Indicator Patterns of Forced Change Learned by an Artificial Neural Network

Abstract

Many problems in climate science require the identification of signals obscured by both the “noise” of internal climate variability and differences across models. Following previous work, we train an artificial neural network (ANN) to predict the year of a given map of annual‐mean temperature (or precipitation) from forced climate model simulations. This prediction task requires the ANN to learn forced patterns of change amidst a background of climate noise and model differences. We then apply a neural network visualization technique (layerwise relevance propagation) to visualize the spatial patterns that lead the ANN to successfully predict the year. These spatial patterns thus serve as “reliable indicators” of the forced change. The architecture of the ANN is chosen such that these indicators vary in time, thus capturing the evolving nature of regional signals of change. Results are compared to those of more standard approaches like signal‐to‐noise ratios and multilinear regression in order to gain intuition about the reliable indicators identified by the ANN. We then apply an additional visualization tool (backward optimization) to highlight where disagreements in simulated and observed patterns of change are most important for the prediction of the year. This work demonstrates that ANNs and their visualization tools make a powerful pair for extracting climate patterns of forced change.

Anthropogenic influence on extreme precipitation over global land areas seen in multiple observational datasets

“…the year of the data) based on the spatial maps of the target variable from an ensemble of GCM simulations. Then a forced signal can be confirmed despite the presence of internal climate variability and inter-model variability 29,30 . This ANN DAI method can identify the non-linear combinations of the forced signal, internal climate variability and inter-model variability 30 .…”

“…Then a forced signal can be confirmed despite the presence of internal climate variability and inter-model variability 29,30 . This ANN DAI method can identify the non-linear combinations of the forced signal, internal climate variability and inter-model variability 30 . This method also has the advantage of being able to explicitly include internal variability and model uncertainty.…”

“…ref. 29,30). As we show in Section 3, imperfections in the prediction also can be physically interpreted within the D&A research framework (Figure 2).…”

“…If an observational dataset exhibits the same forced response as the GCMs, the predicted year time series from that dataset should have a statistically significant positive correlation with the actual year (r) and a linear regression of these two variables should produce a statistically significant positive slope 21,30 . Figure 3 shows these two metrics for observations, reanalysis and testing GCMs, from 51 random iterations of the ANN with different training/testing model sets.…”

“…A machine-learning-based method for the detection of anthropogenic influence (DAI) has been shown to overcome the reliance on trends 29,30 and is even capable of detecting the human influence from weather data on a single day 31 . An artificial neural network (ANN) is trained to predict a proxy of external forcing (e.g.…”