_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper OTC 35433, “Novel Machine-Learning Approach for Predicting the Gel Strength of the Drilling Fluid While Drilling,” by Ahmed Gowida, SPE, and Salaheldin Elkatatny, SPE, King Fahd University of Petroleum and Minerals. The paper has not been peer reviewed. Copyright 2024 Offshore Technology Conference. _ Accurately estimating gel strength is paramount for optimizing drilling operations and preventing cuttings from settling at the wellbore’s bottom. Traditional methods rely on rotational viscometers, which are time-intensive, equipment-dependent, and lack real-time monitoring capabilities. This study underscores the feasibility of leveraging machine learning (ML) as a practical tool for predicting drilling-fluid gel strength, offering real-time monitoring and precise predictions to enhance drilling efficiency, safety, and automation initiatives. Background The gel strength of drilling fluid is assessed using a viscometer, focusing on the 3-rev/min reading obtained after agitating the fluid at 600 rev/min to disrupt any gel formation. Initially, the measurement is taken when the mud reaches a static state for 10 seconds. Subsequent readings are conducted at 10- and 30-minute intervals. The rationale behind the 30-minute reading lies in its ability to indicate whether the mud forms a substantial gel during prolonged static periods, such as when tripping out a bottomhole assembly. Elevated gel strength may result in increased pump pressure required to restore circulation after extended static conditions. Additionally, a consistent upward trend in the 30-minute gel strength suggests the accumulation of ultrafine solids. Consequently, appropriate measures such as chemical treatments or dilution with fresh base fluid are necessary to address this issue. The frequency of measuring various fluid properties is tailored to their respective effects on well-control and drilling operations. These frequent evaluations allow for timely adjustments and monitoring of rheological measurements, offering valuable insights into rock sensitivity and the performance of mud activity and stability after exposure to drilled formations. On the other hand, a complete mud test (including all mud rheological properties) is performed twice a day because it consumes considerable time. It has been observed that mud rheological properties exhibit a significant correlation with two fundamental mud properties: mud weight and Marsh funnel (MF) viscosity. To the best of the authors’ knowledge, a dearth of research exists in the literature aimed at predicting the gel strength of drilling fluid using ML techniques. Consequently, this research endeavor introduces a novel ML model designed specifically for forecasting the gel strength of synthetic oil-based mud systems. Such predictive models are poised to enhance drilling performance by optimizing mud functions. Leveraging MF and mud-density measurements, the developed models aim to forecast the rheological properties of drilling fluid, thereby facilitating improved monitoring of mud functionality during drilling operations at the rig site.