Search NASA⌕ Search

Engineering topics

Tamblyn, Isaac

Publications and source records attributed to Tamblyn, Isaac.

18 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Learning stochastic dynamics and predicting emergent behavior using transformers

We show that a neural network originally designed for language processing can learn the dynamical rules of a stochastic system by observation of a single dynamical trajectory of the system, and can accurately predict its emergent behavior under conditions not observed during training. We consider a lattice model of active matter undergoing continuous-time Monte Carlo dynamics, simulated at a density at which its steady state comprises small, dispersed clusters. We train a neural network called a transformer on a single trajectory of the model. The transformer, which we show has the capacity to represent dynamical rules that are numerous and nonlocal, learns that the dynamics of this model consists of a small number of processes. Forward-propagated trajectories of the trained transformer, at densities not encountered during training, exhibit motility-induced phase separation and so predict the existence of a nonequilibrium phase transition. Transformers have the flexibility to learn dynamical rules from observation without explicit enumeration of rates or coarse-graining of configuration space, and so the procedure used here can be applied to a wide range of physical systems, including those with large and complex dynamical generators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning

Here using a model heat engine, we show that neural-network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Correspondence between neuroevolution and gradient descent

Abstract We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise. Averaged over independent realizations of the learning process, neuroevolution is equivalent to gradient descent on the loss function. We use numerical simulation to show that this correspondence can be observed for finite mutations, for shallow and deep neural networks. Our results provide a connection between two families of neural-network training methods that are usually considered to be fundamentally different.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Dynamical Large Deviations of Two-Dimensional Kinetically Constrained Models Using a Neural-Network State Ansatz

We use a neural-network ansatz originally designed for the variational optimization of quantum systems to study dynamical large deviations in classical ones. We use recurrent neural networks to describe the large deviations of the dynamical activity of model glasses, kinetically constrained models in two dimensions. We present the first finite size-scaling analysis of the large-deviation functions of the two-dimensional Fredrickson-Andersen model, and explore the spatial structure of the high-activity sector of the South-or-East model. These results provide a new route to the study of dynamical large-deviation functions, and highlight the broad applicability of the neural-network state ansatz across domains in physics.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Neuroevolutionary Learning of Particles and Protocols for Self-Assembly

Within simulations of molecules deposited on a surface we show that neuroevolutionary learning can design particles and time-dependent protocols to promote self-assembly, without input from physical concepts such as thermal equilibrium or mechanical stability and without prior knowledge of candidate or competing structures. Furthermore, the learning algorithm is capable of both directed and exploratory design: it can assemble a material with a user-defined property, or search for novelty in the space of specified order parameters. In the latter mode it explores the space of what can be made, rather than the space of structures that are low in energy but not necessarily kinetically accessible.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2021

Watch and learn—a generalized approach for transferrable learning in deep neural networks via physical principles

Transfer learning refers to the use of knowledge gained while solving a machine learning task and applying it to the solution of a closely related problem. Such an approach has enabled scientific breakthroughs in computer vision and natural language processing where the weights learned in state-of-the-art models can be used to initialize models for other tasks which dramatically improve their performance and save computational time. Here we demonstrate an unsupervised learning approach augmented with basic physical principles that achieves fully transferrable learning for problems in statistical physics across different physical regimes. By coupling a sequence model based on a recurrent neural network to an extensive deep neural network, we are able to learn the equilibrium probability distributions and inter-particle interaction models of classical statistical mechanical systems. Our approach, distribution-consistent learning, DCL, is a general strategy that works for a variety of canonical statistical mechanical models (Ising and Potts) as well as disordered interaction potentials. Using data collected from a single set of observation conditions, DCL successfully extrapolates across all temperatures, thermodynamic phases, and can be applied to different length-scales. This constitutes a fully transferrable physics-based learning in a generalizable approach.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Inverse Design of a Graphene-Based Quantum Transducer via Neuroevolution

Here we introduce an inverse design framework based on artificial neural networks, genetic algorithms, and tight-binding calculations, capable to optimize the very large configuration space of nanoelectronic devices. Our non-linear optimization procedure operates on trial Hamiltonians through superoperators controlling growth policies of regions of distinct doping. We demonstrate that our algorithm optimizes the doping of graphene-based three-terminal devices for valleytronics applications, monotonously converging to synthesizable devices with high merit functions in a few thousand evaluations (out of similar or equal to ≃ 2 3800 possible configurations). The best-performing device allowed for a terminal-specific separation of valley currents with similar or equal to ≃ 96% (≃ 94%) K(K') valley purity. Importantly, the devices found through our non-linear optimization procedure have both a higher merit function and higher robustness to defects than the ones obtained through geometry optimization.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Evolutionary reinforcement learning of dynamical large deviations

In this work, we show how to bound and calculate the likelihood of dynamical large deviations using evolutionary reinforcement learning. An agent, a stochastic model, propagates a continuous-time Monte Carlo trajectory and receives a reward conditioned upon the values of certain path-extensive quantities. Evolution produces progressively fitter agents, potentially allowing the calculation of a piece of a large-deviation rate function for a particular model and path-extensive quantity. For models with small state spaces, the evolutionary process acts directly on rates, and for models with large state spaces, the process acts on the weights of a neural network that parameterizes the model's rates. This approach shows how path-extensive physics problems can be considered within a framework widely used in machine learning.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2019

Optimizing thermodynamic trajectories using evolutionary reinforcement learning

Using a model heat engine we show that neural network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally-efficient Carnot, Stirling, or Otto cycles. Given additional irreversible processes this evolutionary scheme learns a hitherto unknown thermodynamic cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

A Density Functional Tight Binding Model with an Extended Basis Set and Three-Body Repulsion for Hydrogen under Extreme Thermodynamic Conditions

Here, we present a new DFTB-p3b density functional tight binding model for hydrogen at extremely high pressures and temperatures, which includes a polarizable basis set ( p ) and a three-body environmentally dependent repulsive potential ( 3b ). We find that use of an extended basis set is necessary under dissociated liquid conditions to account for the substantial p-orbital character of the electronic states around the Fermi energy. The repulsive energy is determined through comparison to cold curve pressures computed from density functional theory (DFT) for the hexagonal close-packed solid, as well as pressures from thermally equilibrated DFT-MD simulations of the liquid phase. In particular, we observe improved agreement in our DFTB-p3b model with previous theoretical and experimental results for the shock Hugoniot of hydrogen up to 100 GPa and 25000 K, compared to a standard DFTB model using pairwise interactions and an s-orbital basis set, only. In conclusion, the DFTB-p3b approach discussed here provides a general method to extend the DFTB method for a wide variety of materials over a significantly larger range of thermodynamic conditions than previously possible.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2013

Reply to “Comment on ‘Prebiotic Chemistry Within a Simple Impacting Icy Mixture’”

In a recent article in this journal, we use quantum simulations to describe the possible formation of prebiotic material from impacting astrophysical icy mixtures on early Earth. Our model system included only simple starting materials found in cometary material, namely a mixture of 2 H 2 O:1 CO:1 CO 2 :1 CH 3 OH:1 NH 3 . Here, we have cycled this mixture sequentially through all of the thermodynamic states of an impact event: shock compression due to impact (high temperature, high pressure end states), expansion to ambient pressures (high temperature, low pressure end states), and cooling to ambient temperatures (low temperature, low pressure end states). Our results predicted that a number of prebiotic materials could be synthesized ultimately upon relaxing to a low temperature, low pressure state, including protein-forming amino acids. Amino acids and peptides are known to be metastable compounds with high activation energies for decomposition. Here, our predictions have since been confirmed by recent gas gun experiments on an icy mixture of similar composition and at similar thermodynamic conditions to our studies, where the protein forming amino acids glycine and alanine were detected as end products.

36 MATERIALS SCIENCE↗
DOE OSTI2013

Theory of Covalent Adsorbate Frontier Orbital Energies on Functionalized Light-Absorbing Semiconductor Surfaces.

Functional hybrid interfaces between organic molecules and semiconductors are central to many emerging information and solar energy conversion technologies. Here we demonstrate a general, empirical parameter-free approach for computing and understanding frontier orbital energies - or redox levels - of a broad class of covalently bonded organic-semiconductor surfaces. We develop this framework in the context of specific density functional theory (DFT) and many-body perturbation theory calculations, within the GW approximation, of an exemplar interface, thiophene-functionalized silicon (111). Through detailed calculations taking into account structural and binding energetics of mixed-monolayers consisting of both covalently attached thiophene and hydrogen, chlorine, methyl, and other passivating groups, we quantify the impact of coverage, nonlocal polarization, and interface dipole effects on the alignment of the thiophene frontier orbital energies with the silicon band edges. For thiophene adsorbate frontier orbital energies, we observe significant corrections to standard DFT (~1 eV), including large nonlocal electrostatic polarization effects (~1.6 eV). Importantly, both results can be rationalized from knowledge of the electronic structure of the isolated thiophene molecule and silicon substrate systems. Silicon band edge energies are predicted to vary by more than 2.5 eV, while molecular orbital energies stay similar, with the different functional groups studied, suggesting the prospect of tuning energy alignment over a wide range for photoelectrochemistry and other applications.

Yu, Min↗
DOE OSTI2013

Prebiotic Chemistry within a Simple Impacting Icy Mixture

In this paper, we present results of prebiotic organic synthesis in shock compressed mixtures of simple ices from quantum molecular dynamics (MD) simulations extended to close to equilibrium time scales. Given the likelihood of an inhospitable prebiotic atmosphere on early Earth, it is possible that impact processes of comets or other icy bodies were a source of prebiotic chemical compounds on the primitive planet. We observe that moderate shock pressures and temperatures within a CO 2 -rich icy mixture (36 GPa and 2800 K) produce a number of nitrogen containing heterocycles, which dissociate to form functionalized aromatic hydrocarbons upon expansion and cooling to ambient conditions. In contrast, higher shock conditions (48–60 GPa, 3700–4800 K) resulted in the synthesis of long carbon-chain molecules, CH 4 , and formaldehyde. All shock compression simulations at these conditions have produced significant quantities of simple C–N bonded compounds such as HCN, HNC, and HNCO upon expansion and cooling to ambient conditions. In conclusion, our results elucidate a mechanism for impact synthesis of prebiotic molecules at realistic impact conditions that is independent of external constraints such as the presence of a catalyst, illuminating UV radiation, or pre-existing conditions on a planet.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗