A Machine Learning Approach to Predict Air Quality in California

Castelli, Mauro; Clemente, Fabiana Martins; Popovič, Aleš; Silva, Sara; Vanneschi, Leonardo

doi:10.1155/2020/8049504

Cited by 168 publications

(60 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further, a trend study [16,17] revealed that AI techniques are more reliable in solving forecasting problems. Therefore, most air quality prediction models [18][19][20] are designed on AI platforms. The efficacy of the model lies in its precise prediction of various levels of air pollutants.…”

Section: Figure 1: Aqi Categories As Defined By Epamentioning

confidence: 99%

See 1 more Smart Citation

COVID19: Forecasting Air Quality Index and Particulate Matter (PM2.5)

Mangayarkarasi¹,

Vanmathi²,

Khan³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Urbanization affects the quality of the air, which has drastically degraded in the past decades. Air quality level is determined by measures of several air pollutant concentrations. To create awareness among people, an automation system that forecasts the quality is needed. The COVID-19 pandemic and the restrictions it has imposed on anthropogenic activities have resulted in a drop in air pollution in various cities in India. The overall air quality index (AQI) at any particular time is given as the maximum band for any pollutant. PM2.5 is a fine particulate matter of a size less than 2.5 micrometers, the inhalation of which causes adverse effects in people suffering from acute respiratory syndrome and other cardiovascular diseases. PM2.5 is a crucial factor in deciding the overall AQI. The proposed forecasting model is designed to predict the annual PM2.5 and AQI. The forecasting models are designed using Seasonal Autoregressive Integrated Moving Average and Facebook's Prophet Library through optimal hyperparameters for better prediction. An AQI category classification model is also presented using classical machine learning techniques. The experimental results confirm the substantial improvement in air quality and greater reduction in PM2.5 due to the lockdown imposed during the COVID-19 crisis.

show abstract

Section: Figure 1: Aqi Categories As Defined By Epamentioning

confidence: 99%

“…Reference [19] developed a system to examine pollutant (CO, SO2, NO, O3, and PM 2.5) concentrations on an hourly basis and predict AQI. The system was based on support vector regression, with radial basis function used as a kernel to make more reliable predictions.…”

Section: Figure 1: Aqi Categories As Defined By Epamentioning

confidence: 99%

COVID19: Forecasting Air Quality Index and Particulate Matter (PM2.5)

Mangayarkarasi¹,

Vanmathi²,

Khan³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…The complex mixture of particulate matter and other gases like ozone was recorded to be associated with an all-cause death rate of up to 9 million in 2015 [ 24 ]. In this connection, building a forecasting system based on hourly air quality prediction plays an important role in health alerts [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction

Wardana

Gardner

Fahmy

2021

Sensors

View full text Add to dashboard Cite

Accurate air quality monitoring requires processing of multi-dimensional, multi-location sensor data, which has previously been considered in centralised machine learning models. These are often unsuitable for resource-constrained edge devices. In this article, we address this challenge by: (1) designing a novel hybrid deep learning model for hourly PM2.5 pollutant prediction; (2) optimising the obtained model for edge devices; and (3) examining model performance running on the edge devices in terms of both accuracy and latency. The hybrid deep learning model in this work comprises a 1D Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to predict hourly PM2.5 concentration. The results show that our proposed model outperforms other deep learning models, evaluated by calculating RMSE and MAE errors. The proposed model was optimised for edge devices, the Raspberry Pi 3 Model B+ (RPi3B+) and Raspberry Pi 4 Model B (RPi4B). This optimised model reduced file size to a quarter of the original, with further size reduction achieved by implementing different post-training quantisation. In total, 8272 hourly samples were continuously fed to the edge device, with the RPi4B executing the model twice as fast as the RPi3B+ in all quantisation modes. Full-integer quantisation produced the lowest execution time, with latencies of 2.19 s and 4.73 s for RPi4B and RPi3B+, respectively.

show abstract

“…It extracts air quality data and meteorological data, and makes cycle prediction with support vector machine. Castelli et al improved the regression of the support vector machine by taking the radial basis function as the core of the support vector regression machine 9 . The improved support regression machine was used to predict air quality and achieved good results.…”

Section: Introductionmentioning

confidence: 99%

An Empirical Mode Decomposition Fuzzy Forecast Model for Air Quality

Chen

Zhu

Sheng

et al. 2021

Preprint

View full text Add to dashboard Cite

Air quality is related to people's health. Severe air pollution can cause respiratory diseases, while good air quality is beneficial to physical and mental health. Therefore, the prediction of air quality is very important. As an important algorithm for signal analysis, empirical mode decomposition can analyze the change trend of air quality well, smooth the complex and changeable air quality data, and get the change trend of air quality under different time scales. According to the change trend under different time scales, the extreme learning machine is used for training, and the corresponding prediction value is obtained. The adaptive fuzzy inference system is used for fitting to obtain the final air quality prediction result. The experimental results show that the signal decomposition fuzzy prediction model has a good learning ability and has good accuracy in predicting the concentration of various pollutants in air quality.

show abstract

A Machine Learning Approach to Predict Air Quality in California

Cited by 168 publications

References 47 publications

COVID19: Forecasting Air Quality Index and Particulate Matter (PM2.5)

COVID19: Forecasting Air Quality Index and Particulate Matter (PM2.5)

Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction

An Empirical Mode Decomposition Fuzzy Forecast Model for Air Quality

Contact Info

Product

Resources

About