AI-Guided Noise Reduction for Urban Geothermal Drilling

Abstract

Urban geothermal energy production plays a critical role in achieving global climate objectives. However, drilling operations in densely populated areas generate significant noise pollution, posing challenges to community acceptance and regulatory compliance. This research presents an artificial intelligence-driven approach to dynamically reduce noise emissions during geothermal drilling. We integrate Deep Reinforcement Learning (DRL) with generative neural network models to provide real-time recommendations for optimal drilling parameters. Specifically, the Drill-LSTM model forecasts future machine states, while the Sound-GAN framework predicts sound propagation based on varying operational conditions. These models feed into a DRL-Agent that learns to balance drilling efficiency with noise minimization. Additionally, an interactive assistance system GUI presents predictions, forecasts, and recommendations to human operators, facilitating informed decision-making. Our system demonstrates significant potential in reducing noise levels, enhancing operational efficiency, and fostering greater acceptance of urban geothermal projects. Future work will focus on refining the models and validating the system in real-world drilling scenarios.