Seismic Safety

With increasing concerns over nonrenewable resources, geothermal energy is gaining popularity for heat and power production. Germany aims to achieve a significant percentage of its energy from renewables by 2050 [1]. Deep geothermal plants are expected to contribute substantially to heating demand [2]. However, these plants induce micro-seismic events that impact building serviceability and human comfort. Until now, the seismic activity measurement in the Bavaria region relied on the free-field vibration sensor network. In a novel approach, recently, additional sensors have been installed at different levels of a low-rise building within the premises of a geothermal operation plant in the south of Munich (see Fig.1). This strategic sensor network aims to collect and analyze unique vibration data. The project focuses on enhancing the understanding and prediction of building responses to micro-earthquake vibrations through data-driven model updating.

The initial phase involves processing and preparing existing sensor data using classical and modern machine learning approaches, such as neural networks, for automated data processing and feature extraction. The second phase aims to develop surrogate models to quantify uncertainty and replace detailed nonlinear analyses. These models will utilize experimental data to enhance the predictive accuracy of structural behavior under induced seismicity. By improving existing building models with experimental data, this project aims to develop a warning system and vibration prediction model to mitigate the impact of induced seismicity in geothermal systems. It will contribute to the safety and efficiency of geothermal energy operations in Munich and potentially worldwide by monitoring building integrity under induced seismicity.