Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 12, 2026Open Access

Benchmarking Physics-Informed Neural Networks for Gravitational Potential Modeling

View Full Paper
Ask AI
Bookmark
Share

Authors

SSSachin Sudheesh

Discussion

Loading...

Member takes

Implication

Randomized trial compares simulation speed of PINNs and traditional solvers in 3D Poisson modeling, indicating significant performance gains.

Key Points

  • The aim is to evaluate the performance of physics-informed neural networks in solving the 3D radial Poisson equation.
  • Compared PINNs with an adaptive Runge-Kutta solver for solving the radial Poisson equation.
  • All evaluations were conducted on a standard CPU to isolate algorithm performance.
  • Measured speed and accuracy during forward simulation and assessed structural correlation.
  • PINNs achieved a speedup of 496.7x over the adaptive numerical method during forward simulation.
  • The steady latency for PINNs was measured at 0.00133 seconds.
  • A structural correlation of r = 0.9793 was observed at the baseline system, but MAPE reached 936.05% under high-frequency perturbations.

Cite This Study

Sachin Sudheesh (2026) studied this question.

synapsesocial.com/papers/6a2ba3a28101cf8926f0238fhttps://doi.org/10.5281/zenodo.20630903
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Physics-informed neural network based on the finite volume method for solving forward and inverse problems2025 · 9 citations
  2. 2Gradient-annihilated PINNs for solving Riemann problems: Application to relativistic hydrodynamics2024 · 41 citations
  3. 3PDGM-PINN: Partial Derivative Guided Multi-Branch Physics-Informed Neural Network2026
  4. 4allaPINNs: A physics-informed neural network with improvement of information representation and loss optimization for solving partial differential equations2025
  5. 5Physics-informed Neural Networks for Solving Second-order Boundary Value Problems Comparison with FEM, FD Methods2026