Efficient Parameter Calibration of Numerical Weather Prediction Models via Evolutionary Sequential Transfer Optimization

TL;DR

This paper introduces SEETO, an efficient transfer optimization algorithm for calibrating weather prediction models, significantly reducing computational costs while improving accuracy through knowledge transfer and surrogate modeling.

Contribution

The paper proposes a novel sequential transfer optimization method that leverages meteorological state representations and adaptive knowledge transfer to enhance calibration efficiency.

Findings

SEETO achieves a 6% average improvement in Hypervolume over baselines within 20 evaluations.

Compared to other methods, SEETO requires 28-64% fewer evaluations to reach similar performance.

Experiments across 10 calibration tasks demonstrate SEETO's superior efficiency and effectiveness.

Abstract

The configuration of physical parameterization schemes in Numerical Weather Prediction (NWP) models plays a critical role in determining the accuracy of the forecast. However, existing parameter calibration methods typically treat each calibration task as an isolated optimization problem. This approach suffers from prohibitive computational costs and necessitates performing iterative searches from scratch for each task, leading to low efficiency in sequential calibration scenarios. To address this issue, we propose the SEquential Evolutionary Transfer Optimization (SEETO) algorithm driven by the representations of the meteorological state. First, to accurately measure the physical similarity between calibration tasks, a meteorological state representation extractor is introduced to map high-dimensional meteorological fields into latent representations. Second, given the similarity in the latent space, a bi-level adaptive knowledge transfer mechanism is designed. At the solution level, superior populations from similar historical tasks are reused to achieve a "warm start" for optimization. At the model level, an ensemble surrogate model based on source task data is constructed to assist the search, employing an adaptive weighting mechanism to dynamically balance the contributions of source domain knowledge and target domain data. Extensive experiments across 10 distinct calibration tasks, which span varying source-target similarities, highlight SEETO's superior efficiency. Under a strict budget of 20 expensive evaluations, SEETO achieves a 6% average improvement in Hypervolume (HV) over two state-of-the-art baselines. Notably, to match SEETO's performance at this stage, the comparison algorithms would require an average of 64% and 28% additional evaluations, respectively. This presents a new paradigm for the efficient and accurate automated calibration of NWP model parameters.