ISI Logo

Top-Down, Intelligent Reservoir Models™ White Paper Software

Experienced reservoir engineers develop an understanding of the specifics of fluid flow behavior in a reservoir, when they work for a reasonably long time on a given asset. These experts become the “go to guy” for that asset. They combine their reservoir and production engineering “know-how” with the specifics they have learned from the operations in the given asset to become an expert in the asset. Now imagine having multiple experts for an asset, and that all their expertise have been combined and preserved (in the form of a reservoir model) in order to be used by anyone in the asset team and the company. Top-Down Modeling is such a tool.


Top-Down Modeling is a formalized and comprehensive, empirical, multi-variant, reservoir simulation model, developed solely based on field measurements (logs, core, well test, seismic, etc.) and historical production /injection data.


Data Requirement:

Top-Down, Intelligent Reservoir Modeling is an introduced, peer-reviewed, reservoir modeling technology that requires only production rate data to start the analysis. The model is fine tuned as more data (logs, cores, pressure, seismic …) is incorporated in the analysis.

Short Development Time:

Development of top-down models is measured in days and weeks and not months.

Analysis Complexity:

Unlike conventional reservoir simulation, no specialized skills are required for the development and analysis of top-down reservoir model. Any petroleum engineer or geo-scientist can build, understand and fully analyze a top-down model.


Top-down models are ideal for fields with at least 50 wells and 5 years of production history. More wells and more historical data enhance the results.


Top-down models can serve as a compliment to existing reservoir simulation models to provide an independent analysis or serve as an alternative to conventional reservoir simulation when such models are time and cost prohibitive.


A completely new and innovative approach that integrates solid reservoir engineering techniques with state-of-the-art in Artificial intelligence and Data Mining (AI&DM).


Field Development Strategies, Remaining Reserves, Optimum In-fill Locations and a List of Underperformer Wells as prime candidates for potential workovers are among the deliverables of Top-Down modeling technology.

Conventional reservoir simulation and modeling is a bottom-up approach. It starts with building a geological model of the reservoir that is populated with the best available petrophysical and geophysical information at the time of development. Engineering fluid flow principles are then added and solved numerically so as to arrive at a dynamic reservoir model. The dynamic reservoir model is calibrated using the production history of multiple wells and the history matched model is used to strategize field development in order to improve recovery.

Top-Down, Intelligent Reservoir Modeling, an introduced and peer-reviewed reservoir modeling technology, approaches the reservoir simulation and modeling from an opposite angle by attempting to build a realization of the reservoir starting with well production behavior (history). The production history is augmented by core, log, well test and seismic data in order to increase the accuracy of the Top-Down modeling technique. Although not intended as a substitute for the conventional reservoir simulation of large, complex fields, this innovative and novel approach to reservoir modeling can be used as an alternative (at a fraction of the cost) to conventional reservoir simulation and modeling in cases where performing conventional modeling is cost (and man-power) prohibitive. In cases where a conventional model of a reservoir already exists, Top-Down modeling should be considered as a compliment to, rather than a competition for the conventional technique, to provide an independent look at the data coming from the reservoir/wells for optimum development strategy and recovery enhancement.


Top-Down, Intelligent Reservoir Modeling starts with well-known reservoir engineering techniques such as Decline Curve Analysis, Type Curve Matching, History Matching using single well numerical reservoir simulation, Volumetric Reserve Estimation and calculation of Recovery Factors for all the wells (individually) in the field. Using statistical techniques multiple Production Indicators (3, 6, and 9 months cum. production as well as 1, 3, 5, and 10 year cum. oil, gas and water production and Gas Oil Ratio and Water Cut) are calculated. These analyses and statistics generate a large volume of data and information that are snapshots of reservoir behavior in discrete slices of time and space. This large volume of data is processed using ISI's proprietary implementation of state-of-the-art in artificial intelligence and data mining (neural modeling, genetic optimization and fuzzy pattern recognition), first using a set of discrete modeling techniques to generate production related predictive models of well behavior. The set of discrete, intelligent models are then integrated using a continuous fuzzy pattern recognition algorithm in order to arrive at a cohesive picture and model of the reservoir as a whole.

The Top-Down, Intelligent Reservoir Model is then calibrated using the most recent set of wells that have been drilled. The calibrated model is then used for field development strategies to improve and enhance hydrocarbon recovery. Following figure shows the Top-Down modeling workflow in the form of a flow chart.



The Top-Down, Intelligent Reservoir Modeling is an elegant integration of state-of-the-art in Artificial Intelligence & Data Mining (AI&DM) with solid reservoir engineering techniques and principles. It provides a unique perspective of the field and the reservoir using actual measurements. It provides qualitatively accurate reservoir characteristics that can play a key role in making important and strategic field development decisions.

Following is a brief summary of several components of this innovative approach to reservoir management. The key to the top-down modeling is ISI's innovative integration of the following components using state-of-the-art Artificial Intelligence & Data Mining (AI&DM).

Decline Curve Analysis

Conventional hyperbolic decline curve analysis is performed on oil, gas and water production data of all the wells. ISI's proprietary Intelligent Decline Curve Analysis is used to model some production data such as GOR and Water Cut that does not usually exhibit a positive but rather a negative decline.

Type Curve Matching

Using the appropriate type curves from the literature, and other that have been developed internally, production data from all wells are analyzed. Special techniques are used to remove the inherent subjectivity associated with type curve matching process.

History Matching

Segment-based history matching is performed using a numerical simulation model.

Production Statistics

General statistics are generated based on the available production data such as 3, 6, 9 months cumulative production as well as one, three, five and ten years cumulative productions. Similar data is generated for Gas Oil Ratio and water cut as well.

Volumetric Reserve Estimation

Using Voronoi graph theory in conjunction with well logs volumetric reserves are estimated for each well, individually. Estimated Ultimate Drainage Area (EUDA) is a byproduct of this procedure. The EUDA is a dynamic property that is related to the production scheme employed in the field and may change as new wells are introduced.

Recovery Factor Calculation

Using the results of Decline Curve analysis and Volumetric Reserve Estimation, a well-based Recovery Factor is calculated for all wells, individually. A field-wide Recovery Factor is also calculated. This would be an item that will be optimized in the consequent steps of the analysis.


Discrete Predictive Modeling

Results of the above mentioned analyses are a wealth of data and information that are generated based on individual wells. Using ISI's unique implementation of the state-of-the-art AI&DM techniques discrete, intelligent, predictive models are developed based on the large amount of data and information that has been generated. The predictive models represent all aspects of reservoir characteristics that have been analyzed.

Continuous Predictive Modeling

Using ISI's innovative, two-dimensional Fuzzy Pattern Recognition (FPR) technology, discrete predictive models are fused into a cohesive full-field reservoir model that is capable of providing a tool for integrated reservoir management. This full field model can identify the distribution of the remaining reserves, sweet spots for In-fill locations as well as under-performer wells. Furthermore, the full field model, upon calibration, is used as an effective tool for field development strategies.

Model Calibration

The full field model is calibrated based on classifying the reservoir into most to least prolific areas prior to be used in the predictive mode. This is done using the latest drilled wells in the field. This practice is an analogy of history matching of the conventional reservoir simulation models. The calibrated model can then be used in predictive mode for field development strategies.

Field Development Strategies

Performing economic analysis, while taking into account the uncertainties associated with decision making, multiple field development strategies are examined in order to identify the optimum set of operations that would result in recovery enhancement. This process includes identification of remaining reserves, sweet spots for In-fill drilling as well as under-performer wells.