Neuromorphic Astronomy: An End-to-End SNN Pipeline for RFI Detection Hardware

TL;DR

This paper presents a neuromorphic hardware pipeline using deep Spiking Neural Networks for real-time Radio Frequency Interference detection in radio astronomy, emphasizing hardware-aware model partitioning and energy efficiency.

Contribution

It introduces a novel greedy partitioning algorithm for deploying large SNNs on neuromorphic hardware and highlights the importance of hardware co-design for optimal performance.

Findings

Achieved 100mW inference with on-chip power measurements.

State-of-the-art accuracy among SNN baselines for RFI detection.

Smaller un-partitioned models outperform larger, split models.

Abstract

Imminent radio telescope observatories provide massive data rates making deep learning based processing appealing while simultaneously demanding real-time performance at low-energy; prohibiting the use of many artificial neural network based approaches. We begin tackling the scientifically existential challenge of Radio Frequency Interference (RFI) detection by deploying deep Spiking Neural Networks (SNNs) on resource-constrained neuromorphic hardware. Our approach partitions large, pre-trained networks onto SynSense Xylo hardware using maximal splitting, a novel greedy algorithm. We validate this pipeline with on-chip power measurements, achieving instrument-scaled inference at 100mW. While our full-scale SNN achieves state-of-the-art accuracy among SNN baselines, our experiments reveal a more important insight that a smaller un-partitioned model significantly outperforms larger, split models. This finding highlights that hardware co-design is paramount for optimal performance. Our work thus provides a practical deployment blueprint, a key insight into the challenges of model scaling, and reinforces radio astronomy as a demanding yet ideal domain for advancing applied neuromorphic computing.