Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Nonlinear problems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 865 records · Page 48
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Grassmannian Diffusion Maps--Based Dimension Reduction and Classification for High-Dimensional Data

This work introduces the Grassmannian diffusion maps (GDMaps), a novel nonlinear dimensionality reduction technique that defines the affinity between points through their representation as low-dimensional subspaces corresponding to points on the Grassmann manifold. Here, the method is designed for applications, such as image recognition and data-based classification of constrained high-dimensional data where each data point itself is a high-dimensional object (i.e., a large matrix) that can be compactly represented in a lower-dimensional subspace. The GDMaps is composed of two stages. The first is a pointwise linear dimensionality reduction wherein each high-dimensional object is mapped onto the Grassmann manifold representing the low-dimensional subspace on which it resides. The second stage is a multipoint nonlinear kernel-based dimension reduction using diffusion maps to identify the subspace structure of the points on the Grassmann manifold. To this end, an appropriate Grassmannian kernel is used to construct the transition matrix of a random walk on a graph connecting points on the Grassmann manifold. Spectral analysis of the transition matrix yields low-dimensional Grassmannian diffusion coordinates embedding the data into a low-dimensional reproducing kernel Hilbert space. Further, a novel data classification/recognition technique is developed based on the construction of an overcomplete dictionary of reduced dimension whose atoms are given by the Grassmannian diffusion coordinates. Three examples are considered. First, a "toy" example shows that the GDMaps can identify an appropriate parametrization of structured points on the unit sphere. The second example demonstrates the ability of the GDMaps to revealing the intrinsic subspace structure of high-dimensional random field data. In the last ex- ample, a face recognition problem is solved considering face images subject to varying illumination conditions, changes in face expressions, and occurrence of occlusions. The technique presented high recognition rates (i.e., 95% in the best case) using a fraction of the data required by conventional methods.

42 ENGINEERING↗
DOE OSTI2022

An E and B gyrokinetic simulation model for kinetic Alfvén waves in tokamak plasmas

The gyrokinetic particle simulation is a powerful tool for studies of transport, nonlinear phenomenon, and energetic particle physics in tokamak plasmas. While most gyrokinetic simulations make use of the scalar and vector potentials, a new model (GK-E&B) has been developed by using the E and B field in a general form and has been implemented in simulating kinetic Alfvén waves in uniform plasma. In our work, the Chen et al. GK-E&B model has been expressed, in general, tokamak geometry using the local orthogonal coordinates and general tokamak coordinates. Its reduction for uniform plasma is verified, and the numerical results show good agreement with the original work. The theoretical dispersion relation and numerical results in the local model in screw pinch geometry are also in excellent agreement. Numerical results show excellent performance in a realistic parameter regime of burning plasmas with high values of β/(M e k$^{2}_{⊥}$ρ$^{2}_{i}$), which is a challenge for traditional methods due to the “cancellation” problem. As one application, the GK-E&B model is implemented with kinetic electrons in the local single flux surface limit. With the matched International Tokamak Physics Activity-Toroidicity-induced Alfvén Eigenmodes parameters adopted, numerical results show the capability of the GK-E&B in treating the parallel electron Landau damping for realistic tokamak plasma parameters. As another application, the global GK-E&B model has been implemented with the dominant electron contribution in the cold electron limit. Its capability in simulating the finite E || due to the finite electron mass is demonstrated.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Turbulence model reduction by deep learning

A defining problem of turbulence theory is to produce a predictive model for turbulent fluxes. These have profound implications for virtually all aspects of the turbulence dynamics. In magnetic confinement devices, drift-wave turbulence produces anomalous fluxes via cross-correlations between fluctuations. In this work, we introduce an alternative, data-driven method for parametrizing these fluxes. The method uses deep supervised learning to infer a reduced mean-field model from a set of numerical simulations. We apply the method to a simple drift-wave turbulence system and find a significant new effect which couples the particle flux to the local gradient of vorticity. Notably, here, this effect is much stronger than the oft-invoked shear suppression effect. We also recover the result via a simple calculation. The vorticity gradient effect tends to modulate the density profile. In addition, our method recovers a model for spontaneous zonal flow generation by negative viscosity, stabilized by nonlinear and hyperviscous terms. We highlight the important role of symmetry to implementation of the new method.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

On the Diffusivity of Moist Static Energy and Implications for the Polar Amplification Response to Climate Warming

Energy balance models (EBMs) have been widely used in a range of climate problems, but the assumption of constant diffusivity in the parameterization of the moist static energy (MSE) flux can be hardly justified. We demonstrate in this study that the diffusive MSE flux can be derived from the basic energy balance equation with a few tolerable assumptions. The estimated diffusivity is both spatially and seasonally dependent, and its midlatitude average is then tested against several scaling theories for the midlatitude eddy diffusivity. The result supports the diffusivity theory of Held and Larichev (1996) modified for the moist atmosphere, affording a dynamics-based parameterization of MSE diffusivity. The implementation of the parameterization in an EBM leads to an interactive MSE diffusivity that accounts for the midlatitude eddy response to climate forcing perturbations. Under a uniform radiative forcing, the EBM with a diffusivity so parameterized produces a weakening of the midlatitude diffusivity and a modestly polar-amplified surface temperature response as an inevitable outcome under the dual constraints of the nonlinear Clausius-Clapeyron relation and the temperature gradient-dependent diffusivity, even in the absence of any poleward amplifying radiative feedbacks. As the consequence of more isothermal temperature and reduced diffusivity, the variance of the midlatitude surface temperature also decreases with warming.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Lifetime renormalization of driven weakly anharmonic superconducting qubits. II. The readout problem

Recent experiments in superconducting qubit systems have shown an unexpectedly strong dependence of the qubit relaxation rate on the readout drive power. This phenomenon limits the maximum measurement strength and thus the achievable readout speed and fidelity. We address this problem here and provide a plausible mechanism for drive-power dependence of relaxation rates. To this end we introduce a two-parameter perturbative expansion in qubit anharmonicity and the drive amplitude through a unitary transformation technique introduced in Part I. This approach naturally reveals number-nonconserving terms in the Josephson potential as a fundamental mechanism through which applied microwave drives can activate additional relaxation mechanisms. Here, we present our results in terms of an effective master equation with renormalized state- and drive-dependent transition frequency and relaxation rates. Comparison of numerical results from this effective master equation to those obtained from a Lindblad master equation which only includes number-conserving terms (i.e., Kerr interactions) shows that number-nonconserving terms can lead to significant drive-power dependence of the relaxation rates. The systematic expansion technique introduced here is of general applicability to obtaining effective master equations for driven-dissipative quantum systems that contain weakly nonlinear degrees of freedom.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

Measurements of the $^{5}D^{°}_{4}$–$^{5}P_{3}$ transition of singly ionized atomic iodine using intermodulated laser induced fluorescence

Iodine has been an element of recent interest for commercial use as fuel in electrostatic propulsion systems. A lingering problem when investigating ionized iodine using non-perturbative, laser-based techniques is determining the spectral width, i.e., the species temperature, of iodine. To this end, the hyperfine structure must be well understood to develop a spatially resolved diagnostic technique capable of ion flow and temperature measurements. Previous work investigated the lineshape of the transition between the $^{5}D^{°}_{4}$ and $^{5}P_{3}$ states of singly-ionized atomic iodine (I II) with laser induced fluorescence (LIF), but the hyperfine structure of the transition was unresolved in those measurements. In this work, an intermodulated LIF technique is used to measure an enhanced lineshape of the same I II transition. Here, a linear least squares fitting algorithm is used to fit the transition lineshape, where hyperfine transition locations and theorized relative amplitudes are constrained by theory. A lineshape model that incorporates hyperfine transition amplitude enhancement introduced from an intermodulated laser technique is implemented into the fitting function, as well as a nonlinear laser saturation effect. We report converged hyperfine coupling coefficients for these I II states.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Virtual to Physical: Reinforcement Learning to Optimize SNS Particle Accelerator Controls

Complex accelerators must have control systems that can handle dynamic nonlinear environments. This makes traditional control methods unsuitable as they can struggle to adapt to these uncertainties. This provides an ideal environment for reinforcement learning algorithms as they are adaptable and generalizable. We present a reinforcement learning pipeline that can effectively handle the dynamics of a complex accelerator. We test and prove our pipelines capabilities on multiple environments including the Spallation Neutron Source (SNS) and the Beam Test Facility (BTF) at Oakridge National Lab (ORNL). Due to the limited time available to train an online algorithm like reinforcement learning on a real accelerator, we utilize a virtual twin accelerator (VIRAC) developed by ORNL to pretrain the policy and show its ability to converge in the virtual environment. We then test the adaptability of the pretrained RL model by applying it on the real accelerator and comparing the results. Utilizing our Scientific Optimization and Controls Toolkit (SOCT) and open-source standards such as Gymnasium we create and solve for a MEBT orbit correction problem in the SNS and an emittance maximization problem in the BTF. We show how Twin Delayed Deep Deterministic Policy Gradient (TD3) can solve this optimization environment in the virtual accelerator and transfer this policy onto the real accelerator for inference and model retraining. We show how reinforcement learning can be utilized as a control system for complex accelerators and provide a model pipeline for how an implementation performs and can be adapted to new accelerator control problems.

Kasparian, Armen [Thomas Jefferson National Accele↗
DOE OSTI2021

Encoder–decoder neural network for solving the nonlinear Fokker–Planck–Landau collision operator in XGC

An encoder–decoder neural network has been used to examine the possibility for acceleration of a partial integro-differential equation, the Fokker–Planck–Landau collision operator. This is part of the governing equation in the massively parallel particle-in-cell code XGC, which is used to study turbulence in fusion energy devices. The neural network emphasizes physics-inspired learning, where it is taught to respect physical conservation constraints of the collision operator by including them in the training loss, along with the ℓ 2 loss. In particular, network architectures used for the computer vision task of semantic segmentation have been used for training. A penalization method is used to enforce the ‘soft’ constraints of the system and integrate error in the conservation properties into the loss function. During training, quantities representing the particle density, momentum and energy for all species of the system are calculated at each configuration vertex, mirroring the procedure in XGC. This simple training has produced a median relative loss, across configuration space, of the order of 10 –4 , which is low enough if the error is of random nature, but not if it is of drift nature in time steps. The run time for the current Picard iterative solver of the operator is O(n 2 ), where n is the number of plasma species. As the XGC1 code begins to attack problems including a larger number of species, the collision operator will become expensive computationally, making the neural network solver even more important, especially since its training only scales as O(n). Here, a wide enough range of collisionality has been considered in the training data to ensure the full domain of collision physics is captured. An advanced technique to decrease the losses further will be subject of a subsequent report. Eventual work will include expansion of the network to include multiple plasma species.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

PPINN: Parareal physics-informed neural network for time-dependent PDEs

Physics-informed neural networks (PINNs) encode physical conservation laws and prior physical knowledge into the neural networks, ensuring the correct physics is represented accurately while alleviating the need for supervised learning to a great degree. While effective for relatively short-term time integration, when long time integration of the time-dependent PDEs is sought, the time–space domain may become arbitrarily large and hence training of the neural network may become prohibitively expensive. To this end, we develop a parareal physics-informed neural network (PPINN), hence decomposing a long-time problem into many independent short-time problems supervised by an inexpensive/fast coarse-grained (CG) solver. In particular, the serial CG solver is designed to provide approximate predictions of the solution at discrete times, while initiate many fine PINNs simultaneously to correct the solution iteratively. There is a two-fold benefit from training PINNs with small-data sets rather than working on a large-data set directly, i.e., training of individual PINNs with small-data is much faster, while training the fine PINNs can be readily parallelized. Consequently, compared to the original PINN approach, the proposed PPINN approach may achieve a significant speed-up for long-time integration of PDEs, assuming that the CG solver is fast and can provide reasonable predictions of the solution, hence aiding the PPINN solution to converge in just a few iterations. To investigate the PPINN performance on solving time-dependent PDEs, we first apply the PPINN to solve the Burgers equation, and subsequently we apply the PPINN to solve a two-dimensional nonlinear diffusion–reaction equation. Furthermore, our results demonstrate that PPINNs converge in a few iterations with significant speed-ups proportional to the number of time-subdomains employed.

42 ENGINEERING↗
DOE OSTI2025

Preserving nonlinear constraints in variational flow filtering data assimilation

Data assimilation aims to estimate the states of a dynamical system by optimally combining sparse and noisy observations of the physical system with uncertain forecasts produced by a computational model. The states of many dynamical systems of interest obey nonlinear physical constraints, and the corresponding dynamics is confined to a certain sub-manifold of the state space. Standard data assimilation techniques applied to such systems yield posterior states lying outside the manifold, violating the physical constraints. This work focuses on particle flow filters which use stochastic differential equations to evolve state samples from a prior distribution to samples from an observation-informed posterior distribution. The variational Fokker-Planck (VFP)—a generic particle flow filtering framework—is extended to incorporate non-linear, equality state constraints in the analysis. To this end, two algorithmic approaches that modify the VFP stochastic differential equation are discussed: (i) VFPSTAB, to inexactly preserve constraints with the addition of a stabilizing drift term, and (ii) VFPDAE, to exactly preserve constraints by treating the VFP dynamics as a stochastic differential-algebraic equation (SDAE). Additionally, an implicit-explicit time integrator is developed to evolve the VFPDAE dynamics. The strength of the proposed approach for constraint preservation in data assimilation is demonstrated on three test problems: the double pendulum, Korteweg-de-Vries, and the incompressible Navier-Stokes equations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Side-channel Leakage Assessment Metrics: A Case Study of GIFT Block Ciphers

Determination of an adequate level of security and providing subsequent mechanisms to achieve it, is one of the most pressing problems regarding embedded computing devices. While there are some solutions available for resource-rich computer systems, direct application of these solutions to resource-constrained environments are often unfeasible. The fundamental problem for such resource-constrained systems is the fact that current cryptographic algorithms utilize significant energy consumption and storage overhead. Both the cryptographic algorithm and its physical implementation affect the resilience of a cryptosystem against side-channel attacks. A side-channel attack represents a process that exploits leakages in order to extract sensitive information such as the key. This paper focuses on Correlation Power Analysis (CPA) which is side-channel attack based on the power consumption leakage. In 2016 the U.S. Commerce Department’s National Institute of Standards and Technology (NIST) initiated the call for proposals of new cryptographic algorithms to strengthen the cryptographic defense of networked devices against cyberattacks and to protect the data created by those innumerable device. This work evaluates S-boxes used by NIST candidates PICCOLO, GIFT, and PRESENT, as well as several S-box variants that demonstrated sufficient weaknesses against classical cryptanalysis, for a quantitative comparison in terms of resiliency to CPA attack. Three well-known theoretical metrics are evaluated: transparency order (TO and RTO), nonlinearity, and signal-to-noise (SNR) ratio, aiming to characterize the resistance of these S-boxes against adversaries exploiting physical leakages. Experimental results from attacks on an 8- bit XMEGA were obtained via the ChipWhisperer platform and of all the S-boxes evaluated, GIFT64 with a PICCOLO S-box was found to be the most susceptible to CPA. Results showed that variations in TO and RTO were not sufficient to ensure practical CPA resistance and that among S-boxes with equal non-linearity there were no significant differences in the TO and SNR variants.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Side-channel Leakage Assessment Metrics: A Case Study of GIFT Block Ciphers

Determination of an adequate level of security and providing subsequent mechanisms to achieve it, is one of the most pressing problems regarding embedded computing devices. While there are some solutions available for resource-rich computer systems, direct application of these solutions to resource-constrained environments are often unfeasible. The fundamental problem for such resource-constrained systems is the fact that current cryptographic algorithms utilize significant energy consumption and storage overhead. Both the cryptographic algorithm and its physical implementation affect the resilience of a cryptosystem against side-channel attacks. A side-channel attack represents a process that exploits leakages in order to extract sensitive information such as the key. This paper focuses on Correlation Power Analysis (CPA) which is side-channel attack based on the power consumption leakage. In 2016 the U.S. Commerce Department’s National Institute of Standards and Technology (NIST) initiated the call for proposals of new cryptographic algorithms to strengthen the cryptographic defense of networked devices against cyberattacks and to protect the data created by those innumerable device. This work evaluates S-boxes used by NIST candidates PICCOLO, GIFT, and PRESENT, as well as several S-box variants that demonstrated sufficient weaknesses against classical cryptanalysis, for a quantitative comparison in terms of resiliency to CPA attack. Three well-known theoretical metrics are evaluated: transparency order (TO and RTO), nonlinearity, and signal-to-noise (SNR) ratio, aiming to characterize the resistance of these S-boxes against adversaries exploiting physical leakages. Experimental results from attacks on an 8- bit XMEGA were obtained via the ChipWhisperer platform and of all the S-boxes evaluated, GIFT64 with a PICCOLO S-box was found to be the most susceptible to CPA. Results showed that variations in TO and RTO were not sufficient to ensure practical CPA resistance and that among S-boxes with equal non-linearity there were no significant differences in the TO and SNR variants.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Quantum Computing Strategy 2026

Quantum computing (QC) is a rapidly maturing technology with the potential for revolutionary impacts on stockpile stewardship science and national security. Recent developments in fault-tolerant architectures have compressed vendor roadmaps, and predictions of a production-ready quantum computer by the mid-2030s are becoming increasingly credible. This strategy provides a roadmap for integrating QC into the Advanced Simulation and Computing (ASC) program by investing in four strategic focus areas: 1. Develop Capabilities in Mission-Relevant Quantum Applications: ASC will prioritize developing quantum-ready applications in mission areas that have shown significant promise for quantum advantage, including simulations of materials in extreme environments, nuclear dynamics, solving linear and nonlinear partial differential equations, and uncertainty quantification. These applications directly support stockpile stewardship science and modernization objectives. 2. Conduct R&D in Algorithms, Software, and Hardware: Sustained research into quantum algorithms, robust software tools, and quantum hardware is essential. ASC will develop efficient quantum algorithms; invest in quantum compilers, debuggers, and performance tools; and explore specialized quantum hardware tailored to NNSA’s unique requirements. 3. Engage with Vendors and Partners: Early and active collaboration with commercial quantum hardware vendors and academic partners is critical. Through testbeds, co-design agreements, and quantum demonstration facilities, ASC will influence hardware design, gain early access to emerging technologies, and ensure that quantum platforms evolve to meet mission needs. 4. Build Knowledge, Experience, and Workforce: Expanding and upskilling the quantum-trained workforce is essential to long-term success. This includes hiring, internal training, university outreach, and postdoctoral support to ensure ASC maintains the expertise required to operate, program, and integrate quantum systems as they become available. While quantum computing will never replace classical computing, it has the potential to solve certain problems with speed and accuracy that would be unachievable using any conceivable classical high-performance computing (HPC) system. By investing strategically in QC, ASC will help propel the emergent QC industry, maintain U.S. technological leadership, ensure mission readiness, and position itself to rapidly adopt quantum technologies as they mature.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Quantifying Energy Conversion in Higher-Order Phase Space Density Moments in Plasmas

Weakly collisional and collisionless plasmas are typically far from local thermodynamic equilibrium (LTE), and understanding energy conversion in such systems is a forefront research problem. The standard approach is to investigate changes in internal (thermal) energy and density, but this omits energy conversion that changes any higher-order moments of the phase space density. In this Letter, we calculate from first principles the energy conversion associated with all higher moments of the phase space density for systems not in LTE. Particle-in-cell simulations of collisionless magnetic reconnection reveal that energy conversion associated with higher-order moments can be locally significant. Furthermore, the results may be useful in numerous plasma settings, such as reconnection, turbulence, shocks, and wave-particle interactions in heliospheric, planetary, and astrophysical plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Latent diffusion can map beam loss to two-dimensional phase-space projections

Beam loss monitors (BLMs) and beam current monitors (BCMs) are ubiquitous at particle accelerators around the world. These simple devices provide noninvasive high-level beam measurements but give no insight into the detailed 6D (𝑥,𝑦,𝑧,𝑝 𝑥 ,𝑝 𝑦 ,𝑝 𝑧 ) beam phase-space distributions or dynamics. We show that generative conditional latent diffusion models can learn intricate patterns to solve the extreme inverse problem of mapping waveforms of tens of BLMs or BCMs along an accelerator to detailed 2D projections of a charged particle beam’s 6D phase-space density. This transformational method can be used at any particle accelerator to transform simple noninvasive devices into detailed beam phase-space diagnostics. We demonstrate this concept via multiparticle simulations of the high-intensity beam in the kilometer-long Los Alamos Neutron Science Center linear proton accelerator.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

An adaptive scalable fully implicit algorithm based on stabilized finite element for reduced visco-resistive MHD

The magnetohydrodynamics (MHD) equations are continuum models used in the study of a wide range of plasma physics systems, including the evolution of complex plasma dynamics in tokamak disruptions. However, efficient numerical solution methods for MHD are extremely challenging due to disparate time and length scales, strong hyperbolic phenomena, and nonlinearity. Additionally, therefore the development of scalable, implicit MHD algorithms and high-resolution adaptive mesh refinement strategies is of considerable importance. In this work, we develop a high-order stabilized finite-element algorithm for the reduced visco-resistive MHD equations based on the MFEM finite element library (mfem.org). The scheme is fully implicit, solved with the Jacobian-free Newton-Krylov (JFNK) method with a physics-based preconditioning strategy. Our preconditioning strategy is a generalization of the physics-based preconditioning methods in Chacón et al. (2002) to adaptive, stabilized finite elements. Algebraic multigrid methods are used to invert sub-block operators to achieve scalability. A parallel adaptive mesh refinement scheme with dynamic load-balancing is implemented to efficiently resolve the multi-scale spatial features of the system. Our implementation uses the MFEM framework, which provides arbitrary-order polynomials and flexible adaptive conforming and non-conforming meshes capabilities. Results demonstrate the accuracy, efficiency, and scalability of the implicit scheme in the presence of large scale disparity. The potential of the AMR approach is demonstrated on an island coalescence problem in the high Lundquist-number regime (≥ 10 7 ) with the successful resolution of plasmoid instabilities and thin current sheets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Binary Optimal Control of Single-Flux-Quantum Pulse Sequences

We introduce a binary, relaxed gradient, trust-region method for optimizing pulse sequences for single flux quanta (SFQ) control of a quantum computer. The pulse sequences are optimized with the goal of realizing unitary gate transformations. Each pulse has a fixed amplitude and duration. Here we model this process as an binary optimal control problem, constrained by Schrödinger’s equation, where the binary variables indicate whether each pulse is on or off. We introduce a first-order trust-region method, which takes advantage of a relaxed gradient to determine an optimal pulse sequence that minimizes the gate infidelity, while also suppressing leakage to higher energy levels. The proposed algorithm has a computational complexity of O(p log(p)), where p is the number of pulses in the sequence. We present numerical results for the H and X gates, where the optimized pulse sequences give gate fidelity’s better than 99.9%, in ≈ 25 trust-region iterations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations

Here we propose a generalized space-time domain decomposition approach for the physics-informed neural networks (PINNs) to solve nonlinear partial differential equations (PDEs) on arbitrary complex-geometry domains. The proposed framework, named eXtended PINNs ( X P I N N s ), further pushes the boundaries of both PINNs as well as conservative PINNs (cPINNs), which is a recently proposed domain decomposition approach in the PINN framework tailored to conservation laws. Compared to PINN, the XPINN method has large representation and parallelization capacity due to the inherent property of deployment of multiple neural networks in the smaller subdomains. Unlike cPINN, XPINN can be extended to any type of PDEs. Moreover, the domain can be decomposed in any arbitrary way (in space and time), which is not possible in cPINN. Thus, XPINN offers both space and time parallelization, thereby reducing the training cost more effectively. In each subdomain, a separate neural network is employed with optimally selected hyperparameters, e.g., depth/width of the network, number and location of residual points, activation function, optimization method, etc. A deep network can be employed in a subdomain with complex solution, whereas a shallow neural network can be used in a subdomain with relatively simple and smooth solutions. We demonstrate the versatility of XPINN by solving both forward and inverse PDE problems, ranging from one-dimensional to three-dimensional problems, from time-dependent to time-independent problems, and from continuous to discontinuous problems, which clearly shows that the XPINN method is promising in many practical problems. The proposed XPINN method is the generalization of PINN and cPINN methods, both in terms of applicability as well as domain decomposition approach, which efficiently lends itself to parallelized computation. The XPINN code is available on h t t p s : / / g i t h u b . c o m / A m e y a J a g t a p / X P I N N s .

97 MATHEMATICS AND COMPUTING↗