Sampling design optimization for soil mapping with random forest

• Published in: Geoderma Vol. 355; p. 113913
• Main Authors: Wadoux, Alexandre M.J-C., Brus, Dick J., Heuvelink, Gerard B.M.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2019
• Subjects: artificial intelligence; case studies; Conditioned Latin Hypercube; data collection; Europe; forestry equipment; k-means; LUCAS; Optimal design; Pedometrics; prediction; Random forest; soil map; soil organic carbon; soil properties; soil surveys; Spatial coverage; Spatial simulated annealing; Uncertainty assessment; Europe; Spatial simulated annealing; k-means; Random forest; LUCAS; Uncertainty assessment; Pedometrics; Conditioned Latin Hypercube; Spatial coverage; Optimal design

Machine learning techniques are widely employed to generate digital soil maps. The map accuracy is partly determined by the number and spatial locations of the measurements used to calibrate the machine learning model. However, determining the optimal sampling design for mapping with machine learnin...