Geothermal energy is a large, renewable, and clean source of energy from the earth in the form of heat. Exploring the deeper layers of the Williston Basin has revealed favorable reservoir temperatures, particularly in the western areas where high heat flows are prevalent. The quality of a geothermal hotspot hinges on the reservoir quality index (RQI), which is determined by the accuracy of calculating the field reservoir permeability. The primary goal of this study is to apply machine learning techniques to accurately calculate the field permeability, which is important for optimizing the RQI. To enhance accuracy, we initially applied various clustering algorithms, including the density-based spatial clustering of applications with noise (DBSCAN), K-means, K-median, and hierarchical clustering methods, to delineate hydraulic flow units (HFU) within the reservoir using porosity, permeability and water saturation core data. Subsequently, regression models including supervised ML regression methods such as neural networks, support vector machine (SVM) regression, Gaussian process regression (GPR), ensemble regression, linear regression, and decision trees were employed for each flow unit to establish correlations and calculate field permeability with each of these models validated using cross-validation. In comparison to the other clustering methods, the hierarchical clustering method showed the best performance by showing a strong correlation between the actual and predicted permeability values. Overall, the SVM and GPR regression methods were observed to show consistent results with the training and testing datasets, with the SVM regression technique yielding higher R-squared values through regression across the different clustering techniques. In addition, cross-plots were employed to successfully delineate the Red River formation into distinct regions, aiding in the definition of formation lithology and the estimation of field water saturation. Our study showcases an integrated approach to predicting reservoir permeability, considering limited core data. ML emerges as an effective tool for characterizing the Red River formation as a geothermal hotspot in North Dakota, showcasing the potential for sustainable energy exploration and utilization which reduces the reliance on extensive coring in order to enhance geothermal exploration accuracy.

The exploration of alternative energy sources has gained significant traction in recent years, driven by the urgent need to mitigate greenhouse gas emissions and transition towards sustainable energy. Among these alternatives, ${\mathrm{C}\mathrm{O}}_2$ plume geothermal and hydrothermal systems have emerged as promising options due to their potential for providing clean, renewable energy. This study presents a probabilistic investigation into the sensitivity of ${\mathrm{C}\mathrm{O}}_2$ plume geothermal and hydrothermal systems under various reservoir conditions in the Williston Basin, North Dakota. In addition to elucidating the impact of reservoir conditions on system performance, the study utilizes probabilistic methods to assess energy output of ${\mathrm{C}\mathrm{O}}_2$ plume geothermal and hydrothermal systems. Insights derived from this probabilistic investigation offer valuable guidance for the working fluid selection, systems design and optimization in the Williston Basin and beyond. Results from the sensitivity analysis reveal the profound influence of reservoir conditions on the behavior and efficiency of ${\mathrm{C}\mathrm{O}}_2$ plume geothermal and hydrothermal systems. Our case study on Red River Formation and Deadwood Formations shows a potential of 34% increase and 32% decrease in heat extraction based on varying reservoir conditions. Our investigations in the Beaver Lodge field within the Red River Formation yielded arithmetic mean values for ${\mathrm{C}\mathrm{O}}_2$ best case resources, hydrothermal resources and the ${\mathrm{C}\mathrm{O}}_2$ worst case as 6.36 $\times {10}^{18}$ J, 4.75 $\times {10}^{18}$ J and 3.24 $\times {10}^{18}$ J, respectively. Overall, this research contributes to advancing the knowledge and understanding of ${\mathrm{C}\mathrm{O}}_2$ plume geothermal and hydrothermal systems as viable pathways towards sustainable energy production and carbon sequestration. By highlighting the sensitivity of these systems to reservoir conditions, the study provides valuable insights that can inform decision-making processes and future research endeavours aimed at fostering the transition to a low-carbon energy landscape.

Geological hydrogen storage, seen as a viable solution for addressing energy demands and mitigating the intermittency of wind power, is gaining recognition. At present, there are no specific studies that estimate hydrogen storage capacity and the potential for wind integration in North Dakota despite the state’s enormous energy resources and capabilities. The study’s key innovation lies in repurposing a region historically associated with oil and gas for sustainable energy storage, thereby addressing the intermittency of wind sources. Moreover, the innovative aspect of this study involves field selection, site screening, characterization, and mathematical modeling to simulate a wind–hydrogen production and geological storage system. A 15 MW wind farm, using real-world data from General Electric wind turbines, is employed to assess storage capacities within the Middle Bakken formation. The study reveals substantial storage potentials in wells W24814, W19693, and W26990, with capacities of 54,000, 33,000, and 22,000 tons, respectively. These capacities translate to energy storage capabilities of 1080, 660, and 440 GWh, with minimum storage durations of 140, 80, and 57 days, respectively, under a 60% system efficiency. By pioneering the integration of wind energy with geological hydrogen storage in a region traditionally dominated by fossil fuel extraction, this research could play a crucial role in advancing North Dakota’s energy transition, providing a blueprint for similar initiatives globally.