Advancing Edge AI for Earthquake Early Warning
Excited to share CRISiSLab's latest publication in Nature Scientific Reports, where Danuka Ravishan leads a project exploring how ultra-lightweight deep learning models can enable real-time earthquake detection directly on low-cost, low-power, MEMS-based edge devices such as Raspberry Shake or similar.
Citation: Ravishan, D., Prasanna, R., Herath, P. et al. Lightweight convolutional neural network for real-time earthquake P-wave detection on edge devices in New Zealand. Sci Rep 16, 11536 (2026). https://doi.org/10.1038/s41598-026-42568-y
Earthquake early warning systems traditionally rely on centralised processing and computationally heavy deep learning models. While landmark works such as PhaseNet, Generalized Phase Detection, and EQTransformer have significantly advanced automated seismic analysis, their architectures are often designed for high-performance computing environments rather than always-on embedded sensing networks.
This project takes a different perspective: instead of prioritising model complexity, it focuses on extreme efficiency for operational deployment. A key contribution of this research is the development of an ultra-compact convolutional neural network for real-time P-wave detection specifically optimised for edge computing environments. Compared with widely used deep-learning seismic pickers such as PhaseNet, GPD, and EQTransformer, which prioritise large-scale accuracy and generalisation, the proposed model demonstrates that high detection performance can be achieved with dramatically reduced computational complexity. The architecture contains ~38K parameters, operates on 2-second waveform windows, and achieves sub-7 ms inference on Raspberry Pi-class hardware, enabling detection directly at sensor nodes rather than relying on centralized servers. By training and validating the system using New Zealand strong-motion data, the work demonstrates how lightweight AI models can support scalable, distributed, and cost-effective earthquake early warning networks, particularly in regions where dense seismic instrumentation remains challenging.
Why this matters:
• Enables AI directly on seismic sensors
• Supports distributed EEW architectures
• Reduces reliance on centralised processing infrastructure
• Opens pathways for low-cost community-scale sensing networks
As extreme events continue to challenge traditional infrastructure, edge AI combined with low-cost sensing technologies may play a critical role in the next generation of disaster early warning systems.
Look out for some exciting outcomes from our EdgeAI work, building on the work published in this paper...!!
There is something appealing about understanding materials and practical workshop tasks, especially when the focus stays on the details people might otherwise overlook. Knowing what a component needs to do can make choosing a material easier to discuss. That thought gives me a starting point for exploring practical technical skills in connection with Zhpifa. The smaller details are what I would want to return to, especially when an explanation feels too broad. Which questions should come before comparing different technical options?
A discussion of following curiosity through everyday information seems more useful when it connects an idea with something easy to picture. A clear question can turn a casual interest into something easier to explore. With Yh75u in mind, Yh75u learning ideas feels like a topic worth exploring one question at a time. It leaves me curious about the steps between understanding an idea and putting it into practice. How do you decide which detail deserves a closer look before moving on?
The idea of reading news and commentary more carefully gives me a reason to slow down and consider the details. A striking headline is easier to evaluate when its main claim is separated from the supporting detail. For Tvplovdiv, I would use news and media literacy as a starting point for a closer discussion of the subject. The smaller details are what I would want to return to, especially when an explanation feels too broad. What would you check before passing a story on to someone else?
I keep coming back to the everyday side of following curiosity through everyday information, where a simple detail can lead to a wider question. A clear question can turn a casual interest into something easier to explore. For Zngoxx, I would use Zngoxx learning ideas as a starting point for a closer discussion of the subject. I can imagine different responses depending on the situation, which makes the question more interesting. How do you decide which detail deserves a closer look before moving on?
The theme of choosing useful digital tools makes me curious about what people notice in their own everyday experiences. A tool becomes useful when it makes a specific task easier rather than simply adding another option. That is why the connection between Vvp2p and everyday technology skills makes me want to think through an example. That is the part I would keep thinking about after moving on to something else. How would you compare two tools using the same everyday task?