National Scale 3D Mapping of Soil pH Using a Data Augmentation Approach

Pierre Roudier,Sarah J Richardson,Olivia R Burge,James K Mccarthy,Anne-Gaelle Ausseil,Gerard J Grealish

doi:10.3390/rs12182872

Pierre Roudier, Sarah J Richardson + Show 4 more

Open Access

https://doi.org/10.3390/rs12182872

Copy DOI

Abstract

Understanding the spatial variation of soil pH is critical for many different stakeholders across different fields of science, because it is a master variable that plays a central role in many soil processes. This study documents the first attempt to map soil pH (1:5 H2O) at high resolution (100 m) in New Zealand. The regression framework used follows the paradigm of digital soil mapping, and a limited number of environmental covariates were selected using variable selection, before calibration of a quantile regression forest model. In order to adapt the outcomes of this work to a wide range of different depth supports, a new approach, which includes depth of sampling as a covariate, is proposed. It relies on data augmentation, a process where virtual observations are drawn from statistical populations constructed using the observed data, based on the top and bottom depth of sampling, and including the uncertainty surrounding the soil pH measurement. A single model can then be calibrated and deployed to estimate pH a various depths. Results showed that the data augmentation routine had a beneficial effect on prediction uncertainties, in particular when reference measurement uncertainties are taken into account. Further testing found that the optimal rate of augmentation for this dataset was 3-fold. Inspection of the final model revealed that the most important variables for predicting soil pH distribution in New Zealand were related to land cover and climate, in particular to soil water balance. The evaluation of this approach on those validation sites set aside before modelling showed very good results (R2=0.65, CCC=0.79, RMSE=0.54), that significantly out-performed existing soil pH information for the country.

Highlights

Soil pH indicates the relative acidity or alkalinity of the soil, and is a master variable in soil science, both in managed and un-managed landscapes [1]
The objectives of this study were to (1) calibrate a soil pH digital soil mapping (DSM) model for New Zealand that uses the best set of observations available for the country; (2) test the potential of a novel 3D DSM approach that augments the amount of depth and attribute information using a resampling strategy; (3) evaluate the results of this model with those of a more traditional 2.5D approach; and (4) compare the accuracy of our model against existing soil pH products available for New Zealand
The observed variability, as assessed by the inter-quartile range (IQR), shows the 100–200 cm horizon to be the most variable, which can be explained by the differences in parent material that contribute to variations deeper in the soil profile

Summary

Introduction

Soil pH indicates the relative acidity or alkalinity of the soil, and is a master variable in soil science, both in managed and un-managed landscapes [1] It plays a central role in numerous soil functions, soil quality, and fertility processes, impacting on physical structure, carbon, nitrogen, and phosphorus cycling, biological activity and regulation, bioavailibility of a range of nutrients, mobility and uptake of some trace elements such as cadmium [2,3]. This translates to soil pH being a parameter that is critical for a wide range of applications and stakeholders, such as the fertiliser industry, the soil ecology community, and soil quality initiatives. Soil pH has been identified as one of the key indicators for monitoring soil quality [9,10] and soil security [11]

Objectives

Methods

Results

Discussion

Conclusion