
Kemal Maulana Alhasa,

Hernani Yulinawati,

Dian Ade Kurnia

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(3)

Опубликована: Июнь 3, 2025

Язык: Английский

Процитировано

0
High-Resolution Daily Spatiotemporal Distribution and Evaluation of Ground-Level Nitrogen Dioxide Concentration in the Beijing–Tianjin–Hebei Region Based on TROPOMI Data DOI Creative Commons
Chunhui Liu, Sensen Wu,

Zhen Dai

и другие.

Remote Sensing, Год журнала: 2023, Номер 15(15), С. 3878 - 3878

Опубликована: Авг. 4, 2023

This study utilized TROPOMI remote sensing data, MODIS ground observation and other ancillary data to construct a high-resolution spatiotemporal distribution evaluation of ground-level NO2 concentrations in the Beijing–Tianjin–Hebei (BTH) region using Geographic Temporal Neural Network Weighted Regression (GTNNWR) model. Through this model, we obtained daily nitrogen dioxide (NO2) at resolution 500 m for period 2019–2022. The research results exhibited higher accuracy more detailed features compared models, enabling accurate reflection spatial temporal variations region, while retaining details trends excluding influence noisy data. Furthermore, conducted an analysis considering important events such as public health incidents Winter Olympics. demonstrated that GTNNWR model outperformed Random Forest (RF), Convolutional (CNN), (GNNWR) models performance metrics R2, RMSE, MAE, MAPE, showcasing greater reliability when heterogeneity non-stationarity. provides crucial support reference atmospheric environmental management pollution prevention control region.

Язык: Английский

Процитировано

6