Summary: This work reduced AI model uncertainty by developing a simple and optimized neural network architecture, which improves model prediction accuracy with limited training data.

Neural networks (NNs) have been widely used in surrogate modeling to reduce forward model evaluation time. Building a surrogate for a large-scale problem with many model responses requires a complex NN, which increases AI model parameter and structural uncertainty. This work used singular value decomposition method to reduce model responses dimensions, which simplifies NN architecture and thus reduces NN model parameter uncertainty. In addition, it used Bayesian optimization to optimize the NN hyperparameters, which produces a best-performing NN model and thus reduces model structural uncertainty (Figure 1). This simple and optimized NN architecture enables only 20 training data to produce accurate predictions otherwise 200 data are needed for the similar accuracy (Figure 2). Moreover, the resulted simple NN limits overfitting which is a fundamental problem of all data-centric methods.

Reference: https://www.geosci-model-dev.net/12/1791/2019/

Funding support: Research of this work is supported by LDRD AI initiative and software development is supported by DOE SciDAC project.