Exploring Randomly Wired Neural Networks for Climate Model Emulation

TL;DR

This study investigates the use of randomly wired neural networks as efficient and potentially superior alternatives to traditional architectures for climate model emulation, demonstrating notable performance improvements and comparable prediction speeds.

Contribution

It introduces the application of randomly wired neural networks to climate model emulation and compares their performance to standard models using the ClimateBench dataset.

Findings

Random wiring improves performance in less complex models by up to 30.4%.

Most randomly wired models outperform their standard counterparts.

Prediction speed remains unaffected by random wiring.

Abstract

Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts, but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this manuscript, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them to their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find that models with less complex architectures see the greatest performance improvement with the addition of random wiring (up to 30.4% for multilayer perceptrons). Furthermore, out of 24 different model architecture, parameter count, and prediction task combinations, only one saw a statistically significant performance deficit in randomly wired networks compared to their standard counterparts, with 14 cases showing statistically significant improvement. We also find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.