![neural-network-model-helps-predict-site-specific-impacts-of-earthquakes](https://utterbuzz.com/wp-content/uploads/2022/04/neural-network-model-helps-predict-site-specific-impacts-of-earthquakes-640x480.png)
In disaster mitigation planning for future large earthquakes, seismic ground motion predictions are a crucial part of early warning systems. The way the ground moves depends on how the soil layers amplify the seismic waves (described in a mathematical site ‘amplification factor’). However, geophysical explorations to understand soil conditions are costly, limiting characterization of site amplification factors to date. Using data on microtremors in Japan, a neural network model can estimate site-specific responses to earthquakes based on subsurface soil conditions.