The GEOLAB project

A research proposal submitted to the CERS on March 31st,1995.

Contact: Pierre Dillenbourg

Abstract This project aims to develop an intelligent learning environment (ILE) for reservoir characterization, in particular the issue of volumetric uncertainty assessment. This difficult domain of geostatistics constitutes the core of the courses provided by our partner, FSS Consultants SA, a member of FSS International. This training generally is provided to main oil companies, but the same concepts and techniques do also concern water reservoir and risk assessment for toxic waste.

This project results from the congruence between the type of software developed by TECFA and the skills taught by FSS. In short, the characterization of petroleum reservoir requires a set of a complex skills whose acquisition heavily rely on experience. Therefore, a learning environment simulates a situation in which the trainee has to perform the same cognitive processes as in his future job. The best example of learning environment is a flight simulator. A learning environment is referred to as 'intelligent' when it includes an agent which can guide and advise the subject. This agent is generally implemented with artificial intelligence techniques.

Through this project FSS aims to maintain a training offer which is up-to-date both with respect to the content and the method. The ILE - called GEOLAB - will not substitute to courses, but enrich these courses and extend training beyond short sessions. This time extension is especially relevant because such complex skills cannot be learned in one week. Therefore, a key issue addressed in this project is the integration of the ILE with the existing lectures provided by FSS. We address this issue in two ways. On one hand, GEOLAB will contain and refer to the multimedia material presented during the lectures. For instance, when the user does some mistake, the system may show relevant parts of theory or analogous cases. On the other hand, GEOLAB will be articulated with the geostatistics software "FSS TOOLS" used by FSS for its training courses.

This project result from the convergence between scientific and commercial interests. We first present the motivation for FSS, and then compare it to our own scientific goals.

Over the last seven years, FSS International has established itself as a leader in the field of technical training and continuing education for the environmental and mining industry. For the oil industry alone, it has taught to over one thousand production geologists, petrophysicists, seismic interpreters and reservoir engineers how to apply geostatistical methods for analysing their data and developing numerical reservoir models. All the major oil companies (Shell, Mobil, Exxon, Esso, Amoco, Elf, Texaco, ...) have asked FSS International to provide in-house training, or have sent the professionals to FSS International public short courses. FSS offices are located in Calgary, Reno, Paris, Geneva, Vancouver and Sidney. For the project, the partner is FSS Consultants SA, the Swiss member of FSS International, directed by Dr. Roland Froidevaux.

Through the years, FSS International has endeavoured to constantly improve and adapt the courses in order to be responsive to the practical challenges of reservoir characterisation and to ensure that the training continues to present current improvement in methodology. This concern for innovation justifies FSS investment in this project. Another source of motivation for FSS is the possibility to extend training beyond short sessions. Currently, the longest training sessions delivered by FSS last five days, including lectures and workshops. Despite the fact that these sessions are very intensive, trainees would benefit from longer working sessions. GEOLAB will enable participants to pursue their training after the end of the training session. This continued education will not only increase the efficiency of the training provided by FSS, but also enable FSS to maintain a longer relationship with their customers.

TECFA is an multidisciplinary research unit in educational technology. Our motivation for this project is two-folded. One on hand, we want to transfer to real scale problems the techniques and prototypes developed in previous research projects. We acquired expertise in the field of 'intelligent learning environments', i.e. advanced educational software using artificial intelligence techniques. During this research, we paid attention to the generality of algorithms in order to support portability across domains. It is hence now our primary interest to test our previous work in a different field. The second interesting aspect for TECFA is the issue of integrating the ILE to be developed with existing lectures and workshops. Too often, designers have built systems without considering how they would be integrated in the existing courses. This lack of concern for integrating new software within existing activities has been detrimental to the development of educational technology.

Moreover, this project would lead TECFA members to play an innovative role in the Swiss community of training software ("Schweiz CBT"). TECFA belongs to this association and has published several papers in the association journal. Most training software we observed is 'superficially' interactive: designers include nice sounds and images, but do not pay enough attention to the cognitive activities of users. Nobody learns complex skills simply by answering questions. We hope that GEOLAB will convince developers to build richer interactive systems, or at least inform the companies who buy such systems that richer forms of interactivity can be developed.

This project belong to an multidisciplinary research field referred to as 'artificial intelligence and education'. P. Dillenbourg has conducted research in this field for 10 years at the universities of Mons (Belgium), Lancaster (UK) and Geneva. We use artificial intelligence (AI) techniques in educational software, not for the sake of using these techniques, but because they enable to conduct rich interactions with the learner. These rich interactions are necessary for the acquisition of complex problem solving skills (Dillenbourg & Martin-Michiellot, 1995). We developed MEMOLAB (Dillenbourg et al, 1994 a & b) within NPR23 program 'artificial intelligence and robotics'. This system teaches the design of psychological experiments on human memory. The system includes an artificial lab in which the learner designs and runs a psychological experiment. The simulation computes the results of the created experiments by extrapolating from the data obtained in similar published experiments (using case-based reasoning techniques). The learner builds the experiment in interaction with a computerized expert. These two agents work step by step together. The expert may disagree with the learner, undo his or her last action, ask for clarification, repair a mistake, and so forth. The learner may remove from the screen the objects created by the expert, ask him an explanation, ask him to continue, and so forth. In other words, the interaction is more flexible and is more symmetrical than in traditional expert systems. MEMOLAB and GEOLAB, the proposed system, reflect the current trends of research: a collaborative approach to learning, a decentralized architecture for systems and the integration of AI techniques with hypertext and multimedia components. (For more detailed information and references, please refer to the detailed research plan)

Research Plan

  1. Which skills are involved in reservoir characterization ? The pedagogical objective in GEOLAB is to train the learner to assess - or quantify- the uncertainty attached to any estimate of hydrocarbon reserve within a reservoir. The key issue for persons involved in reservoir management is not so much to know how much oil is in the reservoir than to describe the range of possible values, i.e. to characterize the uncertainty Srivastava, 1990; Froidevaux, 1992). Uncertainty assessment is a complex undertaking which requires skills in disciplines as different as geology, petrophysics, seismic interpretation and economics (Colin et al, 1995). On top that, because the objective is an assessment of uncertainty, the practitioners involved in this task must also be familiar with probabilistic and geostatistical concepts.

    To illustrate this problem, let consider a typical dome shape reservoir (Figure 1). The total volume of this reservoir (which is the single most critical parameter for the reserve estimation) is given by the intersection of its top surface (in general corresponding to some stratigraphic or structural horizon) with an horizontal plane corresponding to the oil-water contact. These two surfaces (oil-water contact and top of structure) are known precisely at well location only. Elsewhere, they will have to be estimated, partly by extrapolating from the well locations, and partly by interpreting available seismic information. This estimation process involves a whole series of assumptions (on the spatial correlation, wave velocities, rock densities, etc...) and each of them is based on expert judgement, i.e. subjective.

    As a consequence both surfaces are uncertain as to there exact location. Figure 1 illustrates two scenarios for each measure: two variations of the oil-water contact (OWC+ and OWC-) and two variations of the top of structure (TOS+ and TOS-). The impact of this uncertainty is severe on the resulting total volume: the volume corresponding to the optimistic case (light grey area) is in the order of three time bigger than the volume corresponding to the pessimistic case (dark grey area).In the decision-making process (should the oil field be developed or not), the manager will have to consider not only the most likely scenario, but also (and possibly especially) the pessimistic one. If the economics of this low case scenario are unfavourable enough, he may decide not to invest in the development of the reservoir, although the estimated reserves (most likely scenario) were promising. Uncertainty characterization, therefore is a crucial element in reservoir management and an improper assessment of it may lead to huge financial losses, either by being too pessimistic (rejection of a good prospect) and foregoing revenues, or by being to optimistic and sinking capital cost in a project that will never be economic.

    It is clear therefore that the characterization uncertainty is not a trivial task which can be learned on the fly. And since it is not a topic normally found in academic curricula for earth sciences, oil companies rely more and more on in-house professional training to make sure that their key personnel has the required level of familiarity with probabilistic and geostatistical concepts necessary for taking decision in face of uncertainty. Training professionals at characterizing uncertainty fits the approach and systems developed at TECFA for the acquisition of complex problem solving skill. The adjective 'complex' refers to the four following aspects of the task described above:

  2. Why is an ILE relevant for reservoir characterization ? There exists a large variety of educational software (or courseware): frame-based software, drill-and-practice, simulation, tutoring, coaching, micro-world, learning environment, ... and intelligent learning environment. These different names indicate that the system supports different types of learning activities. For instance, a frame-based software is a scenario of questions and answers, while a drill-&-practice includes large series of exercises. A learning environment generally provides a simulated world (in the spirit of a flight simulator) in which the learner has to solve the problems by trials and errors. One adds the qualifier 'intelligent' when the learning environment includes a computerized agent able to solve the same problems as the learner (Clancey, 1987) and hence to interact with the learner during problem solving (for a review, see Wenger, 1987).

    Each category of software has its defenders and its disclaimers. It is pointless to argue that a category is better than another. The real question is to assess whether the learning activities of some program correspond to the objectives fixed by the designer. We argue here that intelligent learning environments are best suited to teach such complex problem solving skills such as those selected for this project (Dillenbourg et al., 1994b).

  3. Integrating GEOLAB with current FSS courses The complex skills described above result from the integration of various pieces of knowledge: concepts, principles, examples and counter-examples, procedures, rules of thumb, ... We previously argued that these various pieces have to be integrated into a complex skill by experience and interaction. Nevertheless, the basic concepts and techniques have to be mastered before. For instance, a future pilot learns the basic procedures and the reading of instruments before to get into a flight simulator. These knowledge grounds have to be acquired before using GEOLAB, during FSS training sessions, through lectures and workshops. These courses introduce learners to the key concepts and techniques in geostatistics and illustrate them with case studies. The critical issue is the degree of integration between these lectures and GEOLAB. We plan to achieve this integration in two ways:
  4. The generic scenario

    The scenario involves three agents, the learner, an experienced colleague who is expert in the domain and a manager who provides them with problems and ask for results. The expert and the manager will be implemented as knowledge-based systems, with CLIPS. The learner has two tools available, a 'calculator' which is an interface to FSS TOOLS and a 'progress pad' , in which the learner fill structured progress reports, store the data computed with FSS tools and add any additional comment. The tools will be implemented with Visual C++. The scenario is structured around four progress meetings. The structure of these meetings will be reflected in the 'progress pad' that the learner will fill in during problem solving. In each of these meeting, the manager and the learner interact about the state of the problem. The scenario starts by a first meeting where the problem is set.

    1. Presentation of the data, the reservoir features (location, ...).
    2. Identification of critical issues. Results of exploratory data analysis. Strategical decision.
    3. Selection of the probabilistic modes
    4. Local uncertainty characterization
    5. Review of results (uncertainty of reserves)
    This scenario is generic, which means that the same scenario applies to different case studies, stored in a database of problems. If one separates the scenario from the problems, new interesting cases can be added, especially cases which are specific to the company to which the course is delivered. Tailoring the problem to the specific cases of the company has been a factor of success for the in-house training provided by FSS.

    The scenario is extensible to other agents. We envisage the possibility to have human experts from FSS to interact with learners after the session via electronic mail or more recent synchronous tools such as the MOOs. This component is however not part of this current project.

  5. Research agenda