All Issue

2024 Vol.58, Issue 1 Preview Page

Research Article

A Study on Digital Soil Mapping of Forest Soil pH Based on Machine Learning

머신러닝 기반 산림 토양 pH의 디지털 토양도 작성 연구

Woojin Shima
,
Yoosoon Anb
,
Gwanyong Jeongc
심 우진a
,
안 유순b
,
정 관용c
aHK Research Professor, Asia Center, Seoul National University/ Instructor, Department of Geography, College of Social Science, Cheonnam National University
bResearch Fellow, Institute for Korean Regional Studies, Seoul National University/ Instructor, Department of Geography, College of Social Science, Seoul National University & Cheonnam National University/ Adjunctive Researcher, Future Earth-Korea Program, Seoul National University Asia Center
cAssociate Professor, Department of Geography, Chonnam National University
a서울대학교 아시아연구소 HK연구교수 및 전남대학교 지리학과 강사
b서울대학교 국토문제연구소 선임연구원 및 서울대학교 사회과학대학 지리학과 강사, 전남대학교 지리학과 강사, 서울대학교 아시아연구소 미래지구 프로그램 공동연구원
c전남대학교 지리학과 부교수
*gyjeong@jnu.ac.kr
31 March 2024. pp. 109-120
PDF XML Citation
Abstract

The geology and climate of the Korean Peninsula contribute to a high prevalence of acidic soil, and this situation is exacerbated by the recent increase in acid rain resulting from air pollution, further worsening the acidification of forest soils. In this research, through digital soil mapping to predict the spatial distribution of forest soil properties, we developed digital soil maps of forest soil pH across South Korea. Upon employing various machine learning methods, the random forest algorithm emerged as the most accurate. Key environmental factors influencing the distribution of forest soil pH were identified, including geographic, topographic, and parent material variables. The spatial distribution of forest soil pH revealed higher pH values in areas with alkaline bedrock (limestone and basalt) and lower pH values in areas dominated by gneiss parent material. Notably, highly acidic soils (pH < 4.5) were found in the metropolitan area, southwestern Chungcheong region, and the southern coast. Strongly acidic soil can negatively affect vegetation growth environment and carbon sequestration capacity, so anthropogenic factors that accelerate acidification should be reduced and continuously managed through periodic monitoring.

Keywords
Forest soil pH
Soil acidification
Digital soil mapping
Artificial intelligence
Random forest

한반도는 지질과 기후의 영향으로 산성 토양 비율이 높으며, 최근 대기오염물질에 의한 산성비의 유입으로 산림 토양의 산성화가 심해지고 있다. 본 연구에서는 산림 토양 특성의 지리적 분포를 예측할 수 있는 디지털 토양도 작성 기법을 적용하여 남한 전역의 산림 토양 pH 디지털 토양도를 구축하였다. 다양한 머신러닝 기법을 적용한 결과, 랜덤 포레스트 알고리즘이 가장 정확도가 높았다. 산림 토양 pH의 분포와 관련된 주요 환경 요인으로 지리변수, 지형변수, 모재변수가 도출되었다. 이 결과를 바탕으로 남한 일대의 산림 토양 pH 분포를 확인한 결과, 석회암과 현무암 등 염기성 모재가 분포한 지역에서 pH가 높게, 주로 편마암 모재가 주로 분포하는 지역에서 토양 pH가 낮게 나타났다. 이 중 강산성(pH 4.5 이하) 토양은 수도권과 충청권 서남부, 남해안 등에 주로 분포했다. 강산성 토양은 식생의 생육 환경과 탄소 격리 능력에 부정적인 영향을 미칠 수 있으므로 산성화를 가속화하는 인위적 요인을 저감하고 주기적인 모니터링을 통해 지속적으로 관리해야 할 것이다.

키워드
산림 토양 pH
토양 산성화
디지털 토양도 작성
인공지능
랜덤 포레스트
References
1
국립산림과학원, 2023, 2022 전국 산림토양 산성화 현황, 국립산림과학원.
2
권민영･김가은･정진현･최창은･박관수･김춘식･손요환, 2021, "1:5,000 산림입지토양도의 제작과 활용 및 향후 발전 방향," 한국산림과학회지 110(4): 479-495.
3
김준호, 2007, 산성비, 서울: 서울대학교 출판문화원.
4
심우진･박수진, 2020, "카테나 개념을 이용한 사면유형화 방법의 개발과 평가," 대한지리학회지 55(3): 231-251.
5
이아림･구남인, 2020, "우리나라 산림토양의 산성화 민감도평가와 그에 따른 토양 이화학적 특성 비교분석," 한국산림과학회지 109(2): 157-168.
6
정관용, 2018, "농업 경관에서 전자토양도 기법을 이용한 토양탄소 저장량 예측 및 경제적 가치평가," 국토지리학회지 52(3): 389-401.
7
정관용, 2019, "지리변수 기반 기계학습을 이용한 산지 소유역 유기층 토양 영양분의 공간적 분포 예측," 국토지리학회지 53(3): 257-270.
8
정진현･구교상･이충화･김춘식, 2002, "우리나라 산림토양의 지역별 이화학적 특성," 한국임학회지 91(6): 694-700.
9
Adhikari, K. and A. E. Hartemink, 2016, Linking soils to ecosystem services - A global review, Geoderma 262: 101-111. 10.1016/j.geoderma.2015.08.009
10
An, Y., W. Shim, and G. Jeong, 2023, High-resolution digital soil maps of forest soil nitrogen across South Korea using three machine learning algorithms, Forests 14(6): 1141. 10.3390/f14061141
11
Augusto, L., A. De Schrijver, L. Vesterdal, A. Smolander, C. Prescott, and J. Ranger, 2015, Influences of evergreen gymnosperm and deciduous angiosperm tree species on the functioning of temperate and boreal forests, Biological Reviews 90(2): 444-466. 10.1111/brv.1211924916992
12
Behrens, T., K. Schmidt, R. A. Viscarra Rossel, P. Gries, T. Scholten, and R. A. MacMillan, 2018, Spatial modelling with Euclidean distance fields and machine learning, European Journal of Soil Science 69(5): 757-770. 10.1111/ejss.12687
13
Bekku, Y. S, T. Nakatsubo, A. Kume, and H. Koizumi, 2004, Soil microbial biomass, respiration rate, and temperature dependence on a successional glacier foreland in Nylesund, Svalbard, Arctic, Antarctic, and Alpine Research 36(4): 395-399. 10.1657/1523-0430(2004)036[0395:SMBRRA]2.0.CO;2
14
Binkley, D. and R. Fisher, 2019, Ecology and management of forest soils, West Sussex: John Wiley & Sons. 10.1002/9781119455745
15
Böhner, J. and T. Selige, 2006, Spatial prediction of soil attributes using terrain analysis and climate regionalization, in Böhner, J., K.R. McCloy, and J. Strobl (eds.), SAGA - Analysis and modelling applications, Goettingen: Goettinger Geographische Abhandlungen.
16
Breiman, L., 2001, Random forest, Machine Learning 45: 5-32. 10.1023/A:1010933404324
17
Chen, S., D. Arrouays, V. L. Mulder, L. Poggio, B. Minasny, P. Roudier, and C. Walter, 2022, Digital mapping of GlobalSoilMap soil properties at a broad scale: A review, Geoderma 409: 115567. 10.1016/j.geoderma.2021.115567
18
Côté, L., S. Brown, D Paré., J. Fyles, and J. Bauhus, 2000, Dynamics of carbon and nitrogen mineralization in relation to stand type, stand age and soil texture in the boreal mixed wood, Soil Bio. Biochem 32: 1079-1090. 10.1016/S0038-0717(00)00017-1
19
Duddigan, S., T. Fraser, I. Green, A. Diaz, T. Sizmur, and M. Tibbett, 2021, Plant, soil and faunal responses to a contrived pH gradient, Plant and Soil 462: 505-524. 10.1007/s11104-021-04879-z
20
Gadd, G. M., 1999, Fungal production of citric and oxalic acid: Importance in metal speciation, physiology and biogeochemical processes, Advances in Microbial Physiology 41:47-92. 10.1016/S0065-2911(08)60165-410500844
21
Gerrard, J., 1992, Soil geomorphology: An integration of pedology and geomorphology, London: Chapman & Hall.
22
Goodfellow, I., Bengio, Y., and Courville. A., 2016, Deep learning, Cambridge: MIT Press.
23
Goulding, K. W. T., 2016, Soil acidification and the importance of liming agricultural soils with particular reference to the United Kingdom, Soil Use and Management 32: 390-399. 10.1111/sum.1227027708478PMC5032897
24
Grunwald, S., G. M. Vasques, and R. G. Rivero, 2015, Fusion of soil and remote sensing data to model soil properties, Advances in Agronomy 131: 1-109. 10.1016/bs.agron.2014.12.004
25
Hateffard, F., L. Steinbuch, and G. B. Heuvelink, 2024, Evaluating the extrapolation potential of random forest digital soil mapping, Geoderma 441: 116740. 10.1016/j.geoderma.2023.116740
26
Hénault, C., H. Bourennane, A. Ayzac, C. Ratié, N. Saby, J. P. Cohan, and C. L. Gall, 2019, Management of soil pH promotes nitrous oxide reduction and thus mitigates soil emissions of this greenhouse gas, Scientific Reports 9(1): 1-11. 10.1038/s41598-019-56694-331882900PMC6934481
27
Hengl, T., and R. A. MacMilland, 2019, Predictive soil mapping with R, Wageningen: OpenGeoHub Foundation.
28
Jeong, G., H. Oeverdieck, S. J. Park, B. Huwe, and M. Ließ, 2017, Spatial soil nutrients prediction using three supervised learning methods for assessment of land potentials in complex terrain, Catena 154: 73-84. 10.1016/j.catena.2017.02.006
29
Kreutzer, K., C. Beier, M. Bredemeier, K. Blanck, T. Cummins, and E. P. Farrell, 1998, Atmospheric deposition and soil acidification in five coniferous forest ecosystems: a comparison of the control plots of the EXMAN sites, Forest Ecology and Management 101: 125-142. 10.1016/S0378-1127(97)00130-8
30
Lee, W. S., 2018, Soil environmental characteristics in forest areas affected by forest fires and restored with different forest restoration methods in Gyeonju, Korea, International Journal of Applied Engineering Research 13(3): 1586-1592.
31
Li, Q., S. Ahn, T. Kim, and S. Im, 2021, Post-fire impacts of vegetation burning on soil properties and water repellency in a pine forest, South Korea, Forests 12: 708. 10.3390/f12060708
32
Liao, K., S. Wu, and Q. Zhu, 2016, Can soil pH be used to help explain soil organic carbon stocks?, CLEAN-Soil, Air, Water 44(12): 1685-1689. 10.1002/clen.201600229
33
Lundström, U. S., D. C. Bain, A. F. S. Taylor, and P. A. W. Van Hees, 2003, Effects of acidification and its mitigation with lime and wood ash on forest soil processes: A review, Water, Air and Soil Pollution: Focus 3: 5-28.
34
McBratney, A. B., M. M. Santos, and B. Minasny, 2003, On digital soil mapping, Geoderma 117(1-2): 3-52. 10.1016/S0016-7061(03)00223-4
35
Meesenburg, H., W. Riek, B. Ahrends, N. Eickenscheidt, E. Grüneberg, J. Evers, and N. Wellbrock, 2019, Soil acidification in German forest soils, in Wellbrock, N. and A. Bolte (eds.), Status and dynamics of forests in Germany, Cham: Springer. 10.1007/978-3-030-15734-0_4
36
Meng, C., D. Tian, H. Zeng, Z. Li, C. Yi, and S. Niu, 2019, Global soil acidification impacts on belowground processes, Environmental Research Letters 14(7): 074003. 10.1088/1748-9326/ab239c
37
Mulder, V. L., S. de Bruin, M. E. Schaepman, and T. R. Mayr, 2011, The use of remote sensing in soil and terrain mapping - A review, Geoderma 162(1-2): 1-19. 10.1016/j.geoderma.2010.12.018
38
Nussbaum, M., S. Zimmermann, L. Walthert, and A. Baltensweiler, 2023, Benefits of hierarchical predictions for digital soil mapping - An approach to map bimodal soil pH, Geoderma 437: 116579. 10.1016/j.geoderma.2023.116579
39
Osman, K.T., 2013, Soils: Properties and management, Dordrecht: Springer. 10.1007/978-94-007-5663-2
40
Reuter, H. I., L. R. Lado, T. Hengl, and L. Montanarella, 2008, Continental-scale digital soil mapping using European soil profile data: Soil pH, Hamburger Beiträge zur Physischen Geographie und Landschaftsökologie 19(1): 91-102.
41
Schaetzl, R. J., and M. L. Thompson, 2015, Soils: Genesis and geomorphology, New York: Cambridge University Press. 10.1017/CBO9781139061803PMC4286239
42
Sulaeman, Y., M. Sarwani, B. Minasny, A. B. McBratney, A. Sutandi, and B. Barus, 2012, Soil-landscape models to predict soil pH variation in the Subang Region of West Java, Indonesia, in Minasny, B., B. P. Malone, and A. B. McBratney (eds.), Digital soil assessments and beyond, Leiden: CRC Press. 10.1201/b12728-63
43
Trudgill, S., 1988, Soil and vegetation systems, Oxford: Oxford University Press.
44
Turner, B. L., 2008, Resource partitioning for soil phosphorus: A hypothesis, Journal of Ecology 96: 698-702. 10.1111/j.1365-2745.2008.01384.x
45
Wadoux, A. M. C., 2019, Using deep learning formultivariate mapping of soilwith quantified uncertainty, Geoderma 351: 59-70. 10.1016/j.geoderma.2019.05.012
46
Wadoux, A. M. C., Padarian, J., and Minasny, B., 2019, Multisource data integration for soil mapping using deep learning, Soil 5(1): 107-119. 10.5194/soil-5-107-2019
47
Walker, D. A., N. A. Auerbach, J. G. Bockheim, F. S. Chapin III, W. Eugster, J. Y. King, and G. L. Vourlitis, 1998, Energy and trace-gas fluxes across a soil pH boundary in the Arctic, Nature 394(6692): 469-472. 10.1038/28839
48
Wang, L., W. Wu, and H. B. Liu, 2019, Digital mapping of topsoil pH by random forest with residual kriging (RFRK) in a hilly region, Soil Research 57(4): 387-396. 10.1071/SR18319
49
Weil, R. R. and N. C. Brady, 2017, The nature and properties of soils, Columbus: Pearson.
50
Weiss, A.D., 2001, Topographic Positions and Landforms Analysis (poster), ESRI International User Conference, July 2001, San Diego: ESRI.
51
Wilding, L. P. and L. P. Drees, 1983, Spatial variability and pedology, in Wilding, L.P., N. E. Smeck, and G. F. Hall (eds.), Pedogenesis and soil taxonomy I. Concepts and interactions, Amsterdam: Elsevier Science Publisher. 10.1016/S0166-2481(08)70599-3
52
Yokoyama, R., M. Shirasawa, and R.J. Pike, 2002, Visualizing topography by openness: a new application of image processing to digital elevation models, Photogrammetric Engineering and Remote Sensing 68(3): 257-265.
53
Zevenbergen, L.W. and C.R. Thorne, 1987, Quantitative analysis of land surface topography, Earth Surface Processes and Landforms 12(1): 47-56. 10.1002/esp.3290120107
Information
  • Publisher :The Korean Association of Professional Geographers
  • Publisher(Ko) :국토지리학회
  • Journal Title :국토지리학회지
  • Journal Title(Ko) :THE GEOGRAPHICAL JOURNAL OF KOREA
  • Volume : 58
  • No :1
  • Pages :109-120
  • Received Date : 2024-03-08
  • Revised Date : 2024-03-26
  • Accepted Date : 2024-03-26
  • DOI :https://doi.org/10.22905/kaopqj.2024.58.1.7
Journal Informaiton 국토지리학회지 국토지리학회지
Online Submission
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • KCI 문헌 유사도 검사
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close