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

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.

Probing the randomness of the local current distributions of 316 L stainless steel corrosion in NaCl solution

“…S0. When multiple "maps of points" are taken at randomly chosen locations of heterogeneous surfaces, with each "map of points" comprising a representative number of the feature under analysis (in our case, grains/grain boundaries), then the sampling method is considered random [60][61][62]. Moreover, as the SECCM maps were described by sparse matrices (either regular or irregular), the randomness of our sampling method was further increased (the variability of the measurements increases when not every point on the grid is considered).…”

Identifying the Minimum Number of Flood Events for Reasonable Flood Peak Prediction of Ungauged Forested Catchments in South Korea

“…Analysis was conducted to determine the minimum number of flood events required for effective flood peak estimation. As the machine learning model is a data-driven model and is directly affected by the quality and quantity of data [28], we compared the relationship between data quantity and prediction capacity. The number of flood events contained in the data of the training dataset was increased gradually to observe any changes in prediction accuracy (Figure 4).…”

“…Deep learning approaches are data-driven models; therefore, the predictive accuracy is determined by the quality and quantity of the input data [28]. Thus, to develop a reasonable predictive model, an adequate amount of data must be collected, and the model should be trained based on these data.…”

Innovative graph neural network approach for predicting soil heavy metal pollution in the Pearl River Basin, China

“…Folorunso et al reviewed research predicting soil quality based on machine learning and analyzed the composition and quality of the soil, the prediction of soil parameters, existing soil datasets, soil maps, the influence of soil nutrients on crop growth, and the status of soil information system research 19 . Yang et al proposed a new optimal sampling algorithm capable of realistically enhancing insufficient soil properties using machine learning uncertainty prediction 20 . Sun et al developed a coupled retrieval approach to quantify nickel (Ni) concentration in agricultural soil using spaceborne hyperspectral imagery.…”