384 Hits in 9.2 sec

Time series analysis and forecasting of Air Pollution Particulate Matter (PM2.5): an SARIMA and factor analysis approach

Uzair Aslam Bhatti, Yan Yuhuan, Zhou Ming-Quan, Sajid Ali, Aamir Hussain, Huo Qing-Song, Zhaoyuan Yu, Linwang Yuan
2021 IEEE Access  
INDEX TERMS Particulate matter, PM 2.5 , PM 10, air pollution.  ...  This study provides in depth analysis of all factors of air pollutants by correlation between those factors.  ...  This paper proposes to build a time series forecasting model using long and short-term memory network combined with attention mechanism, and apply it to the air quality forecasting field.  ... 
doi:10.1109/access.2021.3060744 fatcat:4s5rt34jgrd2hfqs6p2yqk5yt4

A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities

Chiou-Jye Huang, Ping-Huan Kuo
2018 Sensors  
In 2017, the latest research by Li et al. showed that the air pollution estimation system based on a Long Short-Term Memory (LSTM) neural network is more accurate [13] .  ...  To monitor and estimate the PM 2.5 concentration, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are combined and applied to the PM 2.5 forecasting system.  ...  In this paper, the main architectures are Convolutional Neural Network (CNN) [22] and Long Short-Term Memory (LSTM) [23, 24] .  ... 
doi:10.3390/s18072220 pmid:29996546 pmcid:PMC6069282 fatcat:xjf5d2wlubbshpsiqus4osw42q

Why Is Short-Time PM2.5 Forecast Difficult? The Effects of Sudden Events

Nai-Cih Liou, Cyuan-Heng Luo, Sachit Mahajan, Ling-Jyh Chen
2019 IEEE Access  
The existing forecast models for PM2.5 concentration can be classified into long term and short term models depending on whether the forecast is performed for the next few hours or days.  ...  The data were fed into the current short-term forecast model to forecast air quality for the next hour.  ...  We distinguished long-term forecast and short-term forecast by the length of forecasting time: forecasting within one day (such as five minutes or a few hours) are considered short-term, and those more  ... 
doi:10.1109/access.2019.2963341 fatcat:r6gccfikojftba22dj72olx5pm

A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)

Taoying Li, Miao Hua, Xu Wu
2020 IEEE Access  
In this study, A hybrid CNN-LSTM model is developed by combining the convolutional neural network (CNN) with the long short-term memory (LSTM) neural network for forecasting the next 24h PM2.5 concentration  ...  in Beijing, which makes full use of their advantages that CNN can effectively extract the features related to air quality and the LSTM can reflect the long term historical process of input time series  ...  [24] proposed a long short-term memory-fully connected (LSTM-FC) neural network, to predict PM2.5 contamination. Huang et al.  ... 
doi:10.1109/access.2020.2971348 fatcat:q74y6teugrbgpixq6t6w5qjwf4

Short-Term Prediction of PM2.5 Pollution with Deep Learning Methods

2020 Global NEST Journal  
In this study, short-term prediction of PM2.5 pollution at 1, 2 and 3 hours was modelled using deep learning methods.  ...  Three deep learning algorithms and the combination thereof were evaluated: Long-short term memory units (LSTM), recurrent neural networks (RNN) and gated recurrent unit (GRU).  ...  A wide variety of models can be used for this purpose such as long-short term memory units (LSTM), recurrent neural networks (RNN), air quality estimation method based on deep learning (STDL), deep air  ... 
doi:10.30955/gnj.003208 fatcat:eimi7c4vczc2doqovfbmh6sdqu

Evaluation of Time Series Forecasting Models for Estimation of PM2.5 Levels in Air [article]

Satvik Garg, Himanshu Jindal
2021 arXiv   pre-print
There has been an ascent in using machine learning and deep learning models to foresee the results on time series data.  ...  This study adopts ARIMA, FBProphet, and deep learning models such as LSTM, 1D CNN, to estimate the concentration of PM2.5 in the environment.  ...  PM2.5 represents air particulate matter with a diameter under 2.5 micrometers, represents 3% the diameter of human hair [2] .  ... 
arXiv:2104.03226v1 fatcat:whnxa6qowbfktgxnrnqp5t5qfi

Research on PM2.5 Spatiotemporal Forecasting Model Based on LSTM Neural Network

Fang Zhao, Ziyi Liang, Qiyan Zhang, Dewen Seng, Xiyuan Chen, Yassine Maleh
2021 Computational Intelligence and Neuroscience  
features through long- and short-term memory neural networks.  ...  This paper proposed a new air quality spatiotemporal prediction model to predict future air quality and is based on a large number of environmental data and a long short-term memory (LSTM) neural network  ...  [15] proposed a hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory; the model applies a graph convolutional network (GCN) to  ... 
doi:10.1155/2021/1616806 pmid:34712315 pmcid:PMC8548155 fatcat:pzfhhqjbc5gklfit42l4hngwxa

PM2.5 Prediction Model Based on Combinational Hammerstein Recurrent Neural Networks

Yi-Chung Chen, Tsu-Chiang Lei, Shun Yao, Hsin-Ping Wang
2020 Mathematics  
deep learning models, such as deep recurrent neural networks and long short-term memory, despite far lower implementation costs and computational overhead.  ...  Airborne particulate matter 2.5 (PM2.5) can have a profound effect on the health of the population.  ...  [19] employed attention-based long short-term memory and ensemble-learning to predict air pollution concentrations. Zheng et al.  ... 
doi:10.3390/math8122178 fatcat:jhfr7ckgozcznpizls4kgvfhmq

PM10 and PM2.5 real-time prediction models using an interpolated convolutional neural network

Sangwon Chae, Joonhyeok Shin, Sungjun Kwon, Sangmok Lee, Sungwon Kang, Donghyun Lee
2021 Scientific Reports  
AbstractIn this paper, we propose a real-time prediction model that can respond to particulate matters (PM) in the air, which are an indication of poor air quality.  ...  This combination creates the interpolated CNN (ICNN) model that we use to predict PM10 and PM2.5 concentrations.  ...  Long short-term memory (LSTM) is a commonly used model for sequential data processing, such as voice or text processing 42 .  ... 
doi:10.1038/s41598-021-91253-9 pmid:34099763 fatcat:ffnt3o7qyfeodds2e4sxxr6mmq

Forecasting PM2.5 Concentration Using a Single-Dense Layer BiLSTM Method

Aji Teguh Prihatno, Himawan Nurcahyanto, Md. Faisal Ahmed, Md. Habibur Rahman, Md. Morshed Alam, Yeong Min Jang
2021 Electronics  
In this paper, a Single-Dense Layer Bidirectional Long Short-term Memory (BiLSTM) model is developed to forecast the PM2.5 concentrations in the indoor environment by using the time series data.  ...  In recent times, particulate matter (PM2.5) is one of the most critical air quality contaminants, and the rise of its concentration will intensify the hazard of cleanrooms.  ...  predict future air quality by forecasting particulate matter (PM).  ... 
doi:10.3390/electronics10151808 fatcat:zpr2qyhv5fbm5mkyp75l5242iy

Prediction of PM2.5 Concentration Based on the LSTM-TSLightGBM Variable Weight Combination Model

Xuchu Jiang, Yiwen Luo, Biao Zhang
2021 Atmosphere  
This paper establishes a long short-term memory (LSTM) model with a time window size of 12, establishes a T-shape light gradient boosting machine (TSLightGBM) model that uses all information in the time  ...  PM2.5 is one of the main pollutants that cause air pollution, and high concentrations of PM2.5 seriously threaten human health.  ...  Among them, atmospheric particulate matter (PM) is one of the main pollutants that causes air pollution, and fine particulate matter represented by PM 2.5 has enveloped a layer of haze over most cities  ... 
doi:10.3390/atmos12091211 fatcat:3dlg4vc5kvbczcwaybazg5sose

A machine learning-based model to estimate PM2.5 concentration levels in Delhi's atmosphere

Saurabh Kumar, Shweta Mishra, Sunil Kumar Singh
2020 Heliyon  
A regression model is proposed, which uses Extra-Trees regression and AdaBoost, for further boosting.  ...  This work aims to forecast the PM2.5 concentration levels in various regions of Delhi on an hourly basis, by applying time series analysis and regression, based on various atmospheric and surface factors  ...  In this, they have applied LSTM (Long Short-Term Memory) Networks on the air pollution data based on Melbourne, Australia.  ... 
doi:10.1016/j.heliyon.2020.e05618 pmid:33305040 pmcid:PMC7710640 fatcat:2ohe6fek4nh65az2f2airc56zy

Evaluation of Different Machine Learning Approaches in Forecasting PM2.5 Mass Concentrations

Hamed Kaimian, Qi Li, Chunlin Wu, Yanlin Qi, Yuqin Mo, Gong Chen, Sonali Sachdeva, Xianfeng Zhang
2019 Aerosol and Air Quality Research  
a new hybrid model based on long short-term memory (LSTM).  ...  air pollution.  ...  One solution to overcome this problem is to utilize the long short-term memory (LSTM) model architecture as a special class of RNN (Hochreiter and Schmidhuber, 1997) .  ... 
doi:10.4209/aaqr.2018.12.0450 fatcat:rzgtc4ewsvdiblal3vlwrh3gqa

PM2.5 Prediction using Machine Learning Hybrid Model for Smart Health

2019 International Journal of Engineering and Advanced Technology  
Air is polluted by numerous air pollutants, among which Particulate Matter (PM2.5) is considered harmful consists of suspended particles with a diameter less than 2.5 micrometers.This paper aims to acquire  ...  PM2.5 data through IoT devices,store it in Cloud and propose an improved hybrid model that predicts the PM2.5 concentration in the air.  ...  In [6] author proposed new model based on LSTM(Long Short-Term Memory) to forecasting PM2.5 based on the historical data and in [18] author achieves in predicting PM2.5,NO2,SO2 air pollutants concentrations  ... 
doi:10.35940/ijeat.a1187.109119 fatcat:y3d2a3337bgldamhmoh727x4gm


H. Fan, M. Yang, F. Xiao, K. Zhao
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
To tackle this problem, this study proposed a weighted long short-term memory neural network extended model (WLSTME), which addressed the issue that how to consider the effect of the density of sites and  ...  Due to the transportation of air pollutants among areas, the PM2.5 concentration is strongly spatiotemporal correlated.  ...  Recently, long short-term memory neural network (LSTM) (Hochreiter, 1997) , has been used extensively for processing time series data due to its capability of simulating long and short-term tendency simultaneously  ... 
doi:10.5194/isprs-archives-xliii-b3-2020-1451-2020 fatcat:2ooambyfbrc3te6hthtiu2wetm
« Previous Showing results 1 — 15 out of 384 results