Zainab, Tayyaba, Karstens, Jens and Landsiedel, Olaf (2023) LightEQ: On-Device Earthquake Detection with Embedded Machine Learning. [Paper] In: IoTDI '23. , 05.2023, San Antonio, TX, USA . Proceedings of the 8. ACM/IEEE Confernece on Internet of Things Design and Implementation. ; pp. 130-143 . DOI 10.1145/3576842.3582387.

Text LightEQ__On_device_seismic_event_detection_with_embedded_machine_learning.pdf Restricted to Registered users only Download (1MB)

Abstract

The detection of earthquakes in seismological time series is central to observational seismology. Generally, seismic sensors passively record data and transmit it to the cloud or edge for integration, storage, and processing. However, transmitting raw data through the network is not an option for sensors deployed in harsh environments like underwater, underground, or in rural areas with limited connectivity. This paper introduces an efficient data processing pipeline and a set of lightweight deep-learning models for seismic event detection deployable on tiny devices such as microcontrollers. We conduct an extensive hyperparameter search and devise three lightweight models. We evaluate our models using the Stanford Earthquake Dataset and compare them with a basic STA/LTA detection algorithm and the state-of-the-art machine learning models, i.e., CRED, EQtransformer, and LCANet. For example, our smallest model consumes 193 kB of RAM and has an F1 score of 0.99 with just 29k parameters. Compared to CRED, which has an F1 score of 0.98 and 293k parameters, we reduce the number of parameters by a factor of 10. Deployed on Cortex M4 microcontrollers, the smallest version of LightEQ-NN has an inference time of 932 ms for 1 minute of raw data, an energy consumption of 5.86 mJ, and a flash requirement of 593 kB. Our results show that resource-efficient, on-device machine learning for seismological time series data is feasible and enables new approaches to seismic monitoring and early warning applications.

Actions (login required)

View Item