<![CDATA[This paper explores the digital transformation of geothermal power plant operations through the Geothermal Operations Optimization, Reliability, and Efficiency using Machine Learning (GOOREMALE) framework. Geothermal operations have traditionally relied on manual data collection, periodic reporting, and expert-based analysis, which often delay decision-making process and extend its cycle times. These inefficiencies create risks of reduced output, higher operational costs, and slower responses to disturbances, underscoring the need for a structured, data-driven solution. The objective of this research is to evaluate whether the integration of digitalization and machine learning can reduce operational decision-making cycle time and enhance monitoring capabilities. The methodology adopts a multi-phase approach beginning with the digitization of operational log sheets into a centralized database management system (DBMS), followed by the development of Business Intelligence dashboards for real-time visualization, and advancing toward the application of machine learning models. Specifically, Locality Sensitive Hashing (LSH), OPTICS clustering, and Root Mean Square Error (RMSE) evaluation were applied to detect anomalies, forecast deviations, and provide decision support. The results show that GOOREMALE reduced decision-making cycle time by approximately 50%, improved the accuracy of anomaly detection, and delivered real-time dashboards that enhanced situational awareness across operational teams. These outcomes confirm that digital transformation can significantly strengthen the timeliness and accuracy of geothermal operational decision-making. The main contribution of this research is the establishment of a practical and replicable framework for digital transformation in geothermal plant operations, while its boundary is limited to decision-making efficiency without yet covering long-term reliability, subsurface management, or predictive maintenance.]]>
