Subsurface data analysis, reservoir modeling, and machine learning (ML) techniques have been applied to the Brady Hot Springs (BHS) geothermal field in Nevada, USA to further characterize the subsurface and assist with optimizing reservoir management. Hundreds of reservoir simulations have been conducted in TETRAD-G and CMG STARS to explore different injection and production fluid flow rates and allocations and to develop a training data set for ML. This process included simulating the historical injection and production since 1979 and prediction of future performance through 2040. ML networks were created and trained using TensorFlow based on multilayer perceptron, long short-term memory, and convolutional neural network architectures. These networks took as input selected flow rates, injection temperatures, and historical field operation data and produced estimates of future production temperatures. This approach was first successfully tested on a simplified single-fracture doublet system, followed by the application to the BHS reservoir. Using an initial BHS data set with 37 simulated scenarios, the trained and validated network predicted the production temperature for six production wells with the mean absolute percentage error of less than 8%. In a complementary analysis effort, the principal component analysis applied to 13 BHS geological parameters revealed that vertical fracture permeability shows the strongest correlation with fault density and fault intersection density. A new BHS reservoir model was developed considering the fault intersection density as proxy for permeability. This new reservoir model helps to explore underexploited zones in the reservoir. A data gathering plan to obtain additional subsurface data was developed; it includes temperature surveying for three idle injection wells at which the reservoir simulations indicate high bottom-hole temperatures. The collected data assist with calibrating the reservoir model. Data gathering activities are planned for the first quarter of 2021. This GDR submission includes a preprint of the paper titled "Subsurface Characterization and Machine Learning Predictions at Brady Hot Springs" presented at the 46th Stanford Geothermal Workshop (SGW) on Geothermal Reservoir Engineering from February 16-18, 2021.

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells - increasing or decreasing the fluid flow rates across the wells - and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. Data and supporting literature from a study describing a new approach combining reservoir modeling and machine learning to produce models that enable strategies for the mitigation of decreased heat and power production rates over time for geothermal power plants. The computational approach used enables translation of sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy and discovery of optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an "open-source" reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 hours, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 seconds. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs. Includes a synthetic, yet realistic, model of a geothermal reservoir, referred to as open-source reservoir (OSR). OSR is a 10-well (4 injection wells and 6 production wells) system that resembles Brady Hot Springs (a commercially operational geothermal field in Nevada, USA) at a high level but has a number of sufficiently modified characteristics (which renders any possible similarity between specific characteristics like temperatures and pressures as purely random). We study OSR through CMG simulations with a wide range of flow allocation scenarios. Includes a dataset with 101 simulated scenarios that cover the period of time between 2020 and 2040 and a link to the published paper about this project, where we focus on the Machine Learning work for predicting OSR's energy production based on the simulation data, as well as a link to the GitHub repository where we have published the code we have developed (please refer to the repository's readme file to see instructions on how to run the code). Additional links are included to associated work led by the USGS to identify geologic factors associated with well productivity in geothermal fields. Below are the high-level steps for applying the same modeling + ML process to other geothermal reservoirs: 1. Develop a geologic model of the geothermal field. The location of faults, upflow zones, aquifers, etc. need to be accounted for as accurately as possible 2. The geologic model needs to be converted to a reservoir model that can be used in a reservoir simulator, such as, for instance, CMG STARS, TETRAD, or FALCON 3. Using native state modeling, the initial temperature and pressure distributions are evaluated, and they become the initial conditions for dynamic reservoir simulations 4. Using history

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells - increasing or decreasing the fluid flow rates across the wells - and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. Data and supporting literature from a study describing a new approach combining reservoir modeling and machine learning to produce models that enable strategies for the mitigation of decreased heat and power production rates over time for geothermal power plants. The computational approach used enables translation of sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy and discovery of optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an "open-source" reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 hours, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 seconds. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs. Includes a synthetic, yet realistic, model of a geothermal reservoir, referred to as open-source reservoir (OSR). OSR is a 10-well (4 injection wells and 6 production wells) system that resembles Brady Hot Springs (a commercially operational geothermal field in Nevada, USA) at a high level but has a number of sufficiently modified characteristics (which renders any possible similarity between specific characteristics like temperatures and pressures as purely random). We study OSR through CMG simulations with a wide range of flow allocation scenarios. Includes a dataset with 101 simulated scenarios that cover the period of time between 2020 and 2040 and a link to the published paper about this project, where we focus on the Machine Learning work for predicting OSR's energy production based on the simulation data, as well as a link to the GitHub repository where we have published the code we have developed (please refer to the repository's readme file to see instructions on how to run the code). Additional links are included to associated work led by the USGS to identify geologic factors associated with well productivity in geothermal fields. Below are the high-level steps for applying the same modeling + ML process to other geothermal reservoirs: 1. Develop a geologic model of the geothermal field. The location of faults, upflow zones, aquifers, etc. need to be accounted for as accurately as possible 2. The geologic model needs to be converted to a reservoir model that can be used in a reservoir simulator, such as, for instance, CMG STARS, TETRAD, or FALCON 3. Using native state modeling, the initial temperature and pressure distributions are evaluated, and they become the initial conditions for dynamic reservoir simulations 4. Using history

This dataset includes evaluation data ("test" data) and performance metrics for water temperature predictions from multiple modeling frameworks. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL models with an added physical constraint for energy conservation as a loss term. These models were pre-trained with uncalibrated Process-Based model outputs (PB0) before training on actual temperature observations. Performance was measured as root-mean squared errors relative to temperature observations during the test period. Test data include compiled water temperature data from a variety of sources, including the Water Quality Portal (Read et al. 2017), the North Temperate Lakes Long-TERM Ecological Research Program (https://lter.limnology.wisc.edu/), the Minnesota department of Natural Resources, and the Global Lake Ecological Observatory Network (gleon.org). This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).

This data release contains model input and output files for simulating and predicting thermal spring flows at Hot Springs National Park (HOSP), Hot Springs, Arkansas. A three-dimensional hydrogeologic framework of the Hot Springs anticlinorium beneath Hot Springs National Park was constructed to represent the complex hydrogeology of HOSP and surrounding areas to depths exceeding 9,000 feet below ground surface. The framework, composed of 6 rock formations and 1 vertical fault emplaced beneath the thermal springs, was discretized into 19 layers, 429 rows, and 576 columns and incorporated into a 3-dimensional steady-state groundwater-flow model constructed in MODFLOW-2005. Historical daily mean thermal spring flows were simulated for one stress period of approximately 34 years (1980–2014), chosen to represent the period of record for historical climate data used in the quantification of the boundary conditions. The groundwater-flow model was manually calibrated to historical daily mean thermal spring flows of 88,000 cubic feet per day observed over a 12-year period of record (1990–1995 and 1998–2005) at the thermal springs collection system. Calibration was achieved by calculating starting heads and general head boundary conditions from the Bernoulli equation and then adjusting the horizontal and vertical hydraulic conductivities of the rock formations and vertical fault and the hydraulic conductance of head-dependent flux boundaries. The groundwater-flow model was coupled to a surface-water model developed in the Precipitation-Runoff Modeling System (PRMS) by using PRMS-simulated gravity drainage as a specified flux recharge boundary condition in the groundwater-flow model. Together, the MODFLOW and PRMS models were used to (1) locate the areas of groundwater recharge to the thermal springs by using forward and reverse particle-tracking capabilities of MODPATH, (2) simulate the effects of variable recharge rates on the spring flows at the thermal springs, and (3) assess possible effects of climate and land-use change on the long-term variability of spring flows at the thermal springs.

The submission includes the labeled datasets, as ESRI Grid files (.gri, .grd) used for training and classification results for our machine leaning model: - brady_som_output.gri, brady_som_output.grd, brady_som_output.* - desert_som_output.gri, desert_som_output.grd, desert_som_output.* The data corresponds to two sites: Brady Hot Springs and Desert Peak, both located near Fallon, NV. Input layers include: - Geothermal: Labeled data (0: Non-geothermal; 1: Geothermal) - Minerals: Hydrothermal mineral alterations, as a result of spectral analysis using Chalcedony, Kaolinite, Gypsum, Hematite and Epsomite - Temperature: Land surface temperature (% of times a pixel was classified as "Hot" by K-Means) - Faults: Fault density with a 300mradius - Subsidence: PSInSAR results showing subsidence displacement of more than 5mm - Uplift: PSInSAR results showing subsidence displacement of more than 5mm Also, the results of the classification using Brady and Desert Peak to build 2 Convolutional Neural Networks. These were applied to the training site as well as the other site, the results are in GeoTiff format. - brady_classification: Results of classification of the Brady-trained model - desert_classification: Results of classification of the Desert Peak-trained model - b2d_classification: Results of classification of Desert Peak using the Brady-trained model - d2b_classification: Results of classification of Brady using the Desert Peak-trained model

The submission includes the labeled datasets, as ESRI Grid files (.gri, .grd) used for training and classification results for our machine leaning model: - brady_som_output.gri, brady_som_output.grd, brady_som_output.* - desert_som_output.gri, desert_som_output.grd, desert_som_output.* The data corresponds to two sites: Brady Hot Springs and Desert Peak, both located near Fallon, NV. Input layers include: - Geothermal: Labeled data (0: Non-geothermal; 1: Geothermal) - Minerals: Hydrothermal mineral alterations, as a result of spectral analysis using Chalcedony, Kaolinite, Gypsum, Hematite and Epsomite - Temperature: Land surface temperature (% of times a pixel was classified as "Hot" by K-Means) - Faults: Fault density with a 300mradius - Subsidence: PSInSAR results showing subsidence displacement of more than 5mm - Uplift: PSInSAR results showing subsidence displacement of more than 5mm Also, the results of the classification using Brady and Desert Peak to build 2 Convolutional Neural Networks. These were applied to the training site as well as the other site, the results are in GeoTiff format. - brady_classification: Results of classification of the Brady-trained model - desert_classification: Results of classification of the Desert Peak-trained model - b2d_classification: Results of classification of Desert Peak using the Brady-trained model - d2b_classification: Results of classification of Brady using the Desert Peak-trained model

Enhanced geothermal systems (EGS) can provide a sustainable and renewable solution to the new energy transition. Its potential relies on the ability to create a reservoir and to accurately evaluate its evolving hydraulic properties to predict fluid flow and estimate ultimate thermal recovery. Here we develop a hybrid machine learning (ML) model to predict permeability evolution of intermediate-scale (~10 m) hydraulic stimulation experiments at the Sanford Underground Research Facility (the EGS Collab project). We present a 3D map in situ permeability evolution for two of stimulation episodes in this project using microearthquakes (MEQs) data and injection histories of wellhead pressure and flow rate. This map includes both average reservoir permeability evolution over time and local fracture permeability distribution within the evolved reservoir. Compared with the ground truth of average permeability calculated from the well data, our predicted average permeability for these two episodes has a MSE value less than 2.9E-4 and R2 higher than 0.93, indicating that average permeability predicted by machine learning is consistent with good agreement with field observation. Additionally, distributed fracture permeability calculated by empirical equation over time shows the process of fracture propagation and identify the potential fluid path for geothermal reservoir.

These files contain the output of a model calculation to simulate the pressure and temperature of fluid at Brady Hot Springs, Nevada, USA. The calculation couples the hydrologic flow (Darcy's Law) with simple thermodynamics. The epoch of validity is 24 March 2015. Coordinates are UTM Easting, Northing, and Elevation in meters. Temperature is specified in degrees Celsius. Pressure is specified in Pascal.

These files contain the output of a model calculation to simulate the pressure and temperature of fluid at Brady Hot Springs, Nevada, USA. The calculation couples the hydrologic flow (Darcy's Law) with simple thermodynamics. The epoch of validity is 24 March 2015. Coordinates are UTM Easting, Northing, and Elevation in meters. Temperature is specified in degrees Celsius. Pressure is specified in Pascal.