Active emulation of computer codes with Gaussian processes -- Application to remote sensing

Abstract

Many fields of science and engineering rely on running simulations with complex and computationally expensive models to understand the involved processes in the system of interest. Nevertheless, the high cost involved hamper reliable and exhaustive simulations. Very often such codes incorporate heuristics that ironically make them less tractable and transparent. This paper introduces an active learning methodology for adaptively constructing surrogate models, i.e. emulators, of such costly computer codes in a multi-output setting. The proposed technique is sequential and adaptive, and is based on the optimization of a suitable acquisition function. It aims to achieve accurate approximations, model tractability, as well as compact and expressive simulated datasets. In order to achieve this, the proposed Active Multi-Output Gaussian Process Emulator (AMOGAPE) combines the predictive capacity of Gaussian Processes (GPs) with the design of an acquisition function that favors sampling in low density and fluctuating regions of the approximation functions. Comparing different acquisition functions, we illustrate the promising performance of the method for the construction of emulators with toy examples, as well as for a widely used remote sensing transfer code.

Keywords: Active learning; Gaussian process; Emulation; Design of experiments; Computer code; Remote sensing; Radiative transfer model

References in corpus (5)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• A Benchmark and Comparison of Active Learning for Logistic Regression
• Gaussian Process Regression Networks
• Orthogonal parallel MCMC methods for sampling and optimization

Cited by in corpus (14)

• Retrieval of aboveground crop nitrogen content with a hybrid machine learning method
• Gaussian Processes Retrieval of LAI from Sentinel-2 Top-of-Atmosphere Radiance Data
• Adaptive quadrature schemes for Bayesian inference via active learning
• Integrating Domain Knowledge in Data-driven Earth Observation with Process Convolutions
• Active Learning Approach to Optimization of Experimental Control
• Inference over radiative transfer models using variational and expectation maximization methods
• A survey of Monte Carlo methods for noisy and costly densities with application to reinforcement learning and ABC
• Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design
• Living in the Physics and Machine Learning Interplay for Earth Observation
• A Joint introduction to Gaussian Processes and Relevance Vector Machines with Connections to Kalman filtering and other Kernel Smoothers
• Deep Importance Sampling based on Regression for Model Inversion and Emulation
• Compressed particle methods for expensive models with application in Astronomy and Remote Sensing
• Optimality in Noisy Importance Sampling
• An automatic counting algorithm for the quantification and uncertainty analysis of the number of microglial cells trainable in small and heterogeneous datasets