arXiv subjects

Japan K. Patel

Publications and source records attributed to Japan K. Patel.

11 recordsLinked to original sources

arXiv2026

Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation

This work extends our one-dimensional single-sweep neural-operator studies to two dimensions. We consider one-group transport with isotropic scattering. As in the one-dimensional work, we use Fourier neural operators (FNOs) to approximate the high-fidelity scalar flux. Additionally, we also investigate U-shaped neural operators (UNOs) in this study. We consider three surrogates. The first two map the material and source fields directly to the flux, one using an FNO and one using a UNO. The third is an FNO that additionally takes the scalar flux after one source iteration, the single-sweep approximation, as an input. Each case is solved to high fidelity with a verified discrete-ordinates solver, and an average relative L_2 error norm is used to characterize the quality of the inferred maps. We train every surrogate over three random seeds so that differences between them can be assessed against run-to-run variability. Two questions guide the study: whether the single-sweep input improves accuracy over the direct maps, and whether training on the logarithm of the flux improves accuracy in the strongly attenuated regions relevant to shielding.

cs.LG↗

arXiv2026

MAAS-SFRThelper: An Integrated ESAPI Plugin for Structure Generation, Optimization, and Evaluation of Spatially Fractionated Radiation Therapy

Spatially fractionated radiation therapy (SFRT) planning requires three coordinated tasks: generation of high-dose sphere structures, position-aware optimization, and peak-valley dose ratio evaluation. We present MAAS-SFRThelper, a shared-source Eclipse Scripting Application Programming Interface (ESAPI) plugin that integrates structure generation, geometric-aware optimization, and peak-valley dose ratio evaluation for SFRT into a single workflow inside Varian's Eclipse treatment planning system. The plugin exposes five task-oriented tabs sharing common services for sphere extraction and objective creation. The SphereLattice tab generates sphere lattices using five placement patterns. The Optimization tab searches over candidate lattice positions using a four-metric geometric surrogate score and triggers VMAT optimization and dose calculation. The Evaluation tab implements four analysis modes; its three-dimensional peak-valley classification recovers sphere centers from the lattice structure through a geometric extraction pipeline rather than relying on dose thresholds. We validated all functionality on digital phantoms against analytic ground truth. The plugin is distributed as source code under the Varian Limited Use Software License Agreement. Source code and documentation are publicly available on GitHub.

physics.med-ph↗

arXiv2025

Evolutionary Discovery of Sequence Acceleration Methods for Slab Geometry Neutron Transport

We present a genetic programming approach to automatically discover convergence acceleration methods for discrete ordinates solutions of neutron transport problems in slab geometry. Classical acceleration methods such as Aitken's delta-squared and Wynn epsilon assume specific convergence patterns and do not generalize well to the broad set of transport problems encountered in practice. We evolved mathematical formulas specifically tailored to SN convergence characteristics in this work. The discovered accelerator, featuring second differences and cross-product terms, achieved over 75 percent success rate in improving convergence compared to raw sequences - almost double that observed for classical techniques for the problem set considered. This work demonstrates the potential for discovering novel numerical methods in computational physics via genetic programming and attempts to honor Prof. Ganapol's legacy of advancing experimental mathematics applied to neutron transport.

cs.NE↗

arXiv2024

Assessing AI-Enhanced Single-Sweep Approximations for Problems with Forward-Peaked Scattering in Slab Geometry

While the Boltzmann transport equation can accurately model transport problems with highly forward-peaked scattering, obtaining its solution can become arbitrarily slow due to near-unity spectral radius associated with source iteration. Standard acceleration techniques like diffusion synthetic acceleration and nonlinear diffusion acceleration obtain merely one order of magnitude speedups compared to source iteration due to slowly decaying error moments. Additionally, converging approximations to the Boltzmann equation like Fokker-Planck and Boltzmann Fokker Planck run into similar problems with slow convergence. In this paper we assess the feasibility of using Fourier neural operators to obtain AI-enhanced low order, and single-sweep solutions for the transport equation in slab geometry using a predictor-corrector framework.

cs.CE↗

arXiv2024

Diagnostics Using Nuclear Plant Cyber Attack Analysis Toolkit

A Python interface is developed for the GPWR Simulator to automatically simulate cyber-spoofing of different steam generator parameters and plant operation. Specifically, steam generator water level, feedwater flowrate, steam flowrate, valve position, and steam generator controller parameters, including controller gain and time constant, can be directly attacked using command inject, denial of service, and man-in-the-middle type attacks. Plant operation can be initialized to any of the initial conditions provided by the GPWR simulator. Several different diagnostics algorithms have been implemented for anomaly detection, including physics-based diagnostics with Kalman filtering, data-driven diagnostics, noise profiling, and online sensor validation. Industry-standard safety analysis code RELAP5 is also available as a part of the toolkit. Diagnostics algorithms are analyzed based on accuracy and efficiency. Our observations indicate that physics-based diagnostics with Kalman filtering are the most robust. An experimental quantum kernel has been added to the framework for preliminary testing. Our first impressions suggest that while quantum kernels can be accurate, just like any other kernels, their applicability is problem/data dependent, and can be prone to overfitting.

eess.SY↗

arXiv2023

Assessing Nonlinear Diffusion Acceleration for Boltzmann Fokker Planck Equation in Slab Geometry

The convergence of Boltzmann Fokker Planck solution can become arbitrarily slow with iterative procedures like source iteration. This paper derives and investigates a nonlinear diffusion acceleration scheme for the solution of the Boltzmann Fokker Planck equation in slab geometry. This method is a conventional high order low order scheme with a traditional diffusion-plus-drift low-order system. The method, however, differs from the earlier variants as the definition of the low order equation, which is adjusted according to the zeroth and first moments of the Boltzmann Fokker Planck equation. For the problems considered, we observe that the NDA-accelerated solution follows the unaccelerated well and provides roughly an order of magnitude savings in iteration count and runtime compared to source iteration.

math.NA↗

arXiv2021

Transport Synthetic Acceleration for the Solution of the One-Speed Nonclassical Spectral S$_N$ Equations in Slab Geometry

The nonclassical transport equation models particle transport processes in which the particle flux does not decrease as an exponential function of the particle's free-path. Recently, a spectral approach was developed to generate nonclassical spectral S$_N$ equations, which can be numerically solved in a deterministic fashion using classical numerical techniques. This paper introduces a transport synthetic acceleration procedure to speed up the iteration scheme for the solution of the monoenergetic slab-geometry nonclassical spectral S$_N$ equations. We present numerical results that confirm the benefit of the acceleration procedure for this class of problems.

math-ph↗

arXiv2019

Acceleration of the Sn Equations with Highly Anisotropic Scattering using the Fokker-Planck Equation

The discrete ordinates method can model forward-peaked transport problems accurately. However, convergence of discrete ordinates solution can become arbitrarily slow upon use of standard iterative procedures like source iteration and GMRES. Standard zeroth and first moment-based acceleration methods like nonlinear diffusion acceleration and diffusion synthetic acceleration are ineffective in accelerating such problems because these methods do not correct higher order Legendre-moments of angular flux. We explore the idea of using Fokker-Planck as a preconditioner to accelerate forward-peaked transport problems in this paper.

physics.comp-ph↗

arXiv2019

Towards a Multiphysics Model for Tumor Response to Combined-Hyperthermia-Radiotherapy Treatment

We develop a multiphysics-based model to predict the response of localized tumors to combined-hyperthermia-radiotherapy (CHR) treatment. This procedure combines hyperthermia (tumor heating) with standard radiotherapy to improve efficacy of the overall treatment. In addition to directly killing tumor cells, tumor heating amends several parameters within the tumor microenvironment. This leads to radiosensitization, which improves the performance of radiotherapy while reducing the side-effects of excess radiation in the surrounding normal tissue. Existing tools to model this kind of treatment consider each of the physics separately. The model presented in this paper accounts for the synergy between hyperthermia and radiotherapy providing a more realistic and holistic approach to simulate CHR treatment. Our model couples radiation transport and heat-transfer with cell population dynamics.

q-bio.TO↗

arXiv2019

One-Way Coupled Tumor Response Model for Combined-Hyperthermia-Radiotherapy Treatment with Anisotropic Scattering

Therapies such as combined-hyperthermia-radiotherapy (CHR) take advantage of excellent radiosensitization properties of hyperthermia and treat of tumors with both radiation and heat. To appropriately model a CHR treatment, features like tumor heating (heat transfer), dosimetry (radiation transport), and tumor dynamics (cell population dynamics) must be considered together. Our first paper on modeling such treatments introduced a one-way coupled model that could only account for isotropic scattering of radiation. In the present work, we extend our transport model to incorporate anisotropic scattering.

q-bio.TO↗

arXiv2019

Solver Recommendation For Transport Problems in Slabs Using Machine Learning

The use of machine learning algorithms to address classification problems is on the rise in many research areas. The current study is aimed at testing the potential of using such algorithms to auto-select the best solvers for transport problems in uniform slabs. Three solvers are used in this work: Richardson, diffusion synthetic acceleration, and nonlinear diffusion acceleration. Three parameters are manipulated to create different transport problem scenarios. Five machine learning algorithms are applied: linear discriminant analysis, K-nearest neighbors, support vector machine, random forest, and neural networks. We present and analyze the results of these algorithms for the test problems, showing that random forest and K-nearest neighbors are potentially the best suited candidates for this type of classification problem.

cs.LG↗