Machine Learning Magnetic Parameters from Spin Configurations

Phase Transformation Temperature Prediction in Steels via Machine Learning

The phase transformation temperature plays an important role in the design, production and heat treatment process of steels. In the present work, an improved version of the gradient-boosting method LightGBM has been utilized to study the influencing factors of the four phase transformation temperatures, namely Ac1, Ac3, the martensite transformation start (MS) temperature and the bainitic transformation start (BS) temperature. The effects of the alloying element were discussed in detail by comparing their influencing mechanisms on different phase transformation temperatures. The training accuracy was significantly improved by further introducing appropriate features related to atomic parameters. The melting temperature and coefficient of linear thermal expansion of the pure metals corresponding to the alloying elements, atomic Waber-Cromer pseudopotential radii and valence electron number were the top four among the eighteen atomic parameters used to improve the trained model performance. The training and prediction processes were analyzed using a partial dependence plot (PDP) and Shapley additive explanation (SHAP) methods to reveal the relationships between the features and phase transformation temperature.

Quantifying the Magnetic Interactions Governing Chiral Spin Textures Using Deep Neural Networks

The interplay of magnetic interactions in chiral multilayer films gives rise to nanoscale topological spin textures that form attractive elements for next-generation computing. Quantifying these interactions requires several specialized, time-consuming, and resource-intensive experimental techniques. Imaging of ambient domain configurations presents a promising avenue for high-throughput extraction of parent magnetic interactions. Here, we present a machine learning (ML)-based approach to simultaneously determine the key magnetic interactions─symmetric exchange, chiral exchange, and anisotropy─governing the chiral domain phenomenology in multilayers, using a single binarized image of domain configurations. Our convolutional neural network model, trained and validated on over 10,000 domain images, achieved R2 > 0.85 in predicting the parameters and independently learned the physical interdependencies between magnetic parameters. When applied to microscopy data acquired across samples, our model-predicted parameter trends are consistent with those of independent experimental measurements. These results establish ML-driven techniques as valuable, high-throughput complements to conventional determination of magnetic interactions and serve to accelerate materials and device development for nanoscale electronics.

Practical Hamiltonian learning with unitary dynamics and Gibbs states

We study the problem of learning the parameters for the Hamiltonian of a quantum many-body system, given limited access to the system. In this work, we build upon recent approaches to Hamiltonian learning via derivative estimation. We propose a protocol that improves the scaling dependence of prior works, particularly with respect to parameters relating to the structure of the Hamiltonian (e.g., its locality k). Furthermore, by deriving exact bounds on the performance of our protocol, we are able to provide a precise numerical prescription for theoretically optimal settings of hyperparameters in our learning protocol, such as the maximum evolution time (when learning with unitary dynamics) or minimum temperature (when learning with Gibbs states). Thanks to these improvements, our protocol has practical scaling for large problems: we demonstrate this with a numerical simulation of our protocol on an 80-qubit system.

Machine learning for structure-property mapping of Ising models: Scalability and limitations

We present a scalable machine learning (ML) framework for predicting intensive properties and particularly classifying phases of Ising models. Scalability and transferability are central to the unprecedented computational efficiency of ML methods. In general, linear-scaling computation can be achieved through the divide-and-conquer approach, and the locality of physical properties is key to partitioning the system into subdomains that can be solved separately. Based on the locality assumption, ML model is developed for the prediction of intensive properties of a finite-size block. Predictions of large-scale systems can then be obtained by averaging results of the ML model from randomly sampled blocks of the system. We show that the applicability of this approach depends on whether the block-size of the ML model is greater than the characteristic length scale of the system. In particular, in the case of phase identification across a critical point, the accuracy of the ML prediction is limited by the diverging correlation length. We obtain an intriguing scaling relation between the prediction accuracy and the ratio of ML block size over the spin-spin correlation length. Implications for practical applications are also discussed. While the two-dimensional Ising model is used to demonstrate the proposed approach, the ML framework can be generalized to other many-body or condensed-matter systems.

Learning Many-Body Hamiltonians with Heisenberg-Limited Scaling

Learning a many-body Hamiltonian from its dynamics is a fundamental problem in physics. In this Letter, we propose the first algorithm to achieve the Heisenberg limit for learning an interacting N-qubit local Hamiltonian. After a total evolution time of O(ε^{-1}), the proposed algorithm can efficiently estimate any parameter in the N-qubit Hamiltonian to ε error with high probability. Our algorithm uses ideas from quantum simulation to decouple the unknown N-qubit Hamiltonian H into noninteracting patches and learns H using a quantum-enhanced divide-and-conquer approach. The proposed algorithm is robust against state preparation and measurement error, does not require eigenstates or thermal states, and only uses polylog(ε^{-1}) experiments. In contrast, the best existing algorithms require O(ε^{-2}) experiments and total evolution time. We prove a matching lower bound to establish the asymptotic optimality of our algorithm.

Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

Deep learning has an increasing impact to assist research, allowing, for example, the discovery of novel materials. Until now, however, these artificial intelligence techniques have fallen short of discovering the full differential equation of an experimental physical system. Here we show that a dynamical neural network, trained on a minimal amount of data, can predict the behavior of spintronic devices with high accuracy and an extremely efficient simulation time, compared to the micromagnetic simulations that are usually employed to model them. For this purpose, we re-frame the formalism of Neural Ordinary Differential Equations to the constraints of spintronics: few measured outputs, multiple inputs and internal parameters. We demonstrate with Neural Ordinary Differential Equations an acceleration factor over 200 compared to micromagnetic simulations for a complex problem - the simulation of a reservoir computer made of magnetic skyrmions (20 minutes compared to three days). In a second realization, we show that we can predict the noisy response of experimental spintronic nano-oscillators to varying inputs after training Neural Ordinary Differential Equations on five milliseconds of their measured response to a different set of inputs. Neural Ordinary Differential Equations can therefore constitute a disruptive tool for developing spintronic applications in complement to micromagnetic simulations, which are time-consuming and cannot fit experiments when noise or imperfections are present. Our approach can also be generalized to other electronic devices involving dynamics.

Estimating the effective fields of spin configurations using a deep learning technique

The properties of complicated magnetic domain structures induced by various spin-spin interactions in magnetic systems have been extensively investigated in recent years. To understand the statistical and dynamic properties of complex magnetic structures, it is crucial to obtain information on the effective field distribution over the structure, which is not directly provided by magnetization. In this study, we use a deep learning technique to estimate the effective fields of spin configurations. We construct a deep neural network and train it with spin configuration datasets generated by Monte Carlo simulation. We show that the trained network can successfully estimate the magnetic effective field even though we do not offer explicit Hamiltonian parameter values. The estimated effective field information is highly applicable; it is utilized to reduce noise, correct defects in the magnetization data, generate spin configurations, estimate external field responses, and interpret experimental images.

A Deep Learning Perspective on Dropwise Condensation

Condensation is ubiquitous in nature and industry. Heterogeneous condensation on surfaces is typified by the continuous cycle of droplet nucleation, growth, and departure. Central to the mechanistic understanding of the thermofluidic processes governing condensation is the rapid and high-fidelity extraction of interpretable physical descriptors from the highly transient droplet population. However, extracting quantifiable measures out of dynamic objects with conventional imaging technologies poses a challenge to researchers. Here, an intelligent vision-based framework is demonstrated that unites classical thermofluidic imaging techniques with deep learning to fundamentally address this challenge. The deep learning framework can autonomously harness physical descriptors and quantify thermal performance at extreme spatio-temporal resolutions of 300 nm and 200 ms, respectively. The data-centric analysis conclusively shows that contrary to classical understanding, the overall condensation performance is governed by a key tradeoff between heat transfer rate per individual droplet and droplet population density. The vision-based approach presents a powerful tool for the study of not only phase-change processes but also any nucleation-based process within and beyond the thermal science community through the harnessing of big data.

Magnetic State Generation using Hamiltonian Guided Variational Autoencoder with Spin Structure Stabilization

Numerical generation of physical states is essential to all scientific research fields. The role of a numerical generator is not limited to understanding experimental results; it can also be employed to predict or investigate characteristics of uncharted systems. A variational autoencoder model is devised and applied to a magnetic system to generate energetically stable magnetic states with low local deformation. The spin structure stabilization is made possible by taking the explicit magnetic Hamiltonian into account to minimize energy in the training process. A significant advantage of the model is that the generator can create a long-range ordered ground state of spin configuration by increasing the role of stabilization even if the ground states are not necessarily included in the training process. It is expected that the proposed Hamiltonian-guided generative model can bring about great advances in numerical approaches used in various scientific research fields.