지형분석을 이용한 산지토양 탄소의 분포 예측과 불확실성
Spatial Prediction of Soil Carbon Using Terrain Analysis in a Steep Mountainous Area and the Associated Uncertainties
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Soil carbon(C) is an essential property for characterizing soil quality. Understanding spatial patterns of soil C is particularly limited for mountain areas. This study aims to predict the spatial pattern of soil C using terrain analysis in a steep mountainous area. Specifically, model performances and prediction uncertainties were investigated based on the number of resampling repetitions. Further, important predictors for soil C were also identified. Finally, the spatial distribution of uncertainty was analyzed. A total of 91 soil samples were collected via conditioned latin hypercube sampling and a digital soil C map was developed using support vector regression which is one of the powerful machine learning methods. Results showed that there were no distinct differences of model performances depending on the number of repetitions except for 10-fold cross validation. For soil C, elevation and surface curvature were selected as important predictors by recursive feature elimination. Soil C showed higher values in higher elevation and concave slopes. The spatial pattern of soil C might possibly reflect lateral movement of water and materials along the surface configuration of the study area. The higher values of uncertainty in higher elevation and concave slopes might be related to geomorphological characteristics of the research area and the sampling design. This study is believed to provide a better understanding of the relationship between geomorphology and soil C in the mountainous ecosystem.
Abstract
Soil carbon(C) is an essential property for characterizing soil quality. Understanding spatial patterns of soil C is particularly limited for mountain areas. This study aims to predict the spatial pattern of soil C using terrain analysis in a steep mountainous area. Specifically, model performances and prediction uncertainties were investigated based on the number of resampling repetitions. Further, important predictors for soil C were also identified. Finally, the spatial distribution of uncertainty was analyzed. A total of 91 soil samples were collected via conditioned latin hypercube sampling and a digital soil C map was developed using support vector regression which is one of the powerful machine learning methods. Results showed that there were no distinct differences of model performances depending on the number of repetitions except for 10-fold cross validation. For soil C, elevation and surface curvature were selected as important predictors by recursive feature elimination. Soil C showed higher values in higher elevation and concave slopes. The spatial pattern of soil C might possibly reflect lateral movement of water and materials along the surface configuration of the study area. The higher values of uncertainty in higher elevation and concave slopes might be related to geomorphological characteristics of the research area and the sampling design. This study is believed to provide a better understanding of the relationship between geomorphology and soil C in the mountainous ecosystem.
참고문헌 (53)
- Ballabio, C., "Spatial prediction of soil properties in temperate mountain regions using support vector regression", Geoderma, 151, pp.338~350 (2009)
- Binkley, D., "Ecology and management of forest soils" (2012), John Wiley & Sons
- Birkeland, P. W., "Soils and geomorphology" (1999), Oxford University Press
- Bishop, C. M., "Neural networks for pattern recognition" (1995), Clarendon Press
- Borra, S., "Measuring the prediction error. A comparison of crossvalidation, bootstrap and covariance penalty methods", Computational Statistics and Data Analysis, 54(12), pp.2976~2989 (2010)
- Brady, N. C., "Elements of the nature and properties of soils" (2010), Prentice Hall
- Breiman, L., "Random forests", Machine learning, 45(1), pp.5~32 (2001)
- Chapin III, F. S., "Principles of terrestrial ecosystem ecology" (2011), Springer Science & Business Media
- Conrad, O., "System for Automated Geoscientific Analyses (SAGA) v. 2.1.4", Geoscientific Model Development, 8, pp.1991~2007 (2015)
- Dobos, E., "Geomorphometry: Concepts, Software, Applications, 33", pp.461~479 (2009), Elsevier
- Elith, J., "Species distribution models: Ecological explanation and prediction across space and time", Annual Review of Ecology, Evolution, and Systematics, 40, pp.677~697 (2009)
- Grunwald, S., "Environmental soil-landscape modeling:Geographic information technologies and pedometrics" (2006), Taylor & Francis
- Grunwald, S., "Multi-criteria characterization of recent digital soil mapping and modeling approaches", Geoderma, 152, pp.195~207 (2009)
- Hastie, T. J., "The elements of statistical learning: data mining, inference, and prediction" (2009), Springer
- Hjort, J., "Inclusion of explicit measures of geodiversity improve biodiversity models in a boreal landscape", Biodiversity and Conservation, 21(3), pp.3487~3506 (2012)
- Ibáñez, J. J., "Pedodiversity" (2013), CRC Press
- Jenny, H., "Factors of soil formation: a system of quantitative pedology" (1941), McGraw-Hill
- Jensen, J. R., "Remote sensing of the environment: An earth resource perspective" (2006), Pearson education
- Jeong, G., "Spatial Distribution and Predictability of Soil Properties in Mountain Regions", Journal of geography, 57, pp.21~42 (2011)
- 정진현, "우리나라 산림토양의 지역별 이화학적 특성", 한국임학회지, 91(6), pp.694~700 (2002), 한국임학회
- Karatzoglou, A., "kernlab - An S4 package for kernel methods in R", Journal of Statistical Software, 11(9), pp.1~20 (2004)
- Kim, J. H., "Estimating classification error rate:Repeated cross-validation, repeated hold-out and bootstrap", Computational Statistics and Data Analysis, 53(1), pp.3735~3745 (2009)
- Kuhn, M., "Applied predictive modeling" (2013), Springer
- Kunkel, M. L., "A simplified approach for estimating soil carbon and nitrogen stocks in semi-arid complex terrain", Geoderma, 165(1), pp.1~11 (2011)
- 권기태, "유전 알고리즘 기반의 서포트 벡터 회귀를 이용한 소프트웨어 비용산정", 정보처리학회논문지D, 16(5), pp.729~736 (2009), 한국정보처리학회
- Lagacherie, P., "Digital soil mapping: An Introductory Perspective, 31", pp.3~22 (2007), Elsevier
- Lal, R., "Soil Carbon Sequestration Impacts on Global Climate Change and Food Security", Science, 304, pp.1623~1627 (2004)
- 이광률, "소양강 상류 하안단구의 지형면 특성과 퇴적물 분석", 대한지리학회지, 39(1), pp.27~44 (2004), 대한지리학회
- Ließ, M., "Uncertainty in the spatial prediction of soil texture. Comparison of regression tree and Random Forest models", Geoderma, 170, pp.70~79 (2012)
- McBratney, A. B., "On digital soil mapping", Geoderma, 117, pp.3~52 (2003)
- McGill, W. B., "Comparative aspects of cycling of organic C, N, S and P through soil organic matter", Geoderma, 26, pp.267~286 (1981)
- McKenzie, N. J., "Spatial prediction of soil properties using environmental correlation", Geoderma, 89, pp.67~94 (1999)
- Milne, G., "Some suggested units of classification and mapping particularly for East African soils", Soil Research, 4(3), pp.183~198 (1935)
- Minasny, B., "Predicting soil properties in the tropics", Earth-Science Reviews, 106, pp.52~62 (2011)
- Minasny, B., "A conditioned Latin hypercube method for sampling in the presence of ancillary information", Computers and Geosciences, 32(9), pp.1378~1388 (2006)
- Minasny, B., "Digital Mapping of Soil Carbon", Advances in Agronomy, 118, pp.1~47 (2013)
- Minasny, B., "Soil Carbon", pp.45~57 (2014), Springer International Publishing Switzerland
- Osman, K. T., "Forest Soils: Properties and Management" (2013), Springer International Publishing Switzerland
- 박수진, "한반도 지형의 일반성과 특수성, 그리고 지속가능성", 대한지리학회지, 49(5), pp.656~674 (2014), 대한지리학회
- Park, S. J., "Identification and Characterization of Pedogeomorphological Processes on a Hillslope", Soil Science Society of America Journal, 66, pp.1897~1910 (2002)
- Park, S. J., "Identification of the spatial distribution of soils using a process-based terrain characterization", Geoderma, 103, pp.249~272 (2001)
- Peng, G., "Spatial distribution of soil organic carbon and total nitrogen based on GIS and geostatistics in a small watershed in a hilly area of northern china", PLOS ONE, 8(12), pp.1~9 (2013)
- Remesan, R., "Hydrological data driven modelling: A case study approach" (2015), Springer International Publishing Switzerland
- Schaetzl, R., "Treatise on Geomorphology", pp.145~158 (2013), Academic Press
- Schoenholtz, S. H., "A review of chemical and physical properties as indicators of forest soil quality:Challenges and opportunities", Forest Ecology and Management, 138(1-3), pp.335~356 (2000)
- Scull, P., "Predictive soil mapping: a review", Progress in Physical Geography, 27(2), pp.171~197 (2003)
- Smola, A., "A tutorial on support vector regression", Statistics and Computing, 14(3), pp.199~222 (2004)
- Vapnik, V., "The Nature of Statistical Learning Theory" (1995), Springer Verlag
- Vasques, G. M., "Influence of the spatial extent and resolution of input data on soil carbon models in Florida, USA", Journal of Geophysical Research: Biogeosciences, 117(4), pp.1~12 (2012)
- Wilson, J. P., "Terrain analysis:principles and applications" (2000), John Wiley and Sons
- Yoo, K., "Spatial patterns of soil organic carbon on hillslopes: Integrating geomorphic processes and the biological C cycle", Geoderma, 130, pp.47~65 (2006)
- "LAStools - efficient tools for LiDAR processing, version 2.1" (2014)[URL]
- "National Spatial Information Clearinghouse" (2015)[URL]