# Graph Neural Network-Based Anomaly Detection for River Network Systems

arXiv: https://arxiv.org/abs/2304.09367 · HTML: https://mlsanity.com/paper/2304.09367/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 19 Apr 2023.

## Builds on (most cited first, 5 of 5)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2106.06947/) (2021)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [Bayesian spatio-temporal models for stream networks](https://mlsanity.com/paper/2103.03538/) (2021)
- [Bayesian Design with Sampling Windows for Complex Spatial Processes](https://mlsanity.com/paper/2206.05369/) (2022)

## Built on by (most cited first, 2 of 2)

- [A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification](https://mlsanity.com/paper/2410.22377/) (2024)
- [Community-Based Model Sharing and Generalisation: Anomaly Detection in IoT Temperature Sensor Networks](https://mlsanity.com/paper/2601.05984/) (2026)

## Abstract (arXiv)

Water is the lifeblood of river networks, and its quality plays a crucial role in sustaining both aquatic ecosystems and human societies. Real-time monitoring of water quality is increasingly reliant on in-situ sensor technology. Anomaly detection is crucial for identifying erroneous patterns in sensor data, but can be a challenging task due to the complexity and variability of the data, even under normal conditions. This paper presents a solution to the challenging task of anomaly detection for river network sensor data, which is essential for accurate and continuous monitoring. We use a graph neural network model, the recently proposed Graph Deviation Network (GDN), which employs graph attention-based forecasting to capture the complex spatio-temporal relationships between sensors. We propose an alternate anomaly scoring method, GDN+, based on the learned graph. To evaluate the model's efficacy, we introduce new benchmarking simulation experiments with highly-sophisticated dependency structures and subsequence anomalies of various types. We further examine the strengths and weaknesses of this baseline approach, GDN, in comparison to other benchmarking methods on complex real-world river network data. Findings suggest that GDN+ outperforms the baseline approach in high-dimensional data, while also providing improved interpretability. We also introduce software called gnnad.