REDS: Random Ensemble Deep Spatial prediction

TL;DR

REDS introduces a novel spatial prediction method combining random Fourier features and ensemble deep learning models, offering efficient uncertainty quantification for large datasets, demonstrated on simulated and satellite data.

Contribution

It develops a new spatial prediction approach using random features and ensemble deep models, enhancing computational efficiency and uncertainty estimation.

Findings

Effective on simulated data

Performs well on satellite data

Provides simple uncertainty quantification

Abstract

There has been a great deal of recent interest in the development of spatial prediction algorithms for very large datasets and/or prediction domains. These methods have primarily been developed in the spatial statistics community, but there has been growing interest in the machine learning community for such methods, primarily driven by the success of deep Gaussian process regression approaches and deep convolutional neural networks. These methods are often computationally expensive to train and implement and consequently, there has been a resurgence of interest in random projections and deep learning models based on random weights -- so called reservoir computing methods. Here, we combine several of these ideas to develop the Random Ensemble Deep Spatial (REDS) approach to predict spatial data. The procedure uses random Fourier features as inputs to an extreme learning machine (a deep neural model with random weights), and with calibrated ensembles of outputs from this model based on different random weights, it provides a simple uncertainty quantification. The REDS method is demonstrated on simulated data and on a classic large satellite data set.