AI Demos by industry

Geothermal energy AI Demos

Explore geothermal resource screening, reservoir operations, and thermal-energy scenarios. Compare workflows relevant to heating, cooling, and electricity generation. Browse interactive demonstrations relevant to this area, with methods, screenshots, and resource links.

Browse by industry

Choose an industry to explore relevant demonstrations. Research & scientific AI brings together methods used across industries.

9 of 9 entries

Browse entries by name

EnviTrace’s U.S. Geothermal Temperature & Stress Model

EnviTrace has recently developed a comprehensive U.S. Geothermal Temperature & Stress Model. This demo presents the results obtained. It supports regional geothermal screening by bringing continental temperature and stress model information into a common map. Users can compare available model layers, inspect geographic variation, and relate predicted conditions to the underlying inputs. The shared view helps researchers identify areas and model differences that merit closer examination during geothermal resource studies.

Maps geothermal inputs and model predictions across the continental United States.
Compares EnviTrace thermal and stress models with the published Stanford Thermal Model.
Lets users switch input and output layers while inspecting the same geographic area.
Provides regional screening and comparison workflow using existing model layers, rather than a new site-specific simulation.
Research papers summarizing the methods and results are in preparation.

Geothermal Operations (GeoTGo Ops)

Operating a geothermal doublet involves balancing near-term energy recovery with the longer-term condition of the reservoir. GeoTGo Ops connects an operating priority with physics-informed forecasts, candidate strategies, and comparisons of thermal and pressure consequences. The linked views help users examine why one strategy is recommended and how closely competing options meet the same operating goals.

Explores physics-informed operating strategies for a two-well geothermal doublet.
Balances immediate energy output against longer-term thermal effects and pressure-limit risk.
Connects strategy, forecast, decision frontier, and power views to the chosen operating priority.
Distinguishes live-engine results from an illustrative frozen-checkpoint preview; changing a preview priority does not perform a new optimization.

Energy Production/Storage

Subsurface energy decisions depend on how reservoir properties and well arrangements affect flow, heat transfer, and pressure. This synthetic example connects a chosen reservoir domain and physical inputs with field generation and a flow-and-thermal calculation. Comparing the resulting maps and summaries helps users investigate the consequences of an energy production or storage scenario.

Estimates energy production and pressure change for a synthetic reservoir and well arrangement.
Configures a reservoir polygon, resolution, permeability, rock and fluid properties, and operating inputs.
Generates a permeability field and runs the flow and thermal model through separate controls.
Relates output maps and energy or pressure summaries to the selected physical inputs; configuration alone is not a solved scenario.

Geysers Seismicity

The Geysers workflow presents seismic activity within a major operating geothermal field, connecting earthquake locations with their spatial organization over a decade of observations. We have performed various clustering and spatiotemporal ML analyses. We present 3D views of our closest server to make it easier to examine where events concentrate and how different groups occupy the field. The demo provides an interactive starting point for discussing induced seismicity and selecting patterns for further scientific investigation.

Explores earthquake observations from the Geysers geothermal field over 2010–2019.
Groups events into prepared spatial clusters to reveal differences in event density and location.
Supports pan, zoom, hover, and comparison of two clustering views.
Uses prepared observational visualizations; browsing does not fit a new seismic model or establish a causal explanation.
A recent research paper titled “Deep-Embedded-Clustering of Microseismicity Identifies Multiple Failure Mechanisms at The Geysers Geothermal Field” summarizes preliminary ML results.

Geo Modeling

The geological modeling example brings surface terrain and subsurface structures together in a synthetic three-dimensional field. Wells, horizons, faults, and temperature intervals can be examined in the same scene to understand their spatial relationships. This integrated perspective helps geoscience teams explain subsurface geometry and discuss how well information relates to a broader geological interpretation.

Combines wells, geological horizons, faults, terrain, and temperature intervals in an interactive 3D scene.
Relates well trajectories and depth-dependent temperatures to their surrounding geological context.
Provides layer controls, terrain opacity, vertical relief, and well inspection.
Provides access to our open-source and proprietary ML for geospatial analyses.
Uses deterministic synthetic geology for illustration; the scene is not a field-validated subsurface interpretation.

Data Imputation

Incomplete geologic (geospatial) measurements can make regional patterns difficult to interpret and limit the comparisons available to a modeling team. This demo organizes the reconstruction of missing Great Basin data and the evaluation of spatial predictions within a common analysis workflow. Its comparison tools help users examine how selected methods perform when observations are deliberately withheld for checking.

Examines incomplete Great Basin geothermal measurements and their spatial reconstruction.
Organizes dataset preprocessing, held-back splits, comparison methods, and evaluation metrics in one workflow.
Supports regional prediction grids and comparison of reconstructed values with observations withheld from fitting.

Well Log Gap Filling

A geological well log records changes along depth, but gaps can interrupt the patterns needed for interpretation. This synthetic example uses neighboring measurements to estimate missing values while retaining the ordered depth structure of the record. Comparing the reconstructed log with held-back measurements helps users assess the behavior of the gap-filling method before considering a similar workflow for their own data.

Fills intentionally missing measurements along an ordered synthetic geological well log.
Uses our proprietary bounded RobustML neighbor method, with quick and stability-check configurations.
Compares observed and filled values using held-back RMSE and MAE.
Distinguishes the labeled precomputed example from a registered live workspace analysis.

Spatial Geology Gap Filling

Spatial gaps can obscure relationships between geological measurements collected across a field area. This compact synthetic example demonstrates how nearby observations can inform estimates at missing locations through a bounded, distance-weighted neighbor model. Viewing the reconstructed field alongside its evaluation metrics helps users judge both the spatial result and its agreement with held-back evidence.

Reconstructs missing values in a compact synthetic geological field sample.
Uses bounded, distance-weighted RobustML neighbors to estimate values at missing locations.
Shows spatial observations and predictions alongside held-back RMSE and MAE.
Retains a labeled precomputed fallback; live workspace execution is a separate action.

Feature Extraction (spatial)

Large geoscience datasets can contain recurring combinations of attributes that vary across a region. This demo uses NMFk to identify latent spatial factors and groups from selected measurements, with configurable preprocessing and factorization settings. Maps, biplots, and reconstruction views help users connect the extracted mathematical structure with the locations and attributes being studied.

Extracts latent spatial factors and clusters from selected dataset attributes with NMFk.
Configures the factor-count range, restart count, and normalization before factorization.
Provides matrices, latent maps, biplots, and reconstruction evidence to interpret recovered structure.
Supports optional regional interpolation after results exist; a factorization does not by itself establish a geological cause.