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

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 algori...

Full description

Saved in:
Bibliographic Details
Published in:Land (Basel) 2022-11, Vol.11 (11), p.2098
Main Authors: Yang, Hyunje, Lim, Honggeun, Moon, Haewon, Li, Qiwen, Nam, Sooyoun, Kim, Jaehoon, Choi, Hyung Tae
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Analysis
Big Data
Case studies
Data mining
Datasets
Decision trees
Digital mapping
digital soil mapping
Field capacity
Forest soils
Hierarchies
Learning algorithms
Machine learning
Mapping
Performance prediction
Prediction models
predictive uncertainty
sample site survey
Sample size
Sampling
soil investigation plan
Soil mapping
Spatial distribution
Topography
Training
Uncertainty
Variables
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2073-445X
2073-445X
DOI:10.3390/land11112098