Skip to content

FrancoBertoldiMariglio/tfm-saocom-pinn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

tfm-saocom-pinn

Physics-Informed Neural Networks vs. SGP4 for orbit prediction of SAOCOM-1A under variable solar activity.

Master's thesis (Trabajo Fin de Máster) — M.Sc. in Artificial Intelligence, Universidad Internacional de La Rioja (UNIR). Author: Franco Bertoldi Mariglio · Status: in progress


What this is

This thesis empirically compares three approaches for predicting the future orbit of the Argentine synthetic-aperture-radar satellite SAOCOM-1A (NORAD ID 43641, operated by CONAE / built by INVAP), using only public catalog data:

  1. SGP4 — the analytical propagator that is the industry standard (baseline).
  2. MLP — a plain multilayer perceptron with no physics term (experimental control).
  3. PINN — a physics-informed neural network whose loss combines data with the residual of the perturbed equations of motion (J2 + exponential atmospheric drag). This is the focal technique.

Predictions are evaluated at 1-, 3- and 7-day horizons, segmented by level of solar activity (via the F10.7 index), since atmospheric drag — and therefore orbital decay — grows with solar activity.

Research hypotheses

  • H1 (modest): under nominal solar activity (F10.7 < 120 sfu), the PINN does not beat SGP4 on mean along-track error for 1–7 day horizons. SGP4 has been tuned for decades and is hard to beat in its comfort zone.
  • H2 (the bet): under high solar activity (F10.7 > 150 sfu), the PINN reduces mean along-track error by at least 15% vs. SGP4, with statistical significance (paired Wilcoxon, p < 0.05).
  • H3 (control): the physics-free MLP underperforms both SGP4 and the PINN in all conditions, confirming that any PINN advantage comes from the physics term, not raw network capacity.

Every outcome — confirmation, refutation, or partial result — is a valid thesis contribution. Methodological honesty takes priority over expectations: nothing is assumed before it is measured.

Data sources (all public, free, no agreements required)

Source Content
CelesTrak Current GP element sets (TLEs) for SAOCOM-1A
space-track.org Full TLE history (~18 months for this work)
CelesTrak SpaceWeather F10.7 and Ap solar/geomagnetic indices
EGM96 / EGM2008 (NASA GSFC) Earth gravity field coefficients
sgp4 (Python) Vallado's official SGP4 implementation

Current status

  • Reproducible public-data download pipeline (TLEs + space weather)
  • Exploratory data analysis, including interactive 3D Earth + orbit visualizations
  • High-fidelity reference propagation (RK45) for ground truth
  • SGP4 baseline evaluation
  • MLP and PINN models, training, and statistical comparison

Tech stack

Python · NumPy / pandas · PyTorch (planned) · DeepXDE (planned) · sgp4 · SpiceyPy (planned) · Matplotlib / Plotly · Jupyter.

Repository layout

data/        # downloaded data (raw/processed are gitignored; managed with DVC later)
notebooks/   # EDA and experiments
scripts/     # public-data download utilities
docs/        # proposal and project notes

This README is in English for accessibility; project working notes are in Spanish.

About

Master's thesis: Physics-Informed Neural Networks vs. SGP4 for orbit prediction of the SAOCOM-1A satellite under variable solar activity

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages