Search

EP-4264554-B1 - PREDICTIVE GEOLOGICAL DRAWING SYSTEM AND METHOD

EP4264554B1EP 4264554 B1EP4264554 B1EP 4264554B1EP-4264554-B1

Inventors

  • FUCHEY, Yannick
  • MOSCARDI, Eric

Dates

Publication Date
20260506
Application Date
20211217

Claims (10)

  1. A computer-implemented method for representing a geology, comprising: receiving (410) one or more drawing strokes that are part of a geological feature sketch; predicting (411), using a machine learning model, a plurality of likely geological features based at least in part on the one or more drawing strokes before the sketch is complete, wherein the machine learning model is trained based on sketches of known geological features; displaying (412) the plurality of predicted likely geological features, the predictions providing several options for characteristics of the geological feature including at least one of grain size, lithology, structure, and geometry based on the received drawing strokes entered to this point; receiving (414) a selection of one of the one or more predicted geological features; and generating (416) an image representing the geology including a digital representation of the selected one of the one or more predicted geological features.
  2. The method of claim 1, wherein receiving (410; 912) the one or more drawing strokes comprises receiving (914) metadata representing the one or more drawing strokes, and wherein predicting (922) the one or more predicted geological features is based at least in part on the metadata.
  3. The method of claim 2, wherein the metadata comprises an order in which the one or more drawing strokes are received (916).
  4. The method of claim 1, wherein the geological feature sketch at least partially represents a rock layer (918), wherein the method further comprises determining (932) a depth interval of the rock layer in the image based on a position of the one or more drawing strokes, and wherein generating (934) the image comprises adding the rock layer into the image at a location that represents the depth interval.
  5. The method of claim 1, further comprising: receiving (924) one or more additional drawing strokes after receiving the one or more drawing strokes, the one or more additional drawing strokes being entered also as part of the geological feature sketch; and updating (926) the one or more predicted geological features based at least in part on the one or more additional drawing strokes in combination with the one or more drawing strokes.
  6. The method of claim 1, further comprising: displaying (902) a representation of a known geological feature to a plurality of training users; receiving (904) training geological feature sketches from the plurality of training users; and training (908) the machine learning model based at least in part on the training geological feature sketches.
  7. The method of claim 6, wherein receiving (904) the training geological feature sketches comprises receiving (906) point location data, timestamp data, data representing an order in which drawing strokes were entered, and pressure data, and wherein training (908) the machine learning model comprises training (910) the machine learning model based at least in part on the point location data, the timestamp data, the data representing an order in which drawing strokes were entered, and the pressure data.
  8. A computing system (1000), comprising: one or more processors (1004); a display means; and a memory system (1006) including one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors (1004), cause the computing system (1000) to perform operations, the operations comprising the steps of the method of any preceding claims.
  9. A non-transitory computer-readable medium (1006) storing instructions that, when executed by at least one processor (1004) of the computing system (1000) of claim 8, cause the computing system (1000) to perform operations, the operations comprising the steps of the method of any of claims 1 to 7.
  10. A computer program comprising instructions that, when executed by a processor (10004) of the computing system (1000) of claim 8, cause the computing system (1000) to perform the steps of the method of any one of claims 1 to 7.

Description

Background Geologists generally sketch geological data using a pen or pencil and a sketch book. For example, geologists may sketch domain-specific objects such as sedimentological logs, stratigraphic triangles, bioform symbols, landscapes, tool string schemas, and the like. Different people have different drawing abilities, and thus the sketches they produce, even of the same scene, may not be the same. Thus, harmonizing the sketches can prove difficult. Presently, there are tools that permit a user to click through to select different characteristics of portions (e.g., depth interval, grain size, etc.) of a domain-specific object. However, this is a break from the intuitive drawing process that geologists generally employ and may generally slow the process of the geologists recording observations. Mould David et al:"3D geological modeling using sketches and annotations from geological maps". Proceedings of the 4th joint symposium on computational aesthetics, non photorealistic animation and rendering, and sketch-based interfaces and modeling, 8 August 2014, pages 17-25, XP093211033 describes a sketch-based modeler that allows sketching of geological contacts, symbols and annotations. Contacts are checked and combined to define different regions on the map and geological symbols are recognized and assigned to regions within the map. Based on the contacts adjacency and the provided symbols, the system automatically defines which layer lies on top of the other. Based on constraints defined on the sketch and the computed sequence of layers, a 3D geological model is constructed. Natali Mattia et al: "Sketch-based modelling and visualization of geological deposition", Computers &Geosciences, vol 67, 30 June 2014, pages 40-48, XP0268645860 describes a sketch-based interface with a layered data representation and a rendering approach. The approach is based on two synchronized data structures: rearrangeable relative layers which allow geological processes to be kept independent of each other and absolute layers derived from the relative layers used for fast rendering. Summary The present invention resides in a computer-implemented method for representing a geology as defined in claim 1, a computer system as defined in claim 8, a non-transitory, computer-readable medium as defined in claim 9 and a computer program as defined in claim 10. The computing systems and methods disclosed herein are more effective methods for processing collected data that may, for example, correspond to a surface and a subsurface region. These computing systems and methods increase data processing effectiveness, efficiency, and accuracy. Such methods and computing systems may complement or replace conventional methods for processing collected data. Brief Description of the Drawings The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings. In the figures: Figure 1 illustrates an example of a system that includes various management components to manage various aspects of a geologic environment, according to an embodiment.Figure 2 illustrates a flowchart of a method for representing a geology, according to an embodiment.Figure 3 illustrates an input to and an output from the method, according to an embodiment.Figure 4 illustrates a flowchart of another method for representing a geology, according to an embodiment.Figure 5 illustrates a training template for acquiring geological feature sketches to train a machine learning model, according to an embodiment.Figure 6 illustrates a display including input drawing strokes received as part of a geological feature sketch from a user, according to an embodiment.Figure 7 illustrates a display of an image, incorporating digital representations of geological features formed at least partially by predicting geological features being sketched by the user, according to an embodiment.Figure 8A illustrates a view of a user interface (e.g., a "web-app") that may be used to harvest training data from users, according to an embodiment.Figure 8B illustrates a flowchart of a method for acquiring training data for a machine learning model, according to an embodiment.Figures 9A, 9B, and 9C illustrate a flowchart of a method for representing a geology, according to an embodiment.Figure 10 illustrates a schematic view of a computing system, according to an embodiment. Detailed Description Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to one of ordinary skill in the art that the invention may be practiced without these specific details. In other instances, well-known methods, procedures, com