Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability

TL;DR

This paper demonstrates how interpretable neural networks can uncover scientifically meaningful connections in geoscience data, especially climate patterns, by applying advanced interpretation techniques like layerwise relevance propagation.

Contribution

It introduces the application of neural network interpretation methods, particularly LRP, to geosciences, enabling the extraction of scientifically relevant insights from neural models.

Findings

LRP has potential in geoscience research.

Interpretation techniques reveal meaningful climate pattern connections.

Interpretable neural networks facilitate scientific hypothesis generation.

Abstract

Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have often been used within the geosciences to most accurately identify a desired output given a set of inputs, with the interpretation of what the network learns used as a secondary metric to ensure the network is making the right decision for the right reason. Neural network interpretation techniques have become more advanced in recent years, however, and we therefore propose that the ultimate objective of using a neural network can also be the interpretation of what the network has learned rather than the output itself. We show that the interpretation of neural networks can enable the discovery of scientifically meaningful connections within geoscientific data. In particular, we use two methods for neural network interpretation called backwards optimization and layerwise relevance propagation, both of which project the decision pathways of a network back onto the original input dimensions. To the best of our knowledge, LRP has not yet been applied to geoscientific research, and we believe it has great potential in this area. We show how these interpretation techniques can be used to reliably infer scientifically meaningful information from neural networks by applying them to common climate patterns. These results suggest that combining interpretable neural networks with novel scientific hypotheses will open the door to many new avenues in neural network-related geoscience research.