Predicting Water Permeability of the Soil Based on Open Data

Water permeability is a key concept when estimating load bearing capacity, mobility and infrastructure potential of a terrain. Northern sub-arctic areas have rather similar dominant soil types and thus prediction methods successful at Northern Finland may generalize to other arctic areas. In this paper we have predicted water permeability using publicly available natural resource data with regression analysis. The data categories used for regression were: airborne electro-magnetic and radiation, topographic height, national forest inventory data, and peat bog thickness. Various additional features were derived from original data to enable better predictions. The regression performances indicate that the prediction capability exists till 70-120 meters from the closest direct measurement points with C-index over 0.57 and MAPE over baseline. This generalization potential was measured using leave-one-out crossvalidation with a dead zone between the training and testing data sets.