IBM Sequoia's cognitive system will help predict the time and place of a volcanic eruption or earthquake

IBM has announced the creation of a computer model of the movement of Earth's lithospheric plates, calculated using the IBM Sequoia cognitive system. This model can be used to predict volcanic eruptions and earthquakes, with the result that with a high degree of probability it will be possible to know about the place and time of occurrence of a natural phenomenon. The model was developed by a group of scientists, including IBM specialists, representatives from the University of Texas and the California Institute of Technology.

A representative of the IBM research group, Kostas Bekas, said that scientists are well aware of how lithospheric plates move. But knowledge of what happens under the surface is limited. “We know much more about what happens in space than what happens below the surface of the planet. And this is one of the main reasons for the difficulty of building a predictive model of natural disasters, including earthquakes, volcanoes and tsunami. ”


')
The molten mass below the surface of the Earth moves unevenly and is not a single system. In addition, the connectors between the tectonic plates are also uneven. And that makes the calculations and the model itself very, very complex.

The research team used seismograph data from around the world. The obtained information was synchronized with theoretical patterns of plate movement. And already using this complex of data, it was possible to create a more accurate mathematical model of what is happening under the earth's surface with the help of calculations on IBM Sequoia .

If someone had set out to calculate everything on a home PC, even a fairly powerful one, it would take three years. Sequoia completed the entire set of calculations in just one day.

The result does not yet allow predicting the place and time of occurrence of catastrophic phenomena, but the model provides geologists and seismologists with a tool for creating such a forecasting system in the near future. The next step is to improve and refine the existing model.

The wide distribution of sensors connected to the Network will allow scientists to provide more seismic data in the coming years. And with the help of another cognitive system - IBM Watson - it will be possible to analyze the received data and structure it by adding information from scientific articles. Combining all this with the data calculated on IBM Sequoia, scientists will get a system that will significantly increase the level of understanding by scientists of the geological processes leading to the occurrence of natural disasters. And the more data will be, the more accurate the system will be able to get scientists.

IBM is working on this model with the US Department of Energy. With the same ministry, the company is working to create a system for predicting weather phenomena. IBM recently acquired the Weather Company, owner of the Weather Channel. Together with the acquired assets, thousands of weather sensors deployed around the world have moved to IBM.

So soon, let's hope, humanity will receive two reliable forecasting systems at once: weather forecasting and natural disaster forecasting.