Satellite Anomaly Detection Using Variance Based Genetic Ensemble of Neural Networks

TL;DR

This paper introduces a variance-based genetic ensemble of neural networks utilizing Monte Carlo dropout for satellite anomaly detection, improving forecasting and anomaly detection accuracy over existing methods.

Contribution

It presents a novel ensemble approach combining genetic algorithms and uncertainty estimation via MC dropout for enhanced satellite data anomaly detection.

Findings

Ensemble model outperforms existing approaches in forecasting accuracy.

Utilizes MC dropout as an efficient approximation for Bayesian neural networks.

Genetic algorithm optimizes RNN structures for better anomaly detection.

Abstract

In this paper, we use a variance-based genetic ensemble (VGE) of Neural Networks (NNs) to detect anomalies in the satellite's historical data. We use an efficient ensemble of the predictions from multiple Recurrent Neural Networks (RNNs) by leveraging each model's uncertainty level (variance). For prediction, each RNN is guided by a Genetic Algorithm (GA) which constructs the optimal structure for each RNN model. However, finding the model uncertainty level is challenging in many cases. Although the Bayesian NNs (BNNs)-based methods are popular for providing the confidence bound of the models, they cannot be employed in complex NN structures as they are computationally intractable. This paper uses the Monte Carlo (MC) dropout as an approximation version of BNNs. Then these uncertainty levels and each predictive model suggested by GA are used to generate a new model, which is then used for forecasting the TS and AD. Simulation results show that the forecasting and AD capability of the ensemble model outperforms existing approaches.