Earthquakes are extremely devastating and because we don’t have a way to predict them in advance they end up taking a huge toll on lives. The existing systems for earthquake prediction are fraught with false positives to the point of being useless. However, that hasn’t stopped people from trying to predict them, and in a new paper researchers Quentin Bletery and Jean-Mathieu Nocquet claim to have found a unique way to predict them up to 2 hours in advance using GPS data.
They analyzed high-rate GPS time series before 90 different earthquakes that were magnitude 7 and above to find a precursor signal and they observed a subtle signal that rose from the noise about 2 hours before these major earthquakes occurred. This looks extremely promising and if validated can change how we approach disaster management of earthquakes. However, the study still needs to be validated and we don’t yet know if the precursor signal could ever be measured for individual events with the accuracy needed to provide a useful warning.
The existence of an observable precursory phase of slip on the fault before large earthquakes has been debated for decades. Although observations preceding several large earthquakes have been proposed as possible indicators of precursory slip, these observations do not directly precede earthquakes, are not seen before most events, and are also commonly observed without being followed by earthquakes. We conducted a global search for short-term precursory slip in GPS data. We summed the displacements measured by 3026 high-rate GPS time series—projected onto the directions expected from precursory slip at the hypocenter—during 48 hours before 90 (moment magnitude ≥7) earthquakes. Our approach reveals a ≈2-hour-long exponential acceleration of slip before the ruptures, suggesting that large earthquakes start with a precursory phase of slip, which improvements in measurement precision and density could more effectively detect and possibly monitor.
This is an area where Machine Learning might prove to be useful to extrapolate and predict but that being said we still need to validate and verify before implementing it or depending on it. The paper with their findings was published in Science (DOI: 10.1126/science.adg2565)
Source: Hacker News: Early Warning: GPS Data Could Detect Large Earthquakes Hours Before They Happen
– Suramya
[…] some good usecases and there are some advantages to adding Machine Learning to the system. I have written about a few of them […]
Pingback by ChatGPT is not an all powerful AI it can’t even perform simple multiplications « Suramya's Blog — August 19, 2023 @ 9:49 PM