Efficient Optimization of Well-Drilling Sequence with Learned Heuristics

Abstract

Summary When preparing a field–development plan, the forecast value of the development can be sensitive to the order in which the wells are drilled. Determining the optimal drilling sequence generally requires many simulation runs. In this paper, we formulate the sequential decision problem of a drilling schedule as one of finding a path in a decision tree that is most likely to generate the highest net present value (NPV). A nonparametric online–learning methodology is developed to efficiently compute the sequence of drilling wells that is optimal or near optimal. The main ideas behind the approach are that heuristics from relaxed problems can be used to estimate the maximum value of complete drilling sequences constrained to previous wells, and that multiple online–learning techniques can be used to improve the accuracy of the estimated values. The performance of various heuristic methods is studied in a model for which uncertainty in properties is neglected. The initial heuristic used in this work generates a higher estimated NPV than the actual maximum NPV. Although such a heuristic is guaranteed to find the true optimal drilling order when used in the A* informed-search algorithm method, the cost of the search can be prohibitive unless the initial heuristic is highly accurate. For the variants of heuristic search methods with weighting parameters, the results show that it might not be possible to identify parameters that can be used to find a solution quickly without sacrificing the accuracy of the estimated NPV in this drilling–sequence problem. In contrast, the online learned heuristics derived from observations from previous drilling steps are shown to outperform the other variants of heuristic methods in terms of running time, accuracy of the estimated value, and solution quality. Multilearned heuristic search (MLHS) with space reduction (MLHS–SR) is an efficient and fast method to find a solution with high value. Continuing the search with space restoration is guaranteed to improve the solution quality or find the same solution as the MLHS without any space reduction.

Formulating the history matching problem with consistent error statistics

“…The model is the same as was used in Evensen et al [12], and we will not describe the model at length here but rather focus on the impact of introducing correlated measurement errors for a reservoir case. The model was previously used also by Leeuwenburgh et al [18],Hanea et al [14], and Wang and Oliver [26], and we refer to these papers for a detailed presentation.…”

An optimization model for monthly time-step drilling schedule under planned field production

“…Previous work reduces the risk of geological uncertainty and increases the return on the drilling program [ 17 , 18 ]. However, their optimal solution is to maximize the value of the remaining reservoir in the shortest possible time, rather than focusing on the proper sequence of drilling to ensure the target production [ 19 , 20 ] developed a model based on a genetic algorithm and a reservoir simulator for optimal drilling scheduling [ 21 ]. investigated modeling sequence-dependent switchovers for uniform discrete-time scheduling problems.…”

Artificial Intelligence-Centric Low-Enthalpy Geothermal Field Development Planning

“…However, similar challenges, as in hydrocarbon field development, are observed in geothermal field development planning. Some major issues are biases in production forecasts [22,23] and the VOI of sequential data acquisition [24,25] in particular if data gathering costs of the various actions are different [26]. Despite these efforts, the required time from geothermal field appraisal to heat extraction is 3-7 years [5] and the economics of such projects are challenging [27]; in particular, if value erosion occurs owing to the acquisition of too much data, wrong data, or high costs.…”