ADEEP LEARNING GEOTHERMOMETER FOR DEEP RESERVOIRS

Knowing the reservoir temperature is the single most valuable fact in early geothermal exploration, yet measuring it means drilling. Classical chemical geothermometers infer it from spring chemistry but assume a fluid-mineral equilibrium that mixing and degassing routinely break; multicomponent methods demand thermodynamic expertise few programs carry. This 2025 Geologic® study introduces aiION®, a deep learning chemical geothermometer that predicts deep reservoir temperature from eight routinely measured inputs: the major ions, silica and pH of a water sample.

The model was trained on 674 rigorously curated water samples from Nevada's Great Basin, one of the world's best documented geothermal provinces, with target temperatures cross-inferred from four independent lines of evidence: classical silica geothermometers, iGeoT multicomponent geothermometry, a 2,365-entry bottom-hole temperature database and an existing machine learning model. Among four benchmarked algorithms, the deep neural network won decisively, explaining over 97% of temperature variance on both training and test data with a mean absolute error near 2.6 °C. Validated on 42 new wells from geothermal fields worldwide, aiION® held an R² of 0.83 — evidence of genuine global applicability rather than local curve fitting.