Achieving unbiased predictions of national-scale groundwater redox conditions via data oversampling and statistical learning

An important policy consideration for integrated land and water management is to understand the spatial distribution of nitrate attenuation in the groundwater system, for which redox condition is the key indicator. This paper proposes a methodology to accommodate the computational demands of large datasets, and presents national-scale predictions of groundwater redox class for New Zealand. Our approach applies statistical learning methods to predict redox status in areas without sample data. A key achievement was to overcome the influence of sample selection bias on model training via oversampling. National maps are provided for redox class and probability at specified depths. Our model provides unbiased predictions at a scale relevant for environmental policy, and enables targeted interventions that can achieve the desired environmental outcome in a more cost-effective manner than non-targeted interventions.