Simple Optimal Sampling Algorithm to Strengthen Digital Soil Mapping Using the Spatial Distribution of Machine Learning Predictive Uncertainty: A Case Study for Field Capacity Prediction

Hyunje Yang, Honggeun Lim, Haewon Moon, Qiwen Li, Sooyoun Nam, Jaehoon Kim and Hyung Tae Choi ()
Additional contact information
Hyunje Yang: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea
Honggeun Lim: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea
Haewon Moon: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea
Qiwen Li: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea
Sooyoun Nam: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea
Jaehoon Kim: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea
Hyung Tae Choi: Forest Environment and Conservation Department, National Institute of Forest Science, Seoul 02455, Republic of Korea

Land, 2022, vol. 11, issue 11, 1-18

Abstract: Machine learning models are now capable of delivering coveted digital soil mapping (DSM) benefits (e.g., field capacity (FC) prediction); therefore, determining the optimal sample sites and sample size is essential to maximize the training efficacy. We solve this with a novel optimal sampling algorithm that allows the authentic augmentation of insufficient soil features using machine learning predictive uncertainty. Nine hundred and fifty-three forest soil samples and geographically referenced forest information were used to develop predictive models, and FCs in South Korea were estimated with six predictor set hierarchies. Random forest and gradient boosting models were used for estimation since tree-based models had better predictive performance than other machine learning algorithms. There was a significant relationship between model predictive uncertainties and training data distribution, where higher uncertainties were distributed in the data scarcity area. Further, we confirmed that the predictive uncertainties decreased when additional sample sites were added to the training data. Environmental covariate information of each grid cell in South Korea was then used to select the sampling sites. Optimal sites were coordinated at the cell having the highest predictive uncertainty, and the sample size was determined using the predictable rate. This intuitive method can be generalized to improve global DSM.

Keywords: digital soil mapping; field capacity; machine learning; predictive uncertainty; sample site survey; soil investigation plan (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/11/11/2098/pdf (application/pdf)
https://www.mdpi.com/2073-445X/11/11/2098/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:11:y:2022:i:11:p:2098-:d:979647

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().