A Physics-Informed Neural Network for Geodesic Computation and Visualization of Geodesic Spheres on Riemannian Manifolds
Abstract
Visualizing geodesic structures associated with general Riemannian metrics is a challenging problem in computational differential geometry. In this work, we present a computational framework for visualizing geodesics and geodesic spheres on a three-dimensional Riemannian manifold equipped with the metric g=diag(1,x2,1), x>0. The associated Christoffel symbols and curvature tensors are computed symbolically, and the resulting geodesic equations are solved using both \texttt{SciPy}'s numerical integration method and a Physics-Informed Neural Network (PINN). The two solutions are compared to assess the accuracy of the neural network approximation. We further develop geodesic spike diagrams and surface visualizations to illustrate the deformation of geodesic spheres relative to their Euclidean counterparts. Intrinsic Riemannian surface area and volume are estimated numerically using the induced metric and the Riemannian volume density, respectively. For the chosen metric and a geodesic ball of radius one, the computed area and volume are approximately 0.362% and 0.364% smaller than the corresponding Euclidean values at the base grid resolution. A grid-refinement study is also performed to examine the sensitivity of these estimates to numerical resolution. The proposed framework demonstrates how symbolic differential geometry, numerical integration, and PINNs can be combined to investigate and visualize geometric structures associated with Riemannian metrics.
Related
- On the Structure of Sub-Riemannian Geodesic Orbit Manifolds
- Geodesic Models for Loop Spaces on Riemannian Manifolds
- A smooth Riemannian metric on an arbitrary product of spheres with Bernoulli geodesic flow
- Riemannian convex bodies with a geodesic segment on the boundary
- Geodesic Divergence on Riemannian Planes with Bounded Geometry
BibTeX
@misc{bhattacharyya2026physicsinformed,
title = {{A Physics-Informed Neural Network for Geodesic Computation and Visualization of Geodesic Spheres on Riemannian Manifolds}},
author = {Sujit Bhattacharyya},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.38260},
eprint = {2610.38260},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.38260},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - A Physics-Informed Neural Network for Geodesic Computation and Visualization of Geodesic Spheres on Riemannian Manifolds
AU - Sujit Bhattacharyya
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2610.38260
UR - https://arxiv.org/abs/2610.38260
AB - Visualizing geodesic structures associated with general Riemannian metrics is a challenging problem in computational differential geometry. In this work, we present a computational framework for visualizing geodesics and geodesic spheres on a three-dimensional Riemannian manifold equipped with the metric g=diag(1,x^2,1), x>0. The associated Christoffel symbols and curvature tensors are computed symbolically, and the resulting geodesic equations are solved using both \texttt{SciPy}'s numerical integration method and a Physics-Informed Neural Network (PINN). The two solutions are compared to assess the accuracy of the neural network approximation. We further develop geodesic spike diagrams and surface visualizations to illustrate the deformation of geodesic spheres relative to their Euclidean counterparts. Intrinsic Riemannian surface area and volume are estimated numerically using the induced metric and the Riemannian volume density, respectively. For the chosen metric and a geodesic ball of radius one, the computed area and volume are approximately 0.362% and 0.364% smaller than the corresponding Euclidean values at the base grid resolution. A grid-refinement study is also performed to examine the sensitivity of these estimates to numerical resolution. The proposed framework demonstrates how symbolic differential geometry, numerical integration, and PINNs can be combined to investigate and visualize geometric structures associated with Riemannian metrics.
ER -