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 approachable about discussing making online tutoring sessions effective through situations people can actually picture. A clear question before a session can help the learner use the available time well. It makes me curious about the practical side of online tutoring support. I would be interested in a simple example, because it is often the ordinary details that make an idea memorable. How would you check that a tutoring explanation has actually become understandable?
What interests me about choosing a college learning environment is how a broad idea becomes part of an ordinary day. The way a course is taught can affect whether a student feels comfortable asking for help. I would keep that thought nearby when looking for ideas about college study choices. I do not have a settled view yet, but this seems like a good place to slow down and look more closely. What would you ask about teaching and support before choosing a college?
Considering sharing the everyday questions of parenthood, I keep coming back to the difference between knowing about an idea and putting it into practice. Small concerns can be easier to discuss when parents hear that others have similar questions. For me, that is a useful way into the broader subject of parenting support discussions. I am more curious about the process than a polished result, because the steps in between are usually where questions appear. What makes a parenting discussion feel helpful rather than competitive?
What draws my attention to building management skills through practical situations is the possibility of making an unfamiliar subject feel closer to everyday life. A realistic scenario can expose how different decisions affect a team's work. I would keep that thought nearby when looking for ideas about management skills training. I am more curious about the process than a polished result, because the steps in between are usually where questions appear. Which situations are most useful for practising management before taking responsibility for a team?
The topic of using familiar characters in preschool learning gives me a few things to think about, especially when the discussion moves beyond general advice. A familiar character can make a new classroom routine feel easier to approach. I would use that point as a starting question when considering preschool storytelling activities. I would be interested in a simple example, because it is often the ordinary details that make an idea memorable. How can a story character support learning while leaving children room to create?