Font Size: 

We analyze sensor data describing soil productivity in terms of NDVI and soil physical features measured in terms of electroresistivity. We adopt a Bayesian modeling approach to account for covariates with measurement error combined with regression models for aclass of continuous, discrete and mixed univariate response distributions with potentially all parameters depending on a semiparametricstructured additive predictor. Estimates are obtained by Markov chain Monte Carlo simulations.