Journal of Environmental Impact Assessment (환경영향평가)

Korean Society of Environmental Impact Assessment (한국환경영향평가학회)
권호 표지
DOI QR코드

DOI QR Code

Predicting Concentrations of Soil Pollutants and Mapping Using Machine Learning Algorithms

기계학습을 통한 토양오염물질 농도 예측 및 분포 매핑

  • Kang, Hyewon (Department of Landscape Architecture and Rural System Engineering, Seoul National University) ;
  • Park, Sang Jin (Interdisciplinary Program in Landscape Architecture & Integrated Major in Smart City Global Convergence) ;
  • Lee, Dong Kun (Department of Landscape Architecture and Rural System Engineering, Seoul National University)
  • 강혜원 (서울대학교 농업생명과학대학 생태조경.지역시스템공학부) ;
  • 박상진 (서울대학교 환경대학원 협동과정 조경학 및 대학원 융합전공 스마트시티 글로벌 융합) ;
  • 이동근 (서울대학교 농업생명과학대학 조경.지역시스템공학부)
  • Received : 2022.04.08
  • Accepted : 2022.07.06
  • Published : 2022.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study emphasized the soil of environmental impact assessment to devise measures to minimize the negative impact of project implementation on the environment. As a series of efforts for impact assessment procedures, a national inventory-based database was established for urban development projects, and three machine learning model performance evaluation as well as soil pollutant concentration distribution mapping were conducted. Here, nine soil pollutants were mapped to the metropolitan area of South Korea using the Random Forest model, which showed the best performance. The results of this study found that concentrations of Zn, F, and Cd were relatively concerned in Seoul, where urbanization is the most active. In addition, in the case of Hg and Cr6+, concentrations were detected below the standard, which was derived from a lack of pollutants such as industrial and industrial complexes that affect contents of heavy metals. A significant correlation between land cover and pollutants was inferred through the spatial distribution mapping of soil pollutants. Through this, it is expected that efficient soil management measures for minimizing soil pollution and planning decisions regarding the location of the project site can be established.

본 연구는 사업시행이 환경에 미치는 부정적 영향을 최소화할 수 있는 방안을 강구하기 위해 환경영향평가 토양 부문을 강조하였다. 영향평가 절차에 대한 일련의 노력으로서 도시개발사업을 대상으로 하는 국가 인벤토리 기반 데이터베이스를 구축하였으며, 세 가지 기계학습 모델 성능 평가 및 토양오염물질 농도분포 매핑을 진행하였다. 여기에서, 가장 우수한 성능을 보여준 Random Forest 모델을 사용하여 대한 민국 수도권 지역을 대상 9가지 토양오염물질을 매핑하였다. 본 연구의 결과는 도시화가 가장 활발한 서울지역에서 아연(Zn), 불소(F) 및 카드뮴(Cd) 농도가 상대적으로 우려되는 것을 발견하였다. 또한, 수은(Hg)과 크롬(Cr6+)의 경우 농도가 기준 이하로 검출되었는데, 이는 중금속 농도에 영향을 미치는 산업 및 공업단지와 같은 오염원 부족이 원인으로 도출되었다. 토양오염물질 공간분포 매핑을 통해 토양특성 및 토지이용 유형과 오염물질 간의 유의한 상관관계를 유추하였다. 이를 통해 사업 현장 위치에 관한 토양오염 최소화 및 계획 결정에 대한 효율적인 토양관리 방안을 구축할 수 있을 것으로 기대한다.

Keywords

Acknowledgement

본 결과물은 환경부의 재원으로 한국환경산업기술원의 ICT기반 환경영향평가 의사결정 지원 기술개발사업의 지원을 받아 연구되었습니다(No. 2020002990009).

References

  1. Ahirwal J, Nath A, Brahma B, Deb S, Sahoo UK, Nath AJ. 2021. Patterns and driving factors of biomass carbon and soil organic carbon stock in the Indian Himalayan region. Science of the Total Environment 770: 145292.
  2. Azizi K, Ayoubi S, Nabiollahi K, Garosi Y, Gislum R. 2022. Predicting heavy metal contents by applying machine learning approaches and environmental covariates in west of Iran. Journal of Geochemical Exploration 233: 106921.
  3. Bae J, Ryu Y. 2015. Land use and land cover changes explain spatial and temporal variations of the soil organic carbon stocks in a constructed urban park. Landscape and Urban Planning 136: 57-67. https://doi.org/10.1016/j.landurbplan.2014.11.015
  4. Cambou A, Shaw RK, Huot H, Vidal-Beaudet L, Hunault G, Cannavo P, Nold F, Schwartz C. 2018. Estimation of soil organic carbon stocks of two cities, New York City and Paris. Science of the Total Environment 644: 452-464. https://doi.org/10.1016/j.scitotenv.2018.06.322
  5. Yoon DH, Hong YK, Kim JW, Kim SH, Song GH, Lee KM, Kim SC. 2019. Evaluating Heavy Metal Pollution in Soil Using Pollution Index Model. Korean Society of Soil Science and Fertilizer, 168-168. [Korean Literature]
  6. Feng Y, Chen S, Tong X, Lei Z, Gao C, Wang J. 2020. Modeling changes in China's 2000-2030 carbon stock caused by land use change. Journal of Cleaner Production 252: 119659.
  7. Forkuor G, Hounkpatin OK, Welp G, Thiel M. 2017. High resolution mapping of soil properties using remote sensing variables in south-western Burkina Faso: a comparison of machine learning and multiple linear regression models. PloS One 12(1): e0170478.
  8. Golia EE, Diakoloukas V. 2021. Soil parameters affecting the levels of potentially harmful metals in Thessaly area, Greece: a robust quadratic regression approach of soil pollution prediction. Environmental Science and Pollution Research, 1-18.
  9. Gomes LC, Faria RM, de Souza E, Veloso GV, Schaefer CEG, Fernandes FEI. 2019. Modelling and mapping soil organic carbon stocks in Brazil. Geoderma 340: 337-350. https://doi.org/10.1016/j.geoderma.2019.01.007
  10. Govil PK, Sorlie JE, Murthy NN, Sujatha D, Reddy GLN, Rudolph-Lund K, Krishna AK, Rama MK. 2008. Soil contamination of heavy metals in the Katedan industrial development area, Hyderabad, India. Environmental Monitoring and Assessment 140(1): 313-323. https://doi.org/10.1007/s10661-007-9869-x
  11. Hengl T, Mendes de Jesus J, Heuvelink GB, Ruiperez Gonzalez M, Kilibarda M, Blagotic A, Shangguan W, Wright MN, Geng X, Bauer-Marschallinger B, Antonio Guevara M, Vargas R, MacMillan RA, Batjes NH, Leenaars JGB, Ribeiro E, Wheeler I, Mantel S, Kempen B. 2017. SoilGrids250m: Global gridded soil information based on machine learning. PLoS One 12(2): e0169748.
  12. Jeong TU, Cho EJ, Jeong JE, Ji HS, Lee KS, Yoo PJ, Kim GG, Choi JY, Park JH, Kim SH, Heo JS, Seo DC. 2015. Soil contamination of heavy metals in national industrial complexes, Korea. Korean Journal of Environmental Agriculture 34(2): 69-76. [Korean Literature] https://doi.org/10.5338/KJEA.2015.34.2.19
  13. Jia X, Hu B, Marchant BP, Zhou L, Shi Z, Zhu Y. 2019. A methodological framework for identifying potential sources of soil heavy metal pollution based on machine learning: A case study in the Yangtze Delta, China. Environmental Pollution 250: 601-609. https://doi.org/10.1016/j.envpol.2019.04.047
  14. Jun YJ. 2011. Study on characterization of air and soil pollution in Daejeon area using GIS. Master's thesis, Hanbat National University, pp. 1-44. [Korean Literature]
  15. Kim SM, Choi Y, Yi H, Park HD. 2017. Geostatistical prediction of heavy metal concentrations in stream sediments considering the stream networks. Environmental Earth Sciences 76(2): 1-18. [Korean Literature] https://doi.org/10.1007/s12665-016-6304-z
  16. KIMG. 2000. Natural geological mapping for natural environment.
  17. Knoll L, Breuer L, Bach M. 2019. Large scale prediction of groundwater nitrate concentrations from spatial data using machine learning. Science of the Total Environment 668: 1317-1327. https://doi.org/10.1016/j.scitotenv.2019.03.045
  18. Korea Institute of Geoscience and Mineral Resources. 2007. A method for treating fluorine-contaminated soil induced by fluorite. [Korean Literature]
  19. Korea Meteorological Administration. 2021. 2020 Metropolitan Meteorological Administration Climate Data Collection, 11-1360619-000006-10. [Korean Literature]
  20. Li F, Huang J, Zeng G, Liu W, Huang X, Huang B, Gu Y, Shi L, He X, He Y. 2015. Toxic metals in topsoil under different land uses from Xiandao District, middle China: distribution, relationship with soil characteristics, and health risk assessment. Environmental Science and Pollution Research 22(16): 12261-12275. https://doi.org/10.1007/s11356-015-4425-7
  21. Li Y, Wang S, Nan Z, Zang F, Sun H, Zhang Q, Huang W, Bao L. 2019. Accumulation, fractionation and health risk assessment of fluoride and heavy metals in soil-crop systems in northwest China. Science of the Total Environment 663: 307-314. https://doi.org/10.1016/j.scitotenv.2019.01.257
  22. Li Z, Ma Z, van der Kuijp TJ, Yuan Z, Huang L. 2014. A review of soil heavy metal pollution from mines in China: Pollution and health risk assessment. Science of The Total Environment 468-469: 843-853. https://doi.org/10.1016/j.scitotenv.2013.08.090
  23. Liang Z, Chen S, Yang Y, Zhou Y, Shi Z. 2019. High-resolution three-dimensional mapping of soil organic carbon in China: Effects of SoilGrids products on national modeling. Science of The Total Environment 685: 480-489. https://doi.org/10.1016/j.scitotenv.2019.05.332
  24. Ma W, Tan K, Du P. 2016. Predicting soil heavy metal based on Random Forest model. In 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 4331-4334, IEEE.
  25. Mahmoudzadeh H, Matinfar HR, Taghizadeh-Mehrjardi R, Kerry R. 2020. Spatial prediction of soil organic carbon using machine learning techniques in western Iran. Geoderma Regional 21: e00260.
  26. Ministry of Environment. 2010. Summary of the results of the 2009 soil measurement network and soil pollution survey. [Korean Literature]
  27. Pham BT, Pradhan B, Bui DT, Prakash I, Dholakia MB. 2016. A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India). Environmental Modelling & Software 84: 240-250. https://doi.org/10.1016/j.envsoft.2016.07.005
  28. Shahabi H, Hashim M. 2015. Landslide susceptibility mapping using GIS-based statistical models and Remote sensing data in tropical environment. Scientific Reports 5(1): 1-15. https://doi.org/10.9734/JSRR/2015/14076
  29. Shen LQ, Amatulli G, Sethi T, Raymond P, Domisch S. 2020. Estimating nitrogen and phosphorus concentrations in streams and rivers, within a machine learning framework. Scientific Data 7(1): 1-11. https://doi.org/10.1038/s41597-019-0340-y
  30. Varol M. 2011. Assessment of heavy metal contamination in sediments of the Tigris River (Turkey) using pollution indices and multivariate statistical techniques. Journal of Hazardous Materials 195: 355-364. https://doi.org/10.1016/j.jhazmat.2011.08.051
  31. Vasenev VI, Stoorvogel JJ, Leemans R, Valentini R, Hajiaghayeva RA. 2018. Projection of urban expansion and related changes in soil carbon stocks in the Moscow Region. Journal of Cleaner Production 170: 902-914. https://doi.org/10.1016/j.jclepro.2017.09.161
  32. Viscarra-Rossel RA, Lee J, Behrens T, Luo Z, Baldock J, Richards A. 2019. Continentalscale soil carbon composition and vulnerability modulated by regional environmental controls. Nature Geoscience 12(7): 547-552. https://doi.org/10.1038/s41561-019-0373-z
  33. Wang H, Yilihamu Q, Yuan M, Bai H, Xu H, Wu J. 2020. Prediction models of soil heavy metal (loid) s concentration for agricultural land in Dongli: A comparison of regression and random forest. Ecological Indicators 119: 106801.
  34. Yang H, Huang K, Zhang K, Weng Q, Zhang H, Wang F. 2021. Predicting heavy metal adsorption on soil with machine learning and mapping global distribution of soil adsorption capacities. Environmental Science & Technology 55(20): 14316-14328. https://doi.org/10.1021/acs.est.1c02479
  35. Yoon JK, Kim DH, Kim TS, Park JG, Chung IR, Kim JH, Kim H. 2009. Evaluation on natural background of the soil heavy metals in Korea. Journal of Soil and Groundwater Environment 14(3): 32-39.
  36. Zhang D, Tsai JJ. (Eds.). 2006. Advances in machine learning applications in software engineering. Igi Global.
  37. Zhang H, Yin A, Yang X, Fan M, Shao S, Wu J, Wu P, Zhang M, Gao C. 2021. Use of machine-learning and receptor models for prediction and source apportionment of heavy metals in coastal reclaimed soils. Ecological Indicators 122: 107233.
  38. Zhang H, Yin S, Chen Y, Shao S, Wu J, Fan M, Chen F, Gao C. 2020. Machine learning-based source identification and spatial prediction of heavy metals in soil in a rapid urbanization area, eastern China. Journal of Cleaner Production 273: 122858.
  39. Zhou T, Geng Y, Ji C, Xu X, Wang H, Pan J, Bumberger J, Haase D, Lausch A. 2021. Prediction of soil organic carbon and the C: N ratio on a national scale using machine learning and satellite data: A comparison between Sentinel-2, Sentinel-3 and Landsat-8 images. Science of the Total Environment 755: 142661.