Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting

Zhou, Yanlai; Chang, Fi‐John; Chang, Li-Chiu; Kao, I-Feng; Wang, Yi-Shin; Kang, Che-Chia

doi:10.1016/j.scitotenv.2018.09.111

Cited by 131 publications

(45 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a globally optimal method, support machine vector has been increasingly used for PM 2.5 estimation [97][98][99]. However, the scalability of this method is constrained in studies with a large sample size (e.g., high spatiotemporal resolution AOD over a long period and a large region).…”

Section: Strengths Of Bagging Of Residual Networkmentioning

confidence: 99%

A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5

2020

Remote Sensing

View full text Add to dashboard Cite

Accurate estimation of fine particulate matter with diameter ≤2.5 μm (PM2.5) at a high spatiotemporal resolution is crucial for the evaluation of its health effects. Previous studies face multiple challenges including limited ground measurements and availability of spatiotemporal covariates. Although the multiangle implementation of atmospheric correction (MAIAC) retrieves satellite aerosol optical depth (AOD) at a high spatiotemporal resolution, massive non-random missingness considerably limits its application in PM2.5 estimation. Here, a deep learning approach, i.e., bootstrap aggregating (bagging) of autoencoder-based residual deep networks, was developed to make robust imputation of MAIAC AOD and further estimate PM2.5 at a high spatial (1 km) and temporal (daily) resolution. The base model consisted of autoencoder-based residual networks where residual connections were introduced to improve learning performance. Bagging of residual networks was used to generate ensemble predictions for better accuracy and uncertainty estimates. As a case study, the proposed approach was applied to impute daily satellite AOD and subsequently estimate daily PM2.5 in the Jing-Jin-Ji metropolitan region of China in 2015. The presented approach achieved competitive performance in AOD imputation (mean test R2: 0.96; mean test RMSE: 0.06) and PM2.5 estimation (test R2: 0.90; test RMSE: 22.3 μg/m3). In the additional independent tests using ground AERONET AOD and PM2.5 measurements at the monitoring station of the U.S. Embassy in Beijing, this approach achieved high R2 (0.82–0.97). Compared with the state-of-the-art machine learning method, XGBoost, the proposed approach generated more reasonable spatial variation for predicted PM2.5 surfaces. Publically available covariates used included meteorology, MERRA2 PBLH and AOD, coordinates, and elevation. Other covariates such as cloud fractions or land-use were not used due to unavailability. The results of validation and independent testing demonstrate the usefulness of the proposed approach in exposure assessment of PM2.5 using satellite AOD having massive missing values.

show abstract

Section: Strengths Of Bagging Of Residual Networkmentioning

confidence: 99%

A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The statistical methods have shown better performance because the nonlinear and heterogeneous nature of processes in the formation and transportation of air pollution [8]. With the advance of technology and decreasing cost of sensors for collecting air quality data, data mining and machining learning methods become more and more important, such as time series analysis [9], [10], random forest [11], [12], principal component analysis [13], Kalman filters [14], support vector machines (SVMs) [15], [16], and artificial neural networks (ANNs) [5], [7], [17]. PM 2.5 predictions are challenging because the formation and transportation of PM 2.5 is strongly influenced by spatial and temporal variations at both micro-and macro-scales [18], [19].…”

Section: Introductionmentioning

confidence: 99%

Dynamic System Approach for Improved PM_2.5 Prediction in Taiwan

et al. 2020

View full text Add to dashboard Cite

“…e first class is the traditional statistical models, such as seasonal autoregressive integrated moving average (SARIMA) [10,11] and Holt-Winters model [12]. e second class is artificial intelligence models, such as support vector machines [13] and neural network [14]. e genetic algorithm with multivariable grey model is effective when the data size is big [15].…”

Section: Introductionmentioning

confidence: 99%

Forecasting the Agriculture Output Values in China Based on Grey Seasonal Model

Chen

2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The output values for agriculture, forestry, animal husbandry, and fishery are important indicators of agricultural economic development. Therefore, accurately predicting the output values for agriculture, forestry, animal husbandry, and fishery can capture the developmental trend and the optimize the structure. Agriculture, forestry, animal husbandry, and fishery are typical seasonal industries, and thus their output values vary greatly among different seasons. To accurately estimate the seasonal variations in the observed sequence and obtain better prediction results, the output values for agriculture, forestry, animal husbandry, and fishery in different quarters from 2018 to 2021 are predicted and analyzed by using the grey seasonal model (GSM). The results indicated that the prediction accuracy of GSM is relatively high. The output values for the agriculture, forestry, animal husbandry, and fishery as well as their total output value will increase gradually. It is an important achievement of structural reform under the new normal economic situation. In addition, the GSM provides a new method for predicting seasonal data.

show abstract

Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting

Cited by 131 publications

References 38 publications

A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5

A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5

Dynamic System Approach for Improved PM_2.5 Prediction in Taiwan

Forecasting the Agriculture Output Values in China Based on Grey Seasonal Model

Contact Info

Product

Resources

About

Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting

Cited by 131 publications

References 38 publications

A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5

A Robust Deep Learning Approach for Spatiotemporal Estimation of Satellite AOD and PM2.5

Dynamic System Approach for Improved PM2.5 Prediction in Taiwan

Forecasting the Agriculture Output Values in China Based on Grey Seasonal Model

Contact Info

Product

Resources

About

Dynamic System Approach for Improved PM_2.5 Prediction in Taiwan