A Machine Learning Approach to Predicting Single Event Upsets

TL;DR

This paper introduces CREMER, a machine learning model that predicts single event upsets in semiconductor memory devices using positional data, enabling proactive detection and enhancing space vehicle safety.

Contribution

The paper presents a novel machine learning approach, CREMER, that predicts SEUs in advance solely based on positional data, improving reliability and scalability.

Findings

CREMER effectively predicts SEUs before they occur.

Using only positional data simplifies the prediction process.

Implementation of CREMER enhances space vehicle memory safety.

Abstract

A single event upset (SEU) is a critical soft error that occurs in semiconductor devices on exposure to ionising particles from space environments. SEUs cause bit flips in the memory component of semiconductors. This creates a multitude of safety hazards as stored information becomes less reliable. Currently, SEUs are only detected several hours after their occurrence. CREMER, the model presented in this paper, predicts SEUs in advance using machine learning. CREMER uses only positional data to predict SEU occurrence, making it robust, inexpensive and scalable. Upon implementation, the improved reliability of memory devices will create a digitally safer environment onboard space vehicles.