Decision Automation for Oil and Gas Well Startup Scheduling Using MILP Jeffrey D. Kelly a , Brenno C. Menezes b* , Ignacio E. Grossmann b a Industrial Algorithms, 15 St., Andrew Road, Toronto MIP 4C3, Canada b Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh 15213, United States brennocm@andrew.cmu.edu Abstract A novel approach to scheduling the startup of oil and gas wells in multiple fields over a decade-plus discrete-time horizon is presented. The major innovation of our formulation is to treat each well or well type as a batch-process with time-varying yields or production rates that follow the declining, decaying or diminishing curve profile. Side or resource constraints such as process plant capacities, utilities and rigs to place the wells are included in the model. Current approaches to this long-term planning problem in a monthly time-step use manual decision-making with simulators where many scenarios, samples or cases are required to facilitate the development of possible feasible solutions. Our solution to this problem uses mixed-integer linear programming (MILP) which automates the decision-making of deciding on which well to startup next to find optimized solutions. Plots of an illustrative example highlight the operation of the well startup system and the decaying production of wells. Keywords: Well startup optimization, oil and gas production, long-term planning. 1. Introduction Long-term production planning of raw materials from oil and gas reserves determines the scheduling of well startups considering a set of resources to be shared among multiple fields. To meet raw material production profile from these wells, efficient modelling and solution capabilities can properly represent the problem and automate the search of a well exploration chart, typically for a decade-plus time horizon considering a monthly or quarterly time-step. However, current approaches to solve such problems count on simulation of scenarios instead of optimization due to the combinatorics of the long-term planning horizon plays with many different well production that must be started-up, sequenced and shutdown subject to considering constraint limiting equipment, workforce and other resources. We cover in this paper order, placement, timing, capacities and allocations of new wells and well types, along with well production profiles, although the literature in the optimization of oil and gas production also includes surface facilities details. These are manifolds, surface centres, and their interconnections, plus injection profiles of drillings considering pressure, porosity, among other properties and conditions (Flores-Salazar et al., 2011; Gupta and Grossmann, 2012; Tavallali and Karimi, 2016). Although their integrated approach, investigation of medium- to short-term planning or with a year as time-step cannot support strategic decisions to be defined for a decade time-horizon as the proposition of this paper. This aims to guide both the supply of processing plants (in symbiosis with the well production fields) as well as long-term selling contracts of