Geothermal District Heating (GDH) doublets in the Central part of the Paris Basin, particularly in the Capital City suburban areas, face two major concerns: The replacement of aging and declining, when not damaged, well infrastructures and productive/injective capacities; GDH doublets density, approaching overpopulation in some areas, which limits well replacement opportunities and clouds new development issues bearing in mind the space limitations in urban areas and the thermal breakthrough/reservoir cooling shortcomings. The Paris suburban Cachan site was considered a relevant candidate for a first implementation of an alternative well architecture design. In March 2018, the second sub-horizontal geothermal injection well, GCAH2, was successfully tested at the Paris suburban Cachan site, thus validating this innovative sub-horizontal well (SHW) architecture, initiated on the previously drilled production well, GCAH1, recorded as a world first with 1000 m 8-1/2 in. open hole horizontal drain. The sub-horizontal drain sections of the wells were drilled using the geosteering technique in place of the usual geometric pre-planned trajectory. Geosteering was successfully used for optimal well placement of the geothermal injection/production doublet. The real-time data was correlated to reservoir model to design and implement a reliable well trajectory and to increase reservoir exposure. Alongside LWD (logging while drilling), advanced near real-time cuttings analysis utilizing elemental and mineralogical measurements and custom software was used to improve decision making while drilling. The integration of chemo-stratigraphy, mud logging, wireline, logging while drilling and production test results improved the correlation between wells, supporting the building of a proper geological model and reservoir characterization.

Operators, service providers, and contractors are improving the well construction system using transformative digital technologies across multiple companies and within levels of disparate organizations. Well plans are managed in a new way with the creation,execution and continuous improvement of processes to materially deliver value from the onset. A typical operator’s well planning process involves developing a well program across multiple internal and external entities in the design and plan stages while various requirements and details are considered and confirmed. As the well gets closer to being drilled, the well plan must also consider the capabilities and technologies supported by the service companies and drilling contractor.This people-based process leads to variability in assumptions and objectives in standardized plans which can result in execution risk and variations in safety, quality, delivery, and cost (SQDC) performance. One major variability source occurs because of the disconnected nature in which people move data between one another in well planning documents and then to field operations. The authors propose a new way to manage this process across organization and discipline boundaries to reduce this variability. This paper details how digital technologies were incorporated into an agile pilot program to create a common framework for the exchange and management of the well plan. It follows the plan from its development to implementation in a unified, seamless process. Further the authors will demonstrate how the solution was developed across multiple organizations to deliver material value to all parties. Three companies created a collaborative business model to deliver a new digital system enhancing well construction planning and execution in terms of speed and completeness of data transfer, ease of access,and availability for building new data-based workflows and reporting. This business model continues to drive alignment throughout the companies’ well delivery business functions. This paper illustrates, "What is the value that digital transformation brings to my organization or job function".The simple answer is that if executed effectively, the transformation should produce a material improvement or outcome for the business. Digital technology creates material business value as a project management tool directly coupled with wellsite technologies. This approach, in turn, will enable improvement of the well design and SQDC performance in the delivery of the well plan.

Traditional well planning and drilling risk management requires revisiting past experiences for a given drilling volume and it is expected that new well project evaluation requires multidisciplinary teams and plurality of data usage and access. To date, there is little integration of drilling data and mud logs into decisional data space used for well planning. Integration of drilling data and mud logs into models used for well planning allows for the data to be analyzed and used for evaluation in order to answer questions such as: will we encounter stringers? What is the expected ROP during the project? How can I de- risk the project in planning phase? We have developed a methodology to allow well planning and associated subsurface models to be created in geo-referenced drilling data space. At the heart, the method requires to build the static subsurface model using historical well trajectory, drilling data and mud log data. From this point of view the subsurface mathematical data space becomes pure drilling space where first the drilling data will populate the virtual space coordinates, allowing all otherwise standard 3D interpolation and intersect techniques to be used. Our approach provides flexibility and completeness for the data distribution as all the wells have past recorded drilling data while other sources of data may be very sparse such in the case of petrophysical or seismic data. We have tested this approach on data from one field and the methodology is robust for using historical data to populate the model and plan new wells. Using driller definitions, we have built an expedite method to detect stringers and match the new observations with sub-seismic events and petrophysical evaluations. The potential application of this method beyond what we have tested is the possibility for scale up and perform rapid comparative exercise with other information and data sets. Sources of uncertainty and possible propagation of such through drilling data space is briefly introduced. Having a historical database of drilling data in geo-referenced space gives confidence to well planning, helps the drilling team to get updated drilling information and perform risk management prior to drilling.

We monitor the seismic signal emitted from a rotating drill bit in real time with an array of seismic sensors at the seafloor. Drill-bit seismic signals provide information to locate the drill-bit position itself and to image geological objects ahead and around the drill bit for geosteering purposes during drilling operations. The data can be obtained in real time without the need to stop drilling for logging and without any additional downhole instrumentation in the bottom hole assembly. Drill-bit positioning accuracy is independent of measured depth and with meter level lateral precision. T his is significantly better than conventional downhole gyro-based methods, especially for long horizontal wells. With sources along the drilled well path approaching a target reservoir we obtain a 3D reverse VSP (RVSP) image around the well for prediction ahead of the drill bit. This paper presents a case study from the Grane reservoir in the North Sea, where we utilize a permanent reservoir monitoring (PRM) array for listening to signals emitted from drilling with a PDC bit. We present imaging results from a highly deviated well and compare them to 3D seismic. The field example shows the ability to look ahead several hundreds of meters below the drilled well trajectory.

Automated drilling has been discussed for a long time, with much of the discussion being around future ambitions – what could be or might be possible. Given the complexity of a modern drilling operation, the idea of automating all or part of it is daunting. Despite the apparent obstacles, there has recently been significant progress toward this goal, centred on the core process of drilling new boreholes. This paper presents an automated directional-drilling process executed on a commercial well in the Norwegian sector of the North Sea in 2019, where a next-generation intelligent rotary-steerable system completed a well section in a single run with all drilling commands automatically computed, optimized, and downlinked by a drilling automation platform. The section was complex, comprising two intervals requiring steering in three dimensions, separated by a tangent section. Directional-drilling engineers onshore, who had the authority to override the system if necessary, supervised the operation remotely. No such override was required, and the automated system was able to drill the entire section while automatically sending steering decisions. The 12¼-in. landing interval required precise positional control to enter the reservoir in the correct location and with the correct attitude. At the end of the section, with over 1500 m drilled, the final well position was 0.28 m above the target position and 3.89 m to the left, with minimal tortuosity, making it easy to land the subsequent casing string. The final build section, from 33 to 71.6° of inclination, was drilled between 100 and 150 m/hr, with a planned dogleg severity of 3°/30 m. To drill such a complex trajectory automatically would have been unthinkable only a short time ago and marks a major milestone in the development of automated drilling technology.

Low oil prices are forcing the oil and gas industry to reduce the well construction cost. This calls for new and more efficient technologies and methods. Cost optimization may have negative impact on the risk level as less resources are available. Even with a strong focus on risk and new regulatory requirements, the well control risk level is not decreasing, but rather shows an increase. A new workflow has therefore been introduced in a collaborative cloud-based well planning system that combines the most advanced transient, multiphase engine with an automated procedure based on drillers method. The workflow will improve the quality of the well control planning as it will enable a simple way of automatic recalculation when the project context is changing. The data flow and quality control of data will also be improved and result in more up to date planning results. The automation of the process removes a huge amount of manual work that up to know has been required to keep the well control calculations synchronized with the project plan. New engine features unique to well control modeling like transient temperature and full compositional tracking adds resolution and accuracy to the well control planning results and helps deliver consistency in the results. The new workflow will deliver well control calculations with better resolution and accuracy with much less effort than what is normal today and should therefore help to reduce risk and cost associated with well planning.

Approximately 370 000 tons of high-level radioactive waste exists. Some nations have mature projects for disposing of such waste in mined repositories hundreds of meters below ground. Emplacement in boreholes of greater depth could be a cost-efficient and fast alternative, particularly for nations with relatively small amounts of waste. A borehole repository could be developed via an iterative process, which would ultimately end with the completion of a comprehensive safety case and a fully operational disposal facility which would be sealed and decommissioned in a reliable manner. Each design should be adapted to the properties of the waste in question, site-specific geological conditions, and regulatory requirements. This variability causes designs and cost estimates to differ. Overall, borehole disposal of high-level radioactive waste is an opportunity for the drilling industry to expand its service portfolio in a way that is beneficial to the environment and the safety of current and future generations.

Geosteering presently requires physical or virtual interaction between the geologist and the directional driller to arrive at steering decisions. This interaction often results in the loss of valuable information because all context and data may not be shared between them. A framework that is able to automatically integrate the data and information which the geologist and directional driller independently possess can result in improved decision making, and is the topic of this paper. The geosteering framework described herein combines estimation and optimization methods to solve geosteering problems with minimal human intervention. Bayesian estimation procedures are used to approximate the distance from geological features, and a wellbore propagation model is used to estimate system responses of the drilling assembly. The geological estimates and directional drilling model are then jointly used to formulate geosteering decision-making as a stochastic optimization problem. Finally, this optimization problem can be solved to aid decision making. This is done without the need for humans to interact, which significantly reduces potential information loss. This procedure is illustrated for two synthetic case studies.

Several companies and countries have announced plans to drill in the lunar South Pole in the next five years. The drilling process on the Moon or any other planetary body is similar to other exploration drilling by using rotary drills, for example the oil and gas drilling. However, the key performance indicators (KPIs) for this type of drilling are significantly different. This work aimed to develop the drilling optimization algorithms to optimize drilling on the Moon based on the experiences with the terrestrial drilling in related industries. A test drilling unit was designed and fabricated under a NASA Early Stage Innovation (ESI) grant; A high-frequency data acquisition system was used to record drilling responses at 1000 Hz. Parameters like weight on bit (WOB), torque, RPM, rate of penetration (ROP), mechanical specific energy (MSE), field penetration index (FPI), and the uniaxial compressive strength (UCS) were recorded for 40 boreholes in the analog formations. This work utilizes the large dataset comprising of more than 1 billion data points recorded while drilling into various lunar analogous formations and cryogenic lunar formations to optimize power consumption and bit wear during drilling operations. The dataset was processed to minimize the noise. The effect of drilling dysfunctions like auger choking and bit wear was also removed. Extensive feature engineering was performed to identify how each of the parameter affects power consumption and bit wear. The data was then used to train various regression algorithms based on the machine learning approaches like the random forest, gradient boosting, support vector machines, logistic regression, polynomial regression, and artificial neural network to evaluate the applicability of each of these approach in optimizing the power consumption using the control variables like RPM and penetration rate. The best performing algorithm based on ease of application, runtime, and accuracy of the algorithm was selected to provide recommendations for ROP and RPM which would result in minimum power consumption and bit wear for a specific bit design. Since the target location for most lunar expeditions is in permanently shadowed regions, the power available for a drilling operation is extremely limited. The bit wear will significantly affect the mission life too. Algorithms developed here would be vital in ensuring efficient and successful operations on the Moon leading to more robust exploration of the targeted lunar regions.

This paper presents a methodology to superimpose the American Petroleum Institute ( API TR 5C3 2018 ) uniaxial and triaxial limits on tubular design limits plots. Complications due to a recent change of axis are resolved, producing practical design limits plots that avoid the horizontal shift of the API vertical limits, currently done by the industry. The commonly used slanted ellipse is compared against an adaptation of the circle of plasticity in the form of a horizontal ellipse, showing the convenience of this last one with examples. After the new collapse formulation was made part of the main body of standard API TR 5C3 (2018) , the horizontal axis on the standard industry well tubular design limits plot changed. The present study evaluates this redefinition of the horizontal axis. One consequence of this modification is a difficulty plotting the API tension and compression limits. The API horizontal limits (uniaxial burst and collapse) are found to be independent of load case, while the API vertical design limits (uniaxial tension and compression) are dependent on inside and outside tubular pressures. The approaches used by commercial software and industry publications to solve this challenge are reviewed. A new design methodology is developed to link API uniaxial limits to the triaxial theory. The main objective of the study is to establish a mathematical relationship between API tubular design limits and the von Mises triaxial theory ( API TR 5C3 2018 ). A methodology that allows plotting the API uniaxial force limits on the design limit plot is developed. The study also shows that the results obtained from the industry standard slanted ellipse are identical to those obtained from the horizontal ellipse and circle. One important difference is that the slanted ellipse is based on zero axial stress datum while the horizontal ellipse/circle uses neutral axial stress datum. The horizontal ellipse/circle is well suited for calculations involving buckling, it is compatible with the information used in field operations and its formulations are less complicated than the tilted ellipse. Therefore, attention is called to it.

For years, many companies involved with drilling have searched for the ideal method to calculate the state of a drilling rig. While companies cannot agree on a standard definition of "rig state," they can agree that as we move forward in drilling optimization and with further use of remote operations and automation, that rig state calculation is mandatory in one form or the other. Internally in the service company, many methods exist for calculating rig state, but one new technology area holds promise to deliver a more efficient and cost-effective option with higher accuracy. This technology involves vision analytics. Currently, detection algorithms rely heavily on data collected by sensors installed on the rig. However, relying exclusively on sensor data is problematic because sensors are prone to failure and are expensive to maintain and install. By proposing a machine learning model that relies exclusively on videos collected on the rig floor to infer rig states, it is possible to move away from the existing methods as the industry moves to a future of high-tech rigs. Videos, in contrast to sensor data, are relatively easy to collect from small inexpensive cameras installed at strategic locations. Consequently, this paper presents machine learning pipeline that is implemented to perform rig state determination from videos captured on the rig floor of an operating rig. The pipeline can be described in two parts. Firstly, the annotation pipeline matches each frame of the video dataset to a rig state. A convolutional neural network (CNN) is used to match the time of the video with corresponding sensor data. Secondly, additional CNNs are trained, capturing both spatial and temporal information, to extract an estimation of rig state from videos. The models are trained on a dataset of 3 million frames on a cloud platform using graphics processing units (GPU). Some of the models used include a pretrained visual geometry group (VGG) network, a convolutional three-dimensional (C3D) model that used three-dimensional (3D) convolutions, and a two-stream model that uses optical flow to capture temporal information. The initial results demonstrate this pipeline to be effective in detecting rig states using computer vision analytics.

After a first part of the drilling campaign, including about 10 wells and branches achieved within two years, the operator started questioning the geological reservoir model and reserves implications for the field Offshore Congo. Considering the potential economic impact of this development, the decision was made to reduce wellbore positioning uncertainty relying on optimization and survey QAQC processes that could be applied without adding cost of extra equipment, operational time or personnel. With more than 10 wells drilled using recent while drilling measurement and directional tools in the same environment, a wide range of wellbore positioning information was available for analysis, post-correction, and geological/reservoir model deeper understanding. Also, investigation was done to recover existing geomagnetic data acquired during the geophysical campaign. Thanks to this extensive data set, enhanced wellbores positioning was implemented using meticulous combination of processes. The "process" overall impact is often underestimated while most of the data is already available. For lateral positioning correction, it included the processing of geomagnetic IFR data over the Moho field associated to Multi Station Correction. For vertical repositioning, BHA sag correction was applied with scrutinous assessment of residual sag uncertainty and detailed analysis of continuous survey data. This robust, cost-effective, and valuable solution was chosen to be applied by the operator in the Moho field. The process was first applied post-drilling to evaluate the level of improvement that could be brought to another well also exposed to challenging trajectory context (ERD 2 with reduced target 25 × 50 m at almost 8000m MD/RT). It confirmed that the achievable uncertainty reduction would meet well objectives without adding any risk or operational time nor jeopardizing wellbore positioning and collision avoidance. Thus, it brought up to 50 to 60% of uncertainty reduction and about 30m lateral and 3m vertical displacement. The reduction of the uncertainty and trajectory adjustment allowed to enhance geologic context understanding. The vertical position of the well was offset following this revision. This had a 5% consequence in term of oil layer thickness for this well. Then, the team designed and rolled out to the operator and contractors an execution strategy and operational workflow including remote monitoring with near real-time survey QAQC that would ensure the best correction process customized for the specific drilling challenges. This monitoring enabled reducing the ellipsoid to ~20 by 50m radius at TD = 7618m. This allowed entering in the reservoir at the exact top of the structure, behind the fault that was the optimum in term of reserves and secured 90% of potential reserves of this well. The operator's choice of valuing the available information to enhance their asset is a very interesting way to optimize the past efforts put in wellbore positioning to face the current economically constrained environment.

Good hole cleaning is essential to maintaining drilling efficiency and preventing non-productive events such as stuck pipe during well construction operations. A cuttings transport model may be used to determine the cleanliness of a hole, but its real-time rig site implementation is often made difficult by lack of necessary inputs to the model. There is a need for a simpler yet reliable approach to quantifying hole cleanliness using data readily available at any rig site. This paper proposes a method that relies on the detection of events over a long time horizon and the use of key parameters relating to such events to quantify hole cleanliness. These events are related through duration and frequency to probabilistic features in a Bayesian network, to infer the probability that the hole cleaning process has been efficient or poor. These events are also weighted by their age to ensure that current beliefs are not strongly influenced by those that are far in the past. The method was deployed on a drilling advisory system and is currently used on rigs in North American land operations. The events and features found to be most relevant to quantifying hole cleanliness were the circulation rates during drilling, tight spots when moving the drillstring, bit hydraulics, and prolonged periods of inactivity. Proactive hole cleaning actions such as working of the pipe, off bottom circulation and pipe rotation were also considered. The Bayesian network model used by the proposed method was able to be run with low computational overhead (micro-seconds on a standard edge device) compared to a traditional cuttings transport model. This functionality is enabled by an event logging procedure that keeps track of hole-cleaning events over time and consolidates several hours (days) of drilling information into relevant hole-cleaning features that can be processed quickly. The proposed method differentiates itself from the published methods on hole cleaning analysis in two main ways. First, it does not attempt to estimate the cuttings bed height or accumulation over time. Instead, it attempts to infer the probability that the hole cleaning operations are effective over time using features in data that suggest efficient or poor hole cleaning. Second, this method provides a clear indication of when hole cleaning actions are needed and why. The approach was validated with statistical methods using surface datasets from six wells involved in North American land operations. Through this validation it was determined that the method was highly effective in correctly characterizing hole conditions throughout the well operation. On the rig, the system was helpful not only in alerting the drillers whenever hole cleanliness deteriorated but also in providing the most likely causes of the deterioration. This provided the rig crew real-time guidance to make actionable decisions to avoid non-productive events.

Over the last few years, multiple wells have been drilled in the Norwegian Continental Shelf (NCS) and the United Kingdom Continental Shelf (UKCS) using wired drill pipe (WDP). This paper captures highlights from using real-time downhole measurements provided by WDP, for improved drilling operations. It presents learnings on how WDP measurements have been used in the operator's decision process. As part of WDP, along-string measurement subs (ASM) are equipped with temperature, annular/internal pressure, rotation and vibrations sensors. Data is transmitted to surface at high speed and is available in real-time, even when flow is off. The data provide great insight into the hole conditions along the drill string and at the bottom hole assembly (BHA). Based on this insight, drilling parameters at surface can be accurately adjusted, resulting in increased overall efficiency. Large data amounts can be communicated to and from surface with negligible time delay and independent from fluid circulation. Displaying the downhole measurements in real-time, both at the rig site and in remote operations centers has proven essential when optimising well construction activities. All parties need to access the same information in real-time. Moreover, the data need to be presented in an intuitive manner that enable improved operational decisions. To maximize WDP values, the Operator has learned that downhole data must be used to adjust drilling operations in real-time.

Automated geosteering relies on logging-while-drilling data from offset wells to make inferences about the geological formation and help guide directional drilling of the subject well. When data from multiple offset wells are available, it is desirable to consistently combine data typelogs from these wells to better estimate the 3D geological formation around the drilling path. We develop a quantitative typelog alignment method based on a Bayesian approach, where the alignment map between pairs of typelogs are modeled as a random function with a prior distribution. A multi-stage penalized procedure is developed that optimizes this alignment map to minimize a misfit function, while taking the prior knowledge into consideration.

The Deepwater Horizon accident is one of the major environmental disasters in the history of the United States. This accident occurred in 2010, when the Deepwater Horizon mobile offshore drilling unit exploded, while the rig's crew was conducting the drilling work of the exploratory well Macondo deep under the waters of the Gulf of Mexico. Environmental damages included more than four million barrels of oil spilled into the Gulf of Mexico, and economic losses total tens of billions of dollars. The accident brought into question the effectiveness of the regulatory regime for preventing accidents, and protecting the marine environment from oil and gas operations, and prompted regulatory reforms. Ten years after the Deepwater Horizon accident, this article analyzes the implementation of Safety and Environmental Management Systems (SEMS) as one of the main regulatory reforms introduced in the United States after the accident. The analysis uses the theory of regulation which takes into account both state and non-state actors involved in regulation, and therefore, the shift from regulation to governance. The study includes regulations issued after the Deepwater Horizon accident, particularly, SEMS rules I and II, and reports conducted by the National Academy of Sciences, the National Commission on the BP Oil Spill, the Center for Offshore Safety, the Chemical Safety and Hazard Investigation Board, and the Bureau of Safety and Environmental Enforcement (BSEE). The article reveals that though offshore oil and gas operators in the U.S. federal waters have adopted SEMS, as a mechanism of self-regulation, there is not clarity on how SEMS have been implemented in practice towards achieving its goal of reducing risks. The BSEE, as the public regulator has the task of providing a complete analysis on the results of the three audits to SEMS conducted by the operators and third parties from 2013 to 2019. This article argues that the assessment of SEMS audits should be complemented with leading and lagging indicators in the industry in order to identify how SEMS have influenced safety behavior beyond regulatory compliance. BSEE has the challenge of providing this assessment and making transparency a cornerstone of SEMS regulations. In this way, the lessons of the DHW accident may be internalized by all actors in the offshore oil and gas industry.

During drilling, surveys to determine the wellbore trajectory are performed at every drilling connection. However, due to the offset between the survey instrument and the bit (typically between 30-100 ft), this survey represents the sensor's position which is lagged compared to the bit. This paper describes a method to automatically calculate projections to the bit in real-time utilizing multiple data sources: WITSML stream, BHA components and rotary trend analysis while rotary drilling. The projection to the bit calculation routine is performed in real time every 30 seconds. This paper presents results of projections for four horizontal unconventional wells drilled in West Texas. Nearly 75,000 projections were generated on the four wells, validated with 839 survey stations, with median divergence of the projections from the nearest survey stations being less than one foot.

This paper describes a system being developed for providing an optimized real-time decision support with automatic forward-looking and what-if simulations. It will address the challenge of achieving automation, better performance, and avoidance of non-productive time (NPT) in drilling operations. It will additionally address the demanding human support currently required in the entire decision support workflow. The approach includes utilization of Model based reasoning in Artificial Intelligence (AI) with a Digital Twin combined with Machine Learning (ML) and advanced 3D visualization which is a key enabler for operation alerts and optimization. Multiple forward-looking and what-if simulations will also be run in real-time to find optimal parameters for flow, rotation and running speed. A Diagnostic module will detect abnormalities and trigger safeguards. Auto-configuration and auto-calibration will be the key elements for Drilling Advisory system and deployment without the need for back-office support. The personnel involved in the operation (drilling contractor, service provider and operator) will be able to quickly provide the necessary operational input and then the system will be auto-calibrated during the operation. Results will be an Advisory Tool providing the operation with an optimal flow, rotation speed and running speed during Drilling, Tripping, Casing/liner/screen running and cement operations in two applications areas: In front of the driller as an Advisory tool for rigs with legacy drilling control systems not capable of receiving automated instructions. Base for providing direct commands and safeguards to rigs with control systems capable of receiving automated commands of optimal flow, rotation speed and running speed.

Geosteering workflows are increasingly based on updated quantifications of subsurface uncertainties during real-time operations. These workflows give tremendous amounts of information that a human brain cannot make sense of. To advance value creation from geosteering, the industry should develop and adopt decision support systems (DSSs). DSSs might provide either expert tools which inform decisions under uncertainty or optimization-based recommendations. In both cases the adoption of a DSS would require new skillsets to dynamically and systematically interpret uncertainties and parameters required for operational decision making. The aim of this work is to identify the relevant skills and ways to aid good geosteering decisions. We present an experiment where 54 geosteering experts took part in performing steering decisions under uncertainty in a controlled environment using an online competition platform. In the experiment we compare the decisions of the experts with an AI bot that had the same information at its disposal. Two of the participants beat the AI bot. A survey was conducted to reveal their winning strategies. The survey shows that both of the winners had extensive prior geosteering experience. That, together with luck, allowed them to beat the AI bot. At the same time neither of the winners utilized the full potential of uncertainty tools in the platform. While geosteering experts possess insights due to prior experience, the information in the real-time data will still be overwhelming, sometimes resulting in inconsistent and unreliable geosteering choices. The AI bot guarantees reliable and consistent decisions by optimization based on systematic uncertainty analysis. Further development of DSSs, and their use as training-simulators for experts, should lead to improved well placements through adopting well-established principles for high-quality decision-making.

For the past few years, the oil and gas industry has invested in digitalization efforts for well construction and drilling operations with the goal of improving drilling efficiency, e.g. optimizing the time and costs of reaching drilling targets. It is widely recognized that this can be achieved by creating a standardized and structured wellbore planning and execution ecosystem. Today this is still missing; each step of the drilling activity planning is performed in separate spreadsheets and documents, and legacy applications that require point-to-point connections, frequent data importing and exporting, and manual typing and retyping. These inefficiencies make it difficult to standardize ways of working, accurately communicate the drilling activity plans to all stakeholders and partners involved in the value chain, and reuse data to improve the planning process. This paper describes the approach taken by one of the largest independent oil and gas operators in Europe toward an open, standardized, and structured digital drilling ecosystem that orchestrates the exchange of plans between systems while enforcing standardized plan structures from well construction, time estimation, and the time planner to the rig action plan and its connection to a rig control system. Central to this ecosystem is a "smart hub" that receives and centrally masters updated plans, checks each plan's conformance to the schema on which it is based, and distributes each committed plan to registered consumers. The smart hub provides a loose coupling between itself and connected plan consumers and publishers, which enables the easy connection of new systems or the replacement of one system with another. The operator described in this paper is deploying this smart hub to act as its single source of truth for activity planning data and to orchestrate the exchange of this data throughout the planning and execution phases. So far, this approach has elevated the collaboration within the organization and with stakeholders. The longer-term goal of the approach is to inspire the development of new software applications and eliminate old bottlenecks related to manual typing and iteration, thereby improving the user experience and defining new standards for better drilling efficiency. By leveraging the connection of automated drilling to the digital drilling ecosystem, the operator believes a reduction in drilling time of 15-25% can be achieved. This will create substantial cost savings and thus allow smaller reservoirs to be more profitable. Other benefits include more accurate time estimates and resource planning, more efficient logistical services, and better data-driven decision-making.