Self-Supervised Anomaly Detection of Rogue Soil Moisture Sensors

TL;DR

This paper introduces a self-supervised neural network approach utilizing contrastive loss and Dynamic Time Warping for detecting rogue soil moisture sensors in agricultural IoT data, addressing unlabeled data challenges.

Contribution

It presents a novel self-supervised anomaly detection method combining contrastive learning with DTW-based negative sampling for sensor fault detection.

Findings

Effective detection of rogue sensors in real-world datasets

Outperforms traditional supervised methods in unlabeled scenarios

Demonstrates robustness across multiple orchard deployments

Abstract

IoT data is a central element in the successful digital transformation of agriculture. However, IoT data comes with its own set of challenges. E.g., the risk of data contamination due to rogue sensors. A sensor is considered rogue when it provides incorrect measurements over time. To ensure correct analytical results, an essential preprocessing step when working with IoT data is the detection of such rogue sensors. Existing methods assume that well-behaving sensors are known or that a large majority of the sensors is well-behaving. However, real-world data is often completely unlabeled and voluminous, calling for self-supervised methods that can detect rogue sensors without prior information. We present a self-supervised anomalous sensor detector based on a neural network with a contrastive loss, followed by DBSCAN. A core contribution of our paper is the use of Dynamic Time Warping in the negative sampling for the triplet loss. This novelty makes the use of triplet networks feasible for anomalous sensor detection. Our method shows promising results on a challenging dataset of soil moisture sensors deployed in multiple pear orchards.