Stanford Geothermal WorkshopFebruary 9-11, 2026

eothermal prospectivity mapping, the identification of areas likely to host commercially viable geothermal resources, is a complex undertaking reliant on integrating diverse datasets ranging from geological and geophysical surveys to geochemical analyses. Subject-matter-driven methods such as traditional Play Fairway Analysis (PFA) are often subjective and time-consuming. This study explores the application and comparative performance of several machine learning (ML) techniques for automated and objective geothermal prospectivity assessment. Specifically, we investigate the efficacy of SmartTensors’ Nonnegative Matrix Factorization (NMFk), Support Vector Machines (SVM), Artificial Neural Networks (ANN), Gradient Boosting Machines (XGBoost), and Diffusion Models (DM) in predicting geothermal potential. The analyses are based on a dataset collected under the USGS/DOE’s GeoDAWN project and various other past research projects in the Great Basin area. We use surface, structural geology, gravity, magnetic, heat flow, and geochemical data attributes. The performance of each model is rigorously evaluated using a series of metrics, as well as through visual inspection of the resulting prospectivity maps. We also analyze feature importance for each model to gain insights into the key geological and geophysical factors influencing geothermal potential. This research contributes to a more robust and efficient methodology for geothermal exploration, potentially reducing exploration costs and accelerating the discovery of new geothermal resources. Our ML methods and tools are designed to be deployed within EnviCloud (https://envitrace.com/#envicloud; https://envitrace.com/saas. Our EnviCloud is a proprietary, comprehensive, cloud-based platform designed to optimize the entire geothermal energy lifecycle, from initial exploration and site assessment to real-time well monitoring and energy output optimization. It is developed to support Software-as-a-Service licenings as well as project consulting work. By leveraging advanced technologies—including cloud/high-performance computing, aritificla intelligence (AI), machine learning (ML), data analytics, and GIS—EnviCloud streamlines geothermal resource utilization and enhances decision making. The platform offers key features such as AI-powered geothermal mapping, thermal gradient analysis, reservoir simulations, near-real-time data analytics, analysis tools for project feasibility. All at a centralized cloud dashboard for mutli-user collaboration. It also includes tools for tracking sustainability metrics and ensuring regulatory compliance, especially related groundwater contamination and induced seismicity. EnviCloud reduces exploration time and maximizes the potential of geothermal resources. It targets a broad audience, including exploration companies, energy providers, investors, regulators, and research institutions, aiming to promote sustainable energy development. Here, we demonstrate EnviCloud's application in processing a wide range of geologic, geothermal, and geophysics datasets related to the Great Basin. Our ML analyses successfully extracted key features relevant to evaluating geothermal prospectivity. We also showcase the platform's ML techniques for the imputation and blind prediction of missing data.

Topic: Modeling