Spatial extreme quantile estimation using a weighted log-likelihood approach

We propose to estimate spatial extreme quantiles by a weighted log-likelihood approach. It is assumed that the conditional distribution of the variable of interest follows a generalized extreme-value distribution. The associated response surfaces are estimated thanks to the introduction of weights in the log-likelihood. These weights depend on the distance between the point of interest and the observations. The construction of a proper distance relies on the combination of a multidimensional scaling unfolding with a neural network regression. Our approach is illustrated both on simulated and real rainfall datasets.