Abstract
The acquisition of PM2.5 concentration mainly relies on small and provincial control air quality monitoring stations, respectively. The distribution of provincial control stations (PCSs) is sparse as its high cost, conversely the distribution of small stations is relatively dense and spread over the whole space as the relatively low cost, thus the observations of small stations can be employed to predict that of PCSs. Based on this considerations, in this paper, we propose a novel multi-source spatiotemporal data fusion method via the nearest neighbor grids, named MSF-NNG, to interpolate and predict PM2.5 concentration of PCSs by utilizing those data of small stations. Firstly, we divide the city into 1 km \(\times \) 1 km grids, and then Cressman interpolation method is employed to fill the missing ones with the observations of small stations, wherein the observations include PM2.5 concentrations, humidity, temperature and wind speed. Secondly, it needs to find the neighbors of a PCS based on its grid partitions. Thirdly, MSF-NNG is proposed to interpolate and predict the PM2.5 concentrations of PCS by fusing the information of PM2.5 concentrations, humidity, temperature and wind speed of the corresponding neighbor grids. Finally, comparison experiments are conducted on several data sets, the results show MSF-NNG method with obvious advantages in interpolation and prediction for PM2.5 concentrations over fourteen and twelve algorithms, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Stafoggia, M., et al.: Estimation of daily PM 10 and PM 2.5 concentrations in Italy, 2013–2015, using a spatiotemporal land-use random-forest model. Environ. Int. 124(1), 170–179(2019)
Chin, M.: Basic mechanisms for adverse cardiovascular events associated with air pollution. Heart 101(4), 253–256 (2015)
Yao, C., Cao, Z., Han, Y.: Industrial agglomeration, population urbanization, land urbanization and environment pollution. Areal Res. Dev. 39(5), 145–149 (2020)
Zheng, Y., et al.: Forecasting fine-grained air quality based on big da ta. In: 21th ACM SIGKDD International Conference on Knowledge Discovery Data Mining., pp. 2267–2276 (2010)
Jutzeler, A., Li, J., Faltings, B.: A Region-based model for estimating urban air pollution. In: 28th AAAI Conference on Artificial Intelligence, pp. 425–430 (2014)
Chen, L., Cai, Y., Ding, Y., Lv, M., Yuan, C., Chen, G.: Spatially fine-grained urban air quality estimation using ensemble semi-supervised learning and pruning. In: 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 1076–1087 (2016)
Zheng, Y., Liu, F., Hsieh, H.: U-air: when urban air quality inference meets big data. In: 19th ACM SIGKDD The International Conference on Knowledge Discovery and Data Minin, pp. 1436–1444(2013)
Liu, X., Wang, X., Zou, L., Xia, J., Pang, W.: Spatial imputation for air pollutants data sets via low rank matrix completion algorithm. Environ. Int. 139, Art. no. 105713 (2020)
Qin, M., Du, Z., Zhang, F., Liu, R.: A matrix completion-based multiview learning method for imputing missing values in buoy monitoring data. Inf. Sci. 487(2), 18–30 (2019)
Qi, Z., Wang, T., Song, G., Hu, W., Zhang, Z.: Deep air learning interpolation, prediction, and feature analysis of fine-grained air quality. IEEE Trans. Knowl. Data Eng. 30(23), 2285–2297 (2018)
Chen, Z., et al.: Extreme gradient boosting model to estimate PM2.5 concentrations with missing-filled satellite data in China. Atmos. Environ. 202(1), 180–189 (2019)
Malings, C., et al.: Development of a general calibration model and long-term performance evaluation of low-cost sensors for air pollutant gas monitoring. Atmos. Meas. Tech. 12(2), 903–920 (2019)
Liu, N., Ma, R., Wang, Y., Zhang, L.: Inferring fine-grained air pollution map via a spatiotemporal super-resolution scheme. In: 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2019 ACM International Symposium ACM, pp. 498–504 (2019)
Ma, R., et al.: Fine-grained air pollution inference with mobile sensing systems: a weather-related deep autoencoder model. In: 2020 ACM on Interactive Mobile Wearable and Ubiquitous Technologies, Art. no. 52 (2020)
Li, J., Heap, A.: Spatial interpolation methods applied in the environmental sciences-a review. Environ. Modell. Softw. 53(12), 174–189 (2014)
Sekulic, A., Kilibarda, M., Heuvelink, G., Nikolic, M., Bajat, B.: Random Forest Spatial Interpolation. Remote Sens. 12, Art. no. 1687(2020)
Wei, J., et al.: Estimating 1-KM-resolution PM2.5 concentrations across China using the space-time random forest approach. Remote Sens. Environ. 231, Art. no. 111221 (2019)
Wei, J., et al.: Improved 1 km resolution PM2.5 estimates across China using enhanced space-time extremely randomized trees. Atmos. Chem. Phys. 20(6), 3273–3289 (2020)
Li, T., Shen, H., Zeng, C., Yuan, Q., Zhang, L.: Point-surface fusion of station measurements and satellite observations for mapping PM2.5 distribution in China: Methods and assessment. Atmos. Environ. 152(1), 477–489 (2017)
Huang, G., Li, X., Zhang, B., Ren, J.: PM2.5 concentration forecasting at surface monitoring sites using GRU neural network based on empirical mode decomposition. Sci. Total Environ. 768(3), Art. no. 144516 (2021)
Wu, X., Wang, Y., He, S., Wu, Z.: PM2.5_PM10 ratio prediction based on a long short-term memory neural network in Wuhan, China. Geosci. Model Dev. 13(3), 1499–1511 (2020)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Ahmed, M., Xiao, Z., Shen, Y.: Estimation of ground PM2.5 concentrations in pakistan using convolutional neural network and multi-pollutant satellite images. Remote Sens. 14, Art. no. 1735 (2022)
Cressman, G.: An operational objective analysis system. Mon. Weather Rev. 87(10), 367–374 (1959)
Liu, Z., Huang, R., Hu, Y., Fan, S., Feng, P.: Generating high spatiotemporal resolution LAI based on MODIS/GF-1 data and combined Kriging-Cressman interpolation. Int. J. Agric. Biol. Eng. 9(5), 120–131 (2016)
Li, L., Zhang, J., Wang, Y., Ran, B.: Missing value imputation for traffic-related time series data based on a multi-view learning method. IEEE Trans. Intell. Transp. Syst. 20(8), 2933–2943 (2019)
Willmott, C., Rowe, C., Philpot, W.: Small-scale climate maps: a sensitivity analysis of some common assumptions associated with grid-point interpolation and contouring. Am. Cartograph. 12(1), 5–16 (1985)
Cormack, R., Cressie, N.: Statistics for spatial data. Int. Biometric Soc. 48(4), 1300–1302 (1992)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)
Acknowledgments
The authors would like to thank the support of the National Key R &D Program of China (2019YFB2103000), the State Key Program of National Nature Science Foundation of China (61936001), the Natural Science Foundation of Chongqing (cstc2019jcyj-cxttX0002, cstc2020jcyj- msxmX0737, cstc2021ycjh-bgzxm0013), the Key Cooperation Project of Chongqing Municipal Education Commission (HZ2021008), and the Science and Technology Research Program of Chongqing Education Commission of China (KJQN201900638).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, X., Hu, J., Zhou, P., Wang, G. (2022). An Improved Multi-source Spatiotemporal Data Fusion Model Based on the Nearest Neighbor Grids for PM2.5 Concentration Interpolation and Prediction. In: Tan, Y., Shi, Y. (eds) Data Mining and Big Data. DMBD 2022. Communications in Computer and Information Science, vol 1744. Springer, Singapore. https://doi.org/10.1007/978-981-19-9297-1_20
Download citation
DOI: https://doi.org/10.1007/978-981-19-9297-1_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9296-4
Online ISBN: 978-981-19-9297-1
eBook Packages: Computer ScienceComputer Science (R0)