Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation

Li, Xiang; Peng, Ling; Yao, Xiaojing; Cui, Shaolong; Hu, Yuan; You, Cai; Chi, Tianhe

doi:10.1016/j.envpol.2017.08.114

Cited by 486 publications

(265 citation statements)

References 35 publications

Supporting

Mentioning

214

Contrasting

Unclassified

Order By: Relevance

“…Xiang et al have proposed a RNN based model for predicting air pollutant concentrations along with an evaluation strategy [27]. A deep air system was developed by Vikram et al for forecasting pollution in Beijing [14].…”

Section: Related Workmentioning

confidence: 99%

Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks

Rao¹,

Devi²,

Ramesh³

2019

IJISA

View full text Add to dashboard Cite

The research activity considered in this paper concerns about efficient approach for modeling and prediction of air quality. Poor air quality is an environmental hazard that has become a great challenge across the globe. Therefore, ambient air quality assessment and prediction has become a significant area of study. In general, air quality refers to quantification of pollution free air in a particular location. It is determined by measuring different types of pollution indicators in the atmosphere. Traditional approaches depend on numerical methods to estimate the air pollutant concentration and require lots of computing power. Moreover, these methods cannot draw insights from the abundant data available. To address this issue, the proposed study puts forward a deep learning approach for quantification and prediction of ambient air quality. Recurrent neural networks (RNN) based framework with special structured memory cells known as Long Short Term Memory (LSTM) is proposed to capture the dependencies in various pollutants and to perform air quality prediction. Real time dataset of the city Visakhapatnam having a record of 12 pollutants was considered for the study. Modeling of temporal sequence data of each pollutant was performed for forecasting hourly based concentrations. Experimental results show that proposed RNN-LSTM frame work attained higher accuracy in estimating hourly based air ambience. Further, this model may be enhanced by adopting bidirectional mechanism in recurrent layer.Index Terms-Air quality, air pollution, prediction, environment, deep learning, recurrent neural networks, long short term memory.

show abstract

Section: Related Workmentioning

confidence: 99%

Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks

Rao¹,

Devi²,

Ramesh³

2019

IJISA

View full text Add to dashboard Cite

show abstract

“…e network architecture of the LSTM model used in the paper is shown in Figure 5, which is the same as the LSTMextended network proposed in [13]. e main input is the air pollutant data, and the auxiliary input is the time and meteorology data.…”

Section: Feature Transformationmentioning

confidence: 99%

“…According to the above experiments, for simplicity, 9 was selected as the most appropriate in uential historical time lag for di erent future time lag. Advances in Meteorologyand SVC are widely used air quality forecast models, they were ne-tuned in this paper in order to make a fair comparison with MKSVC, and the LSTM in this paper has the same structure as the LSTM extended model proposed in [13]. Figure 7 shows the experimental ow.…”

Section: Feature Transformationmentioning

confidence: 99%

“…Various machine learning methods have been applied to predict the air quality. Widely used methods include classical autoregressive moving average (ARMA) methods like the autoregressive integrated moving average (ARIMA) [5], support vector machine (SVM) methods like the support vector classifier (SVC) [6,7], ensemble methods like the random forest (RF) [8,9], artificial neural network (ANN) methods like the multiple layer perceptron (MLP) [10,11], and deep learning methods like the long short-term memory neural network (LSTM NN) [12,13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Multiple Kernel Learning Approach for Air Quality Prediction

Zheng

et al. 2018

Advances in Meteorology

View full text Add to dashboard Cite

Air quality prediction is an important research issue due to the increasing impact of air pollution on the urban environment. However, existing methods often fail to forecast high-polluting air conditions, which is precisely what should be highlighted. In this paper, a novel multiple kernel learning (MKL) model that embodies the characteristics of ensemble learning, kernel learning, and representative learning is proposed to forecast the near future air quality (AQ). e centered alignment approach is used for learning kernels, and a boosting approach is used to determine the proper number of kernels. To demonstrate the performance of the proposed MKL model, its performance is compared to that of classical autoregressive integrated moving average (ARIMA) model; widely used parametric models like random forest (RF) and support vector machine (SVM); popular neural network models like multiple layer perceptron (MLP); and long short-term memory neural network. Datasets acquired from a coastal city Hong Kong and an inland city Beijing are used to train and validate all the models. Experiments show that the MKL model outperforms the other models. Moreover, the MKL model has better forecast ability for high health risk category AQ.

show abstract

“…Despite achieving a relatively high prediction accuracy, the average mean absolute error of their predictions was around 9 μg/m 3 , compared to the average concentration of 83 μg/m 3 . Li et al [37] utilized long short-term memory (LSTM) along with several machine learning techniques. Their results, however, showed a significant error for more than a four-hour prediction.…”

mentioning

confidence: 99%

A real-time hourly ozone prediction system using deep convolutional neural network

Eslami

Choi

Lops

et al. 2019

Neural Comput & Applic

View full text Add to dashboard Cite

This study uses a deep learning approach to forecast ozone concentrations over Seoul, South Korea for 2017. We employ a deep convolutional neural network (CNN). We apply this method to predict the hourly ozone concentration on each day for the entire year using several predictors from the previous day, including the wind fields, temperature, relative humidity, pressure, and precipitation, along with in-situ ozone and NO2 concentrations. We refer to a history of all observed parameters between 2014 and 2016 for training the predictive models. Model-measurement comparisons for the 25 monitoring sites for the year 2017 report average indexes of agreement (IOA) of 0.84-0.89 and a Pearson correlation coefficient of 0.74-0.81, indicating reasonable performance for the CNN forecasting model. Although the CNN model successfully captures daily trends as well as yearly high and low variations of the ozone concentrations, it notably underpredicts high ozone peaks during the summer. The forecasting results are generally more accurate for the stations located in the southern regions of the Han River, the result of more stable topographical and meteorological conditions. Furthermore, through two separate daytime and nighttime forecasts, we find that the monthly IOA of the CNN model is 0.05-0.30 higher during the daytime, resulting from the unavailability of some of the input parameters during the nighttime. While the CNN model can predict the next 24 hours of ozone concentrations within less than a minute, we identify several limitations of deep learning models for real-time air quality forecasting for further improvement.

show abstract

Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation

Cited by 486 publications

References 35 publications

Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks

Air Quality Prediction in Visakhapatnam with LSTM based Recurrent Neural Networks

A Multiple Kernel Learning Approach for Air Quality Prediction

A real-time hourly ozone prediction system using deep convolutional neural network

Contact Info

Product

Resources

About