MLLGAPMay 7, 2023

Fast parameter estimation of Generalized Extreme Value distribution using Neural Networks

arXiv:2305.04341v117 citations
Originality Incremental advance
AI Analysis

This work addresses a computational bottleneck for researchers and practitioners modeling extreme events like floods and heatwaves, though it is incremental as it improves efficiency rather than introducing a new paradigm.

The paper tackles the computational inefficiency of estimating parameters for the Generalized Extreme Value distribution using conventional maximum likelihood methods by proposing a neural network-based, likelihood-free approach, achieving comparable accuracy with significant computational speedup as demonstrated in simulations and applied to temperature data.

The heavy-tailed behavior of the generalized extreme-value distribution makes it a popular choice for modeling extreme events such as floods, droughts, heatwaves, wildfires, etc. However, estimating the distribution's parameters using conventional maximum likelihood methods can be computationally intensive, even for moderate-sized datasets. To overcome this limitation, we propose a computationally efficient, likelihood-free estimation method utilizing a neural network. Through an extensive simulation study, we demonstrate that the proposed neural network-based method provides Generalized Extreme Value (GEV) distribution parameter estimates with comparable accuracy to the conventional maximum likelihood method but with a significant computational speedup. To account for estimation uncertainty, we utilize parametric bootstrapping, which is inherent in the trained network. Finally, we apply this method to 1000-year annual maximum temperature data from the Community Climate System Model version 3 (CCSM3) across North America for three atmospheric concentrations: 289 ppm $\mathrm{CO}_2$ (pre-industrial), 700 ppm $\mathrm{CO}_2$ (future conditions), and 1400 ppm $\mathrm{CO}_2$, and compare the results with those obtained using the maximum likelihood approach.

Code Implementations1 repo
Foundations

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

Your Notes