| Title | Hidden Geothermal Signatures of the Southwest New Mexico |
|---|---|
| Authors | Velimir V. VESSELINOV, Bulbul AHMMED, Maruti K. MUDUNURU, Satish KARRA, Richard MIDDLETON |
| Year | 2020 |
| Conference | World Geothermal Congress |
| Keywords | new mexico, geothermal, big data, nmfk, hidden geothermal signals |
| Abstract | In Play Fairway Analysis (PFA)s Phase-I Project funding by the U.S. Department of Energy’s Geothermal Technologies Office, we identified four potential regions for exploration of new geothermal resources in the southwest NM (SWNM). These regions include Colorado Plateau, Volcanic Field, Rio Grande Rift, and Basin and Range Province. They are known to have moderate- and high-temperature geothermal resources (e.g., more than 60oC) in operation. Moreover, based on the outcomes of the PFA Phase-I, these regions are also known to have hidden geothermal systems. The objective of this study is to find the signatures of the hidden geothermal systems and future data collection locations to efficiently explore and develop geothermal resources in the SWNM region. To achieve this, we combine datasets from these four distinct regions. A dataset is generated to perform advanced data analysis to find hidden geothermal signatures. An unsupervised machine learning technique called non-negative matrix factorization with customized k-means clustering (NMFk) is applied to this data matrix. NMFk is a robust technique for finding hidden patterns / signatures in data that are not visible in open eyes or other exploratory data analytics. Hidden signals of NMFk analysis reveal hidden geothermal resources and indicate key parameters to characterize the geothermal system in SWNM. Also, spatial clusters by NMFk provide potential geothermal resources and future data collection plans to explore more geothermal resources in SWNM. |