Bayesian Maximum Entropy data fusion of field observed LAI and Landsat ETM+ derived LAI

Accurate high resolution LAI reference maps are necessary for the validation of coarser resolution satellite derived LAI products. In this paper, an efficient method for combining field observations and Landsat ETM+ derived LAI is proposed based on the Bayesian Maximum Entropy paradigm to get more accurate reference maps. This method can take account of the uncertainties associated with field observations and linear relationship between the ETM+ LAI and in situ measurements to perform a nonlinear prediction of the interest variable. A comparison with ETM+ derived LAI surfaces in three validation sites from the BIGFOOT project showed that the RMSE can be reduced by this approach, indicating a promising method in fusing different sources and different types of data.