Thematic Modules: Physics


Noise Simulation for Radio Astronomy


Simulation of the propagation of pulsar signals from the source to antennas and generation of synthetic data – written in C++.

This is a component of ML-PPA (Machine Learning-based Pipeline for Pulsar Analysis), a framework for extracting pulsar signals in data streams from radio astronomical antennas.

Value proposition PulsarDT implemented in C++. This is going to be the production version of the whole ML-PPA package and will also include a C++ version of the ML-classifier (PulsarRFI_NN).

Release Notes

This is the first internal release. Assorted related materials, including Jupyter notebooks with use examples, are available at GitLab or will be added soon. For a wider context and theory behind the whole ML-PPA (including detailed explanations with regard to the status of each component) one should refer to the paper. This component is an efficient parallel-computing capable implementation of the whole ML-PPA, including the ML-classifier and DT, a layered architecture with a Python-based user interface on the top of various modules containerized using Singularity. This version includes a C++ implementation of PulsarDT as its main module.

Future Plans

Ultimately this component will contain the whole ML-PPA package, both the physics-based DT (PulsarDT) and the ML-classifier (PulsarRFI_NN). Including stable versions of both plus a user interface is the main development goal at the moment, and then updating these two tools as the Python prototypes are updated. Another goal is to work on the efficient use of parallel computing.


Target Audience
  • Expert users
  • Developers