Search

The output of simulations can be extremely challenging to work with. For example, in large-scale particle-in-cell simulations in plasma physics, trillions of particles are simulated over millions of time steps, creating Petabytes of data. In this project, we develop methods to compress particle data by training conditional invertible neural networks (cINNs) on the particle data. The particles then can be reconstructed by running the trained model in generative mode. This allows us to reach up to millionfold compression, and a controlled loss of a accuracy. The models can be conditioned not only on the temporal axis but also on other types of simulation outputs of smaller data volume, leading potentially to even higher compression factors. In order to enable the neural network model to represent simulation data over long time spans, we apply methods from Continual Learning, where each new learning task is represented by a dataset produced by a simulation time step. This approach enables us to efficiently solve the inverse problem of particle data reconstruction from radiation data in a time-resolved manner by side-stepping demanding simulations.

The output of simulations can be extremely challenging to work with. For example, in large-scale particle-in-cell simulations in plasma physics, trillions of particles are simulated over millions of time steps, creating Petabytes of data. In this project, we develop methods to compress particle data by training conditional invertible neural networks (cINNs) on the particle data. The particles then can be reconstructed by running the trained model in generative mode. This allows us to reach up to millionfold compression, and a controlled loss of a accuracy. The models can be conditioned not only on the temporal axis but also on other types of simulation outputs of smaller data volume, leading potentially to even higher compression factors. In order to enable the neural network model to represent simulation data over long time spans, we apply methods from Continual Learning, where each new learning task is represented by a dataset produced by a simulation time step. This approach enables us to efficiently solve the inverse problem of particle data reconstruction from radiation data in a time-resolved manner by side-stepping demanding simulations.

The properties of electrons in matter are of fundamental importance. They give rise to virtually all molecular and material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets. Modeling and simulation of such diverse applications rely primarily on density functional theory (DFT), which has become the principal method for predicting the electronic structure of matter. While DFT calculations have proven to be very useful to the point of being recognized with a Nobel prize in 1998, their computational scaling limits them to small systems. We have developed a machine learning framework for predicting the electronic structure on any length scale. It shows up to three orders of magnitude speedup on systems where DFT is tractable and, more importantly, enables predictions on scales where DFT calculations are infeasible. Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances science to frontiers intractable with any current solutions. This unprecedented modeling capability opens up an inexhaustible range of applications in astrophysics, novel materials discovery, and energy solutions for a sustainable future.

The properties of electrons in matter are of fundamental importance. They give rise to virtually all molecular and material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets. Modeling and simulation of such diverse applications rely primarily on density functional theory (DFT), which has become the principal method for predicting the electronic structure of matter. While DFT calculations have proven to be very useful to the point of being recognized with a Nobel prize in 1998, their computational scaling limits them to small systems. We have developed a machine learning framework for predicting the electronic structure on any length scale. It shows up to three orders of magnitude speedup on systems where DFT is tractable and, more importantly, enables predictions on scales where DFT calculations are infeasible. Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances science to frontiers intractable with any current solutions. This unprecedented modeling capability opens up an inexhaustible range of applications in astrophysics, novel materials discovery, and energy solutions for a sustainable future.

Test whether two sets of points are samples from the same D-dimensional probability distribution without having access to the PDF.

We strive to popularize the usage of uncertainty quantification methods in machine learning through publications and application in various projects covering diverse fields from regression and classification to instance segmentation. In addition, we employ domain shift detection techniques to tackle population-level out-of-distribution scenarios. In all cases, the goal is to assess model prediction validity given unseen test data.

Understanding the properties of matter under extreme conditions is essential for advancing our fundamental understanding of astrophysical objects and guides the search for exoplanets, it propels the discovery of materials exhibiting novel properties that emerge under high temperatures and pressure, it enables novel technologies such as nuclear fusion, and supports diagnostics of experiments at large-scale brilliant photon sources. While modeling in this challenging research domain has so far relied on first-principles methods [1,2], these turn out to be computationally too expensive for simulations at the required time and length scales. Reduced models, such as average-atom models [3], come at a reduced computational and are useful by connecting atomistic details with hydrodynamics simulations, but they provide less accuracy. Artificial intelligence (AI) has great potential for accelerating electronic structure calculations to hitherto unattainable scales [4]. I will present our recent efforts on accomplishing speeding up Kohn-Sham density functional theory calculations with deep neural networks in terms of our Materials Learning Algorithms framework [5,6] by illustrating results for metals across their melting point. Furthermore, our results towards automated machine-learning save orders of magnitude in computational efforts for finding suitable neural networks and set the stage for large-scale AI-driven investigations [7]. [1] T. Dornheim, A. Cangi, K. Ramakrishna, M. Böhme, S. Tanaka, J. Vorberger, Phys. Rev. Lett. 125, 235001 (2020). [2] K. Ramakrishna, A. Cangi, T. Dornheim, J. Vorberger, Phys. Rev. B 103, 125118 (2021). [3] T. J. Callow, E. Kraisler, S. B. Hansen, A. Cangi, Phys. Rev. Research 4, 023055 (2022). [4] L. Fiedler, K. Shah, M. Bussmann, A. Cangi, Phys. Rev. Materials 6, 040301 (2022). [5] A. Cangi et al., MALA, https://doi.org/10.5281/zenodo.5557254 (2021). [6] J. A. Ellis, L. Fiedler, G. A. Popoola, N. A. Modine, J. A. Stephens, A. P. Thompson, A.

Test whether two sets of points are samples from the same D-dimensional probability distribution without having access to the PDF.

The properties of electrons in matter are of fundamental importance. They give rise to virtually all molecular and material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets. Modeling and simulation of such diverse applications rely primarily on density functional theory (DFT), which has become the principal method for predicting the electronic structure of matter. While DFT calculations have proven to be very useful to the point of being recognized with a Nobel prize in 1998, their computational scaling limits them to small systems. We have developed a machine learning framework for predicting the electronic structure on any length scale. It shows up to three orders of magnitude speedup on systems where DFT is tractable and, more importantly, enables predictions on scales where DFT calculations are infeasible. Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances science to frontiers intractable with any current solutions. This unprecedented modeling capability opens up an inexhaustible range of applications in astrophysics, novel materials discovery, and energy solutions for a sustainable future.

Introduction to kernel methods and Gaussian processes

We strive to popularize the usage of uncertainty quantification methods in machine learning through publications and application in various projects covering diverse fields from regression and classification to instance segmentation. In addition, we employ domain shift detection techniques to tackle population-level out-of-distribution scenarios. In all cases, the goal is to assess model prediction validity given unseen test data.

Machine Learning (ML) based methods are proliferating in industry, society, science and physics in particular in the last years. Not only do ML tools allow inferences from experimental data, but also have shown to be an inroads to previously unreachable theoretical or experimental domains. In this presentation, I'll introduce Helmholtz AI as a funded networking activity within Helmholtz to support matter research in using ML for science. I'll dive into how and why the program is split into research and collaboration-as-a-service staff. If time allows, I'll discuss how we approach ML projects with scientists from a consulting point of view.

Understanding the properties of matter under extreme conditions is essential for advancing our fundamental understanding of astrophysical objects and guides the search for exoplanets, it propels the discovery of materials exhibiting novel properties that emerge under high temperatures and pressure, it enables novel technologies such as nuclear fusion, and supports diagnostics of experiments at large-scale brilliant photon sources. While modeling in this challenging research domain has so far relied on first-principles methods [1,2], these turn out to be computationally too expensive for simulations at the required time and length scales. Reduced models, such as average-atom models [3], come at a reduced computational and are useful by connecting atomistic details with hydrodynamics simulations, but they provide less accuracy. Artificial intelligence (AI) has great potential for accelerating electronic structure calculations to hitherto unattainable scales [4]. I will present our recent efforts on accomplishing speeding up Kohn-Sham density functional theory calculations with deep neural networks in terms of our Materials Learning Algorithms framework [5,6] by illustrating results for metals across their melting point. Furthermore, our results towards automated machine-learning save orders of magnitude in computational efforts for finding suitable neural networks and set the stage for large-scale AI-driven investigations [7]. [1] T. Dornheim, A. Cangi, K. Ramakrishna, M. Böhme, S. Tanaka, J. Vorberger, Phys. Rev. Lett. 125, 235001 (2020). [2] K. Ramakrishna, A. Cangi, T. Dornheim, J. Vorberger, Phys. Rev. B 103, 125118 (2021). [3] T. J. Callow, E. Kraisler, S. B. Hansen, A. Cangi, Phys. Rev. Research 4, 023055 (2022). [4] L. Fiedler, K. Shah, M. Bussmann, A. Cangi, Phys. Rev. Materials 6, 040301 (2022). [5] A. Cangi et al., MALA, https://doi.org/10.5281/zenodo.5557254 (2021). [6] J. A. Ellis, L. Fiedler, G. A. Popoola, N. A. Modine, J. A. Stephens, A. P. Thompson, A.

Scripts and Models for "Predicting the Electronic Structure of Matter on Ultra-Large Scales" This data set contains scripts and models to reproduce the results of our manuscript "Physics-informed Machine Learning Models for Scalable Density Functional Theory Calculations". The scripts are supposed to be used in conjunction with the ab-initio data sets also published alongside our research article. Requirements python>=3.7.x mala>=1.1.0 ase numpy Contents | Folder name | Description | |------------------|--------------------------------------------------| | data_analysis/ | Run script for RDF calculations | | model_inference/ | Run script to run inference based on MALA models | | model_training/ | Run script to train MALA models | | trained_models/ | Trained models for beryllium and aluminium | re> 

The properties of electrons in matter are of fundamental importance. They give rise to virtually all molecular and material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets. Modeling and simulation of such diverse applications rely primarily on density functional theory (DFT), which has become the principal method for predicting the electronic structure of matter. While DFT calculations have proven to be very useful to the point of being recognized with a Nobel prize in 1998, their computational scaling limits them to small systems. We have developed a machine learning framework for predicting the electronic structure on any length scale. It shows up to three orders of magnitude speedup on systems where DFT is tractable and, more importantly, enables predictions on scales where DFT calculations are infeasible. Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances science to frontiers intractable with any current solutions. This unprecedented modeling capability opens up an inexhaustible range of applications in astrophysics, novel materials discovery, and energy solutions for a sustainable future.

The successful characterization of high energy density (HED) phenomena in experimental facilities is possible only with numerical modeling. The persistence of electron correlation in HED matter is one of the greatest challenges for accurate numerical modeling and has hitherto impeded our ability to model HED phenomena across multiple length and time scales at sufficient accuracy. Standard methods from electronic structure theory (density functional theory) capture electron correlation at high accuracy, but are limited to small scales due to their high computational cost. In this talk, I will present a solution to this problem in terms of a data-driven modeling framework for matter under extreme conditions – the Materials Learning Algorithms (MALA) package. MALA generates surrogate models based on deep neural networks that reproduce the output of density functional theory calculations at a fraction of the computational cost. This opens up the path towards multiscale materials modeling for matter under ambient and extreme conditions at a computational scale and cost that is unattainable with current algorithms. MALA is modular and open source. It enables users to perform the entire modeling toolchain using only a few lines of code. MALA is jointly developed by the Center for Advanced Systems Understanding (CASUS), Sandia National Laboratories (SNL), and Oak Ridge National Laboratory (ORNL).

An introduction to Automatic Differentiation with theory and code examples.

Uncertainty quantification for neural network models

In this presentation, I'd like to present the current status of Helmholtz AI consultancy for matter research in Helmholtz. I'd provide sneak previews into past and ongoing vouchers we embarked upon for the accelerator physics community and other collaborators. I'll try my best to give some insights on what we use our cluster for and why. Last but not least, I'll discuss challenges we faced along the way and will highlight some future directions if time allows.

Helmholtz AI has been available for members of ARD since its inception 2019/20. In this presentation, I'd like to present the current status of Helmholtz AI consultancy for matter research in Helmholtz. I'd provide sneak previews into past and ongoing vouchers we embarked upon for the accelerator physics community. Last but not least, I'll discuss challenges we faced along the way and will highlight some future directions if time allows.

MALA (Materials Learning Algorithms) is a data-driven framework to generate surrogate models of density functional theory calculations based on machine learning. Its purpose is to enable multiscale modeling by bypassing computationally expensive steps in state-of-the-art density functional simulations.

This data set was crowdsourced at the 2021 Helmholtz MT ARD ST3 meeting from attendants of the Machine Learning Tutorial on Sep 30, 2021. For more details on the event, see https://indico.desy.de/event/28823

A jupyter notebook that can predict the shoe size of a person based on their gender, height and weight. This is a notebook meant for training purposes to show case how public data can be used to train a machine learning predictor. This notebook uses a public crowd-sourced dataset from https://doi.org/10.5281/zenodo.5541145 to conduct the training.

An introduction to Automatic Differentiation with theory and code examples.