Abstract
Pollution is a major public health and human rights issue that disproportionately affects the poor and disadvantaged. However, academic studies have not fully explored the relationship between poverty and the spatial distribution of environmental pollution, notably in Thailand. Thus, this chapter aims to fill a void in academic research by exploring the implementation of machine learning in the estimation of poverty by training input data from widely available and accessible open source, including environmental pollution and road density. The poverty rate is obtained from the TPMAP website and then clustered into two groups, “high and low,” using hot spot analysis. The Google Earth Engine is used to extract pollution indexes such as carbon monoxide, formaldehyde, nitrogen, and sulfur dioxide, while road density is downloaded from OpenStreetMap. This study compares four different machine learning models: XGboost, lasso, random forest, and ridge regression for poverty estimation. The result of the study reveals that poverty-related areas are highly correlated with environmental pollution. The random forest technique has the best performance prediction among the four methods, with an R2 of 0.79. Finally, feature importance analysis is used to determine the most influential features in order to assist decision-makers in gaining a better understanding of poverty.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Heart (2017) Pollution and Poverty – HEART. https://www.heart-resources.org/reading_pack/pollution-and-poverty/. Accessed 18 Nov 2021
GAHP (2017) Achieving The #GlobalGoals And Addressing Pollution Go Hand In Hand – GAHP | Global Alliance on Health and Pollution. https://gahp.net/achieving-globalgoals-addressing-pollution-go-hand-hand/. Accessed 9 May 2022
Borgen Project (2021) How Air Pollution Affects Poverty in Europe – The Borgen Project. https://borgenproject.org/air-pollution-and-poverty/. Accessed 18 Nov 2021
ADB: Mapping Poverty Through Data Integration and Artificial Intelligence (2020)
Puttanapong, N., Martinez Jr, A., Addawe, M., et al.: Predicting Poverty Using Geospatial Data in Thailand working paper series (2020)
ADB: Mapping the Spatial Distribution of Poverty Using Satellite Imagery in Thailand, (2021)
Sangkasem, K.: Analysis of spatial inequality using DMSP-OLS nighttime-light satellite imageries: a case study of Thailand. Wiley Online Libr. (2020). https://doi.org/10.1111/rsp3.12386
Sedda, L., Tatema, A.J., Morley, D.W., et al.: Poverty, health and satellite-derived vegetation indices: their inter-spatial relationship in West Africa. Int. Health. 7, 99–106 (2015). https://doi.org/10.1093/inthealth/ihv005
Dawson, T., Onésimo Sandoval, J.S., Sagan, V., Crawford, T.: A spatial analysis of the relationship between vegetation and poverty. ISPRS Int J Geo-Information. 7 (2018). https://doi.org/10.3390/ijgi7030083
He, X., Mai, X.: Poverty and physical geographic factors: An empirical analysis of Sichuan Province using the GWR model. Sustainability. (2020). https://doi.org/10.3390/su1301
Bhattacharya, H., Innes, R.: Is there a Nexus between Poverty and Environment in Rural India? 2006 Annu Meet July 23–26, Long Beach (2006)
Morikawa, R.: Remote sensing tools for evaluating poverty alleviation projects: a case study in Tanzania. Procedia Eng. 78, 178–187 (2014). https://doi.org/10.1016/j.proeng.2014.07.055
Chen, S., Ou, J.: The environmental and health impacts of poverty alleviation in China: From a consumption-based perspective. Sustainability. (2021). https://doi.org/10.3390/su13041784
Casillas, C.: The energy-poverty-climate nexus. Science. 330, 1181–1182 (2010). https://doi.org/10.1126/science.1197412
Dasgupta, S., Laplante, B., Wang, H., Wheeler, D.: Confronting the environmental Kuznets curve. J. Econ. Perspect. 16, 147–168 (2002). https://doi.org/10.1257/0895330027157
Dorji, U., Siripanpornchana, C., Surasvadi, N., et al.: Exploring night light as proxy for poverty and income inequality approximation in Thailand. In: IEEE region 10 annual international conference, proceedings/TENCON, pp. 1082–1087 (2019)
Bakwin, P.S., Tans, P.P., Novelli, P.C.: Carbon monoxide budget in the northern hemisphere. Geophys. Res. Lett. 21, 433–436 (1994). https://doi.org/10.1029/94GL00006
Sinha, V., Hakkim, H., Kumar, V.: Advances in identification and quantification of non-methane volatile organic compounds emitted from biomass fires through laboratory fire experiments. Adv Atmos Chem, 169–197 (2019). https://doi.org/10.1142/9789813271838_0003
Craig, K.: A review of the chemistry, pesticide use, and environmental fate of sulfur dioxide, as used in California. Rev. Environ. Contam. Toxicol. 246, 33–64 (2019). https://doi.org/10.1007/398_2018_11
Thompson, A.M.: The oxidizing capacity of the Earth’s atmosphere: probable past and future changes. Science. 256, 1157–1165 (1992). https://doi.org/10.1126/SCIENCE.256.5060.1157
Xue, J., Liu, S., Chen F.: GIS analysis on relationship between traffic density parameters and near-road air pollutants (2019)
Rachiel, T.: Hot spot spatial analysis Columbia public health. In: Columbia Public Heal (2020) https://www.publichealth.columbia.edu/research/population-health-methods/hot-spot-spatial-analysis. Accessed 26 May 2022
Lin Htet, N., Kongprawechnon, W., Thajchayapong, S., Isshiki, T.: Machine learning approach with multiple open-source data for mapping and prediction of poverty in Myanmar. In: ECTI-CON 2021–2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology: Smart Electrical System and Technology, Proceedings, pp. 1041–1045 (2021)
Tingzon, I., Orden, A., Go, K.T., et al.: Mapping poverty in the philippines using machine learning, satellite imagery, and crowd-sourced geospatial information. Int Arch Photogramm Remote Sens Spat Inf Sci ISPRS Arch. 42, 425–431 (2019). https://doi.org/10.5194/isprs-archives-XLII-4-W19-425-2019
Acknowledgments
This research is financially supported by Thailand Advanced Institute of Science and Technology (TAIST), National Science and Technology Development Agency (NSTDA), Tokyo Institute of Technology, and Sirindhorn International Institute of Technology (SIIT), Thammasat University (TU) under the TAIST-Tokyo Tech Program. Also this research is partially supported by Thammasat University Research fund under the TSRI, Contract No. TUFF19/2564 and TUFF24/2565, for the project of “AI Ready City Networking in RUN,” based on the RUN Digital Cluster collaboration scheme.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Isnan, M., Horanont, T., Plangprasopchok, A. (2023). Machine Learning Approach with Environmental Pollution and Geospatial Information for Mapping Poverty in Thailand. In: Boonpook, W., Lin, Z., Meksangsouy, P., Wetchayont, P. (eds) Applied Geography and Geoinformatics for Sustainable Development. Springer Geography. Springer, Cham. https://doi.org/10.1007/978-3-031-16217-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-16217-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16216-9
Online ISBN: 978-3-031-16217-6
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)