APLGMLSep 9, 2019

Machine learning accelerates parameter optimization and uncertainty assessment of a land surface model

arXiv:1909.04196v229 citations
Originality Incremental advance
AI Analysis

This work addresses the computational bottleneck in parameter optimization for LSMs, which is crucial for atmospheric and related processes, though it is incremental as it builds on existing MCMC and machine learning techniques.

The paper tackles the problem of efficiently optimizing unknown soil and vegetation parameters in land surface models (LSMs) by combining Markov Chain Monte Carlo (MCMC) with machine learning, resulting in a method that is 50,000 times faster than direct MCMC application and improves the simulation of soil moisture and vegetation dynamics.

The performance of land surface models (LSMs) significantly affects the understanding of atmospheric and related processes. Many of the LSMs' soil and vegetation parameters were unknown so that it is crucially important to efficiently optimize them. Here I present a globally applicable and computationally efficient method for parameter optimization and uncertainty assessment of the LSM by combining Markov Chain Monte Carlo (MCMC) with machine learning. First, I performed the long-term (decadal scales) ensemble simulation of the LSM, in which each ensemble member has different parameters' values, and calculated the gap between simulation and observation, or the cost function, for each ensemble member. Second, I developed the statistical machine learning based surrogate model, which is computationally cheap but accurately mimics the relationship between parameters and the cost function, by applying the Gaussian process regression to learn the model simulation. Third, we applied MCMC by repeatedly driving the surrogate model to get the posterior probabilistic distribution of parameters. Using satellite passive microwave brightness temperature observations, both synthetic and real-data experiments in the Sahel region of west Africa were performed to optimize unknown soil and vegetation parameters of the LSM. The primary findings are (1) the proposed method is 50,000 times as fast as the direct application of MCMC to the full LSM; (2) the skill of the LSM to simulate both soil moisture and vegetation dynamics can be improved; (3) I successfully quantify the characteristics of equifinality by obtaining the full non-parametric probabilistic distribution of parameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes