The Linux Foundation — in partnership with IBM and startup Grillo — today announced an initiative called OpenEEW to accelerate the deployment of open source earthquake early warning (EEW) detection systems around the world. The organizations say OpenEEW will incorporate sensing, detection, and analysis components from Grillo’s EEW platform, along with a Docker software version of the detection component that can be deployed to Kubernetes and Red Hat OpenShift on IBM Cloud.
An estimated 3 billion people live with the threat of earthquakes globally. According to the U.S. Geological Survey, in California, there’s a 94% chance that an earthquake will not be just a foreshock. Yet only a few countries — like Mexico, Japan, Turkey, Romania, China, Italy, portions of the U.S., and Taiwan — have EEWs, in part because they can cost upwards of $1 billion.
OpenEEW, which was created with support from the U.S. Agency for International Development, the Clinton Foundation, and Arrow Electronics, includes internet of things elements like hardware and firmware that can detect and transmit motion. Real-time detection systems can be deployed on platforms from Kubernetes to Raspberry Pi, and software allows users to receive alerts on devices, wearables, and mobile apps.
IBM, which originally supported Grillo through the Clinton Foundation’s Clinton Global Initiative (CGI) Action Network, says it will add OpenEEW technologies to its Call for Code deployment pipeline supported by the Linux Foundation. Call for Code, which was launched in May 2018, aims to combine data, AI, and blockchain technologies to create systems that allow for better responses to natural disasters. IBM previously said it would spend $30 million over five years to rally developers around the program.
Beyond this, IBM says it has developed a new dashboard to visualize sensor readings and has deployed six of Grillo’s earthquake sensors to conduct tests in Puerto Rico. With OpenEEW, the company hopes to encourage the building of EEWs in places like Nepal, New Zealand, Ecuador, and other seismic regions. These communities could then help OpenEEW by advancing sensor hardware design and creating methods to deliver alerts to citizens.
In a step toward fulfilling this vision, Grillo says researchers from Harvard University and the University of Oregon are actively analyzing the more than 1TB of data its sensors have collected since 2017 in Mexico, Chile, Puerto Rico, and Costa Rica. With support from the David Rockefeller Center for Latin American Studies and the David and Lucile Packard Foundation, Harvard researchers are working with Grillo to deploy a network of sensors across Mexico City and assess the seismic behavior and seismicity beneath the ancient lake basin.
A growing body of research touches on AI-driven earthquake detection. Harvard and Google created an AI model capable of predicting the location of aftershocks up to one year after a major earthquake. And in a paper from the Department of Geophysics at Stanford University, scientists described an AI system — dubbed Cnn-Rnn Earthquake Detector, or CRED — that can isolate and identify a range of seismic signals from historical and continuous data.
Just today, Google announced the launch of an earthquake detection system for compatible Android devices.