This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 202643, “Dynamic Process Optimization Using a Reduced-Order Modeling Framework,” by Ravikishan Guddeti, SPE, IPCOS, and Sathish Sankaran, SPE, Xecta Digital Labs, prepared for the 2020 Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, held virtually 9–12 November. The paper has not been peer reviewed. The role of process operations upstream, midstream, and downstream is critical to fundamental business resilience and production optimization in a dynamic environment. In the complete paper, the authors propose a fast, hybrid, self-learning dynamic process-modeling method derived from routine plant measurements that can be used for short-term forecasts, scenario modeling, and process optimization and control. Introduction The methodology, reduced-order modeling (ROM), can use large quantities of data from plant sensors to create a dynamic process model that can be used to optimize process performance. The authors propose a model structure and a hybrid method that is physically intuitive and interpretable and can learn incrementally in real time and thus can augment human intelligence with fast machine-derived insights. Problem Description In the offshore facility system considered in this work, the oilwell flowlines are connected to the platform through risers that terminate at the facility inlet. Each topside flowline includes a subsea production flowline connected to a pressure-controlled choke. This topsides flowline choke is used to control production rate or manage slugging conditions. The facility is designed to provide separation and processing of the oil and condensate production as required to meet export pipeline specifications. A typical oil-separation train consists of many stages of separation and contains liquid surge volume to accommodate surges in liquid rate that may occur from wells or subsea flowlines. Depending on the space available, these separators are two- or three-phase separators. The liquid from each stage is dumped to the subsequent stage of separation, allowing the three phases (oil, gas, and water) to separate. Gas from each stage of separation is compressed, treated to remove water, and then pumped into the export line. Water removed in the separation trains is routed to treating systems before being dumped back into the sea. The dry oil is stored in the dry oil tank and pumped out to the pipelines. Each well has different characteristics that change with the age of the well. As the wells mature with reduced reservoir pressures and increased gas/oil ratio, the hydrocarbon phases travel at lower velocity, resulting in unstable flow regimes. When wells producing at high water cuts are brought online, combined with low gas flow rates and low wellhead pressure, the potential for slug flow can disrupt steady operation of the separation train. The frequency of these events increases with aging reservoirs and high-water-cut production. An effective real-time tool is needed that can monitor current operating conditions continuously and is able to run through alternative mitigation strategies quickly using the predictive model to analyze the effect on downstream processes.