159: Optimizing the benefits of machine learning for scientific problems

Souvik Mukherjee discusses his article in July's The Leading Edge about high-resolution imaging of subsurface infrastructure using AI. The use of drones for geophysical data acquisition and artificial intelligence (AI) for geophysical data processing, imaging, and interpretation are active focus areas in current industry and academic applications. Unlocking their cumulative potential in single-focus applications can have a transformative impact, possibly leading to dramatic cost reductions in key use cases and new application areas for enhanced actionable business intelligence. In this conversation, Souvik presents field study results from Texas and California that show the potential for imaging pipelines and other subsurface infrastructure using AI-based methods on high-resolution aboveground magnetic data. He also highlights the similarities and differences between conventional least-squares inversion and machine learning-based inversion and how he achieved a 100-fold increase in efficiency. Whether exploring AI, machine learning, algorithms, or the latest geophysical technology, this conversation has something for everyone. RELATED LINKS * Souvik Mukherjee, Ronald S. Bell, William N. Barkhouse, Santi Adavani, Peter G. Lelièvre, and Colin G. Farquharson, (2022), "High-resolution imaging of subsurface infrastructure using deep learning artificial intelligence on drone magnetometry," The Leading Edge 41: 462–471. (https://doi.org/10.1190/tle41070462.1) * Yaoguo Li and Chester J. Weiss, (2022), "Introduction to this special section: Potential fields," The Leading Edge 41: 452–452. (https://doi.org/10.1190/tle41070452.1) * Read the July 2022 special section: Potential fields (https://library.seg.org/toc/leedff/41/7) Subscribers can read the full articles at https://library.seg.org/, and abstracts are always free. CREDITS SEG produces Seismic Soundoff to benefit its members, the scientific community, and inform the public on the value of geophysics. Please leave a 5-star rating on Apple Podcasts and Spotify to show your support for the show. It takes less than five seconds to leave a 5-star rating and is the number one action you can take to show your appreciation for this free resource. And follow the podcast while you are on the app to be notified when each new episode releases. Original music created by Zach Bridges. Andrew Geary hosted, edited, and produced this episode for 51 features, LLC. Thank you to the SEG podcast team: Jennifer Cobb, Kathy Gamble, and Ally McGinnis.