Magnetic geometry has a significant effect on the level of turbulent transport in fusion plasmas. Here, we model and analyze this dependence using multiple machine learning methods and a dataset of > 200,000 nonlinear simulations of ion-temperature-gradient turbulence in diverse non-axisymmetric geometries. The dataset is generated using a large collection of both optimized and randomly generated stellarator equilibria. At fixed gradients, the turbulent heat flux varies between geometries by several orders of magnitude. Trends are apparent among the configurations with particularly high or low heat flux. Regression and classification techniques from machine learning are then applied to extract patterns in the dataset. Due to a symmetry of the gyrokinetic equation, the heat flux and regressions thereof should be invariant to translations of the raw features in the parallel coordinate, similar to translation invariance in computer vision applications. Multiple regression models including convolutional neural networks (CNNs) and decision trees can achieve reasonable predictive power for the heat flux in held-out test configurations, with highest accuracy for the CNNs. Using Spearman correlation, sequential feature selection, and Shapley values to measure feature importance, it is consistently found that the most important geometric lever on the heat flux is the flux surface compression in regions of bad curvature. The second most important feature relates to the magnitude of geodesic curvature. These two features align remarkably with surrogates that have been proposed based on theory, while the methods here allow a natural extension to more features for increased accuracy. The dataset, released with this publication, may also be used to test other proposed surrogates, and we find many previously published proxies do correlate well with both the heat flux and stability boundary.

We present our work on developing and training scalable graph foundation models (GFM) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFM training to tens of thousands of GPUs on datasets that consist of hundreds of millions of graphs. Our GFMs use multi-task learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as the total energy and atomic forces. Using over 150 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two United States Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge National Laboratory. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2,000 GPUs on Perlmutter and 16,000 GPUs on Frontier. Hyperparameter optimization (HPO) was performed on over 64,000 GPUs on Frontier to select GFM architectures with high accuracy. Early stopping was applied on each GFM architecture for energy awareness in performing such an extreme-scale task. The training of an ensemble of highest-ranked GFM architectures continued until convergence to establish uncertainty quantification (UQ) capabilities with ensemble learning. Our contribution opens the door for rapidly developing, training, and deploying GFMs using large-scale computational resources to enable AI-accelerated materials discovery and design.

Vision Transformers (ViTs) are pivotal for foundational models in scientific imagery, including Earth science applications, due to their capability to process large sequence lengths. While transformers for text has inspired scaling sequence lengths in ViTs, yet adapting these for ViTs introduces unique challenges. We develop distributed sequence parallelism for ViTs, enabling them to handle up to 1M tokens. Our approach, leveraging DeepSpeed-Ulysses and Long-Sequence-Segmentation with model sharding, is the first to apply sequence parallelism in ViT training, achieving a 94% batch scaling efficiency on 2,048 AMD-MI250X GPUs. Evaluating sequence parallelism in ViTs, particularly in models up to 10B parameters, highlighted substantial bottlenecks. We countered these with hybrid sequence, pipeline, tensor parallelism, and flash attention strategies, to scale beyond single GPU memory limits. Our method significantly enhances climate modeling accuracy by 20% in temperature predictions, marking the first training of a transformer model on a full-attention matrix over 188K sequence length.

Machine learning (ML) techniques and atomistic modeling have rapidly transformed materials design and discovery. Specifically, generative models can swiftly propose promising materials for targeted applications. However, the predicted properties of materials through the generative models often do not match with calculated properties through ab initio calculations. This discrepancy can arise because the generated coordinates are not fully relaxed, whereas the many properties are derived from relaxed structures. Neural network-based potentials (NNPs) can expedite the process by providing relaxed structures from the initially generated ones. Nevertheless, acquiring data to train NNPs for this purpose can be extremely challenging as it needs to encompass previously unknown structures. This study utilized extended ensemble molecular dynamics (MD) to secure a broad range of liquid- and solid-phase configurations in one of the metallic systems, nickel. Then, we could significantly reduce them through active learning without losing much accuracy. We found that the NNP trained from the distilled data could predict different energy-minimized closed-pack crystal structures even though those structures were not explicitly part of the initial data. Furthermore, the data can be translated to other metallic systems (aluminum and niobium), without repeating the sampling and distillation processes. Our approach to data acquisition and distillation has demonstrated the potential to expedite NNP development and enhance materials design and discovery by integrating generative models.