EP4073694A1 - Procede de categorisation d'une roche a partir d'au moins une image - Google Patents
Procede de categorisation d'une roche a partir d'au moins une imageInfo
- Publication number
- EP4073694A1 EP4073694A1 EP20816185.1A EP20816185A EP4073694A1 EP 4073694 A1 EP4073694 A1 EP 4073694A1 EP 20816185 A EP20816185 A EP 20816185A EP 4073694 A1 EP4073694 A1 EP 4073694A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- rock
- image
- categorizing
- categorized
- descriptor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
Definitions
- the present invention relates to the field of categorization of rocks, in particular the determination of the lithological facies of rocks.
- the object of the present invention is to automatically and precisely categorize a rock.
- the present invention relates to a method for categorizing a rock, in which at least one image of the rock to be categorized is acquired, and a decision tree is used which categorizes the rocks according to several descriptors, and a decision tree is used.
- automatic learning method from a base of rock images. Machine learning is applied for each descriptor considered in order to precisely determine descriptors of the rock to be categorized, which allows precise categorization of the rock by means of the decision tree.
- the invention relates to a method for categorizing a rock using a rock image database.
- a decision tree is constructed which categorizes the rocks according to a plurality of descriptors characterizing said rocks; b) Each image of said base of rock images is associated with a plurality of said descriptors characterizing said rock; c) At least one image of said rock to be categorized is acquired; d) at least one descriptor is determined for said at least one acquired image of said rock to be analyzed by means of automatic learning from said base of rock images, automatic learning being applied to each descriptor considered; and e) said rock to be categorized is categorized, by means of said at least one determined descriptor and by means of said constructed decision tree.
- said decision tree is a decision tree of naturalistic description of said rocks.
- said at least one image of said rock to be categorized is acquired by photography, by microscopy or by a scanner.
- said image of said rock to be categorized by photography is acquired by means of a smart phone.
- said decision tree categorizes the lithological facies of said rock.
- At least one descriptor characterizing said rock is chosen from the origin of said rock, the chemistry of said rock, the presence of foliation, the presence of olivine, the presence of bedding, the presence of mica.
- said machine learning uses a neural network, preferably a convolutional neural network.
- the method comprises a step of pre-processing said at least one image acquired prior to the step of determining at least one descriptor of said at least one acquired image.
- the method comprises a step of integrating into said rock image base said at least one acquired image and said at least one associated determined descriptor.
- the invention relates to a method of exploiting a soil or a subsoil, in which the following steps are implemented: a) At least one rock of said soil or of said subsoil is categorized in means of the method of categorizing a rock according to one of the preceding characteristics; and b) said soil or said subsoil is exploited as a function of said categorization of said at least one rock.
- said exploitation of the ground or of the subsoil relates to the construction of a structure on said ground or in the subsoil, the storage of gas in the subsoil, or the exploitation of raw materials of said soil or said subsoil, preferably said raw materials being the rock itself, or a material or a fluid contained in said soil or in said subsoil.
- FIG. 1 illustrates the steps of the method according to one embodiment of the invention.
- FIG. 2 illustrates the steps of the method according to a second embodiment of the invention.
- Figure 3 illustrates the steps of the method according to a third embodiment of the invention.
- Figure 4 illustrates a decision tree according to one embodiment of the invention.
- FIG. 5 illustrates a decision tree for an exemplary embodiment of the invention for the categorization of the lithological facies of a rock.
- the present invention relates to a method of categorizing a rock.
- the categorization of a rock is called the determination of a target characteristic of a rock. It can be the identification of a rock, for example it can be in particular the lithological facies of the rock. It can also be ranges of petrophysical properties, such as particle size and porosity, or ranges of geological ages and formation conditions, mechanical history of rock, etc.
- the method according to the invention uses a database of images of rocks, it is a database of images of different rocks.
- the method according to the invention implements the following steps:
- the method according to the invention can be implemented by means of a computer system, in particular a computer, a smart phone ("smartphone"), etc.
- Steps 1) and 2) can be performed in this order or simultaneously.
- Steps 1) and 2) can be performed beforehand and can be performed offline.
- Steps 3) to 6) can be performed online. These steps are detailed in the remainder of the description.
- FIG. 1 illustrates, schematically and in a nonlimiting manner, the steps of the method according to one embodiment of the invention.
- ARB which categorizes the rocks according to descriptors (characteristics), and a plurality of descriptors (among those used in the decision tree) are associated with each image of the BIR rock image database.
- APP machine learning is carried out from the rock image database.
- the method may further include a step of preprocessing the image.
- the method according to the invention implements the following steps:
- the method according to the invention can be implemented by means of a computer system, in particular a computer, a smart phone ("smartphone"), etc.
- Steps 1) and 2) can be performed in this order or simultaneously.
- Steps 1) and 2) can be performed beforehand and can be performed offline.
- Steps 3) to 6) can be performed online. These steps are detailed in the remainder of the description.
- FIG. 2 illustrates, schematically and in a nonlimiting manner, the steps of the method according to this embodiment of the invention.
- an ARB decision tree is constructed which categorizes the rocks according to descriptors (characteristics), and a plurality of descriptors (among those used in the BIR rock image base) are associated with each image. decision).
- APP machine learning is carried out from the rock image database.
- the method may further include a step of updating the image base with the acquired image.
- the method according to the invention implements the following steps:
- the method according to the invention can be implemented by means of a computer system, in particular a computer, a smart phone ("smartphone"), etc.
- Steps 1) and 2) can be performed in this order, or simultaneously.
- Steps 1) and 2) can be performed beforehand and can be performed offline.
- Steps 3) to 7) can be performed online. These steps are detailed in the remainder of the description.
- FIG. 3 illustrates, schematically and in a nonlimiting manner, the steps of the method according to this embodiment of the invention.
- an ARB decision tree is constructed which categorizes the rocks according to descriptors (characteristics), and a plurality of descriptors (among those used in the BIR rock image base) are associated with each image. decision).
- APP machine learning is carried out from the rock image database.
- On line Onl we acquire an image of the rock to be categorized IMA, then by means of APP machine learning, we determine by inference (INF) a plurality of descriptors desc (only three are shown) of the rock to be categorized, and these descriptors desc are applied to the decision tree ARB to determine DET the categorization because of the rock to be categorized. Finally, the new image acquired and the associated descriptors are added in the automatic learning APP, this step is illustrated by the arrows relating to the descriptors desc which are directed to the automatic learning step.
- the embodiments described above can be combined to combine the effects.
- the method can then comprise a step of pre-processing the image and a step of updating the base of rock images.
- a decision tree is constructed which categorizes the rocks according to several descriptors (called auxiliary characteristics, and which are different from the target characteristic) which categorize the rock.
- a decision tree is a tool representing a set of choices in the graphical form of a tree. The various possible decisions are located at the ends of the branches (the “leaves” of the tree), and are reached according to decisions taken at each stage.
- each step corresponds to a value of a descriptor
- each end of a branch corresponds to a categorization of the rock.
- Figure 4 illustrates, schematically and in a non-limiting manner, a decision tree that can be used for the method according to the invention.
- the descriptors are denoted desd, desc2, desc3 and desc4 and are delimited by the vertical dotted lines
- the values of the descriptors are indicated by letters from a to m
- the categorizations of the rock are denoted from cari to car8 .
- the first decision corresponds to the descriptor desd which can take the values a or b.
- the second descriptor desc2 can take the values c or d, while when the first descriptor desd is equal to b, the second descriptor desc 2 is equal to e or f, and so on.
- the categorization of the rock is determined. For example, if the first descriptor desd is equal to a, the second descriptor desc2 is equal to c and the third descriptor desc3 is equal to g, then the associated categorization is the cari categorization.
- the decision tree can be constructed from a naturalistic description of the rocks.
- descriptors and categorizations can be chosen to match the families of rocks.
- This embodiment makes it possible to adopt a naturalistic categorization of rocks
- the categorizations can be in particular: dunite, gabbro, orthogneiss, granite, basalt, mica schist, schist, etc.
- at least one naturalistic descriptor of the rocks can be determined.
- the naturalistic descriptor of the rocks can in particular be chosen from:
- olivine the presence of olivine: it can be present or absent
- the presence of bedding it can be present or absent, or
- descriptors make it possible to distinguish between the most frequently encountered rocks. Indeed, these descriptors make it possible to take into account the texture, the origin, the structure (bedding, sheet), the color linked to the chemistry of the rock, the presence of specific minerals (olivine, mica).
- FIG. 5 illustrates, schematically and in a non-limiting manner, a decision tree for this embodiment.
- the first descriptor concerns the origin, which can be plutonic (a), effusive (b) or sedimentary (c).
- the second descriptor concerns chemistry, which can be basic (d, f) or acid (e, g).
- the second descriptor is foliation which may be present (h) or absent (i).
- the third descriptor is olivine, which can be present (j) or absent (k).
- the rock is a dunite, and if it is absent (k) the rock is a Gabbro.
- the third descriptor is bedding, which can be present (I) or absent (m).
- bedding is present (I) then the rock is an orthogneiss, and if it is absent (m) the rock is a granite.
- the rock is a basalt.
- the origin is effusive (b) and the chemistry acidic (g)
- the rock is of a different type N / C.
- the third descriptor is the presence of mica, which can be present (n) or absent (o).
- mica can be present (n) then the rock is a mica schist, and if it is absent (o) the rock is a shale.
- the rock is sedimentary (a) and the foliation absent (i), the rock is of another type N / C.
- the number of categorizations depends on the desired precision in the classification of rocks. According to one aspect of the invention, for the embodiment for which the method categorizes the lithological facies of the rock for a wide audience, the number of categorizations may be between 5 and 30, preferably between 8 and 20. According to one. another aspect of the invention, for the embodiment for which the method categorizes the lithological facies of the rock for a specialist audience, the number of categorizations may be between 5 and 300, or even more.
- a plurality of rock descriptors are associated with each image of the rock image database.
- the descriptors are those used to build the decision tree. We thus form a learning base for each descriptor considered.
- descriptors can be implemented by image processing, which can analyze in particular the colors, shapes, dimensions of the rocks of the rock image base, or any other information contained in the image.
- the descriptors can also include the geolocation of the image. This geolocation can be linked to the image, in particular if it comes from a photograph taken by a smart phone ("smartphone"). Indeed, this descriptor makes it possible to bring together rocks having close geographical areas.
- association of images with descriptors can be implemented by a user.
- the number of rock images in the rock image database can depend on the number of descriptors considered in the decision tree. A large number of rock images improves the accuracy of rock categorization. However, a high number of rock images requires a large memory, and may require a significant process execution time.
- the base of rock images can include at least one image by categorization of rocks. According to one embodiment, the rock image base can include around one hundred rock images, preferably the number of rock images can be several hundred rock images, preferably the number of rock images. number of rock images can be several thousand rock images, or even several tens of thousands of rock images.
- a microscopic or macroscopic image can be acquired. This could be an image of a thin blade of a rock, an image of a rock sample, or an image of an outcrop (eg cliff). Thus, it is possible to determine the categorization of the rock regardless of the information available.
- the image of the rock to be categorized can be acquired by photography, by microscopy, by a scanner, or by any similar means. These means allow a simple acquisition requiring only conventional equipment.
- the image of the rock can be acquired by photography using a smart phone ("smartphone").
- smart phone smart phone
- the pre-processing of the acquired image can consist of a selection of a zone of interest on the acquired image.
- this pre-processing can make it possible to remove the background of the image, which does not correspond to the rock to be categorized.
- the pre-processing may consist of a modification of the image, in particular its contrast, its luminosity, an enlargement, etc.
- the pre-processing may be a pre-processing linked to the method of acquiring the image, for example polarized light, infrared wavelength, etc.
- At least one descriptor of the acquired image of the rock to be categorized is determined by means of machine learning from said base of rock images and descriptors associated with step 2), and by application to the image acquired in step 3) (and possibly pre-processed in step 4). Machine learning is then applied for each descriptor considered, and a plurality of descriptors of the acquired image is then obtained.
- This step makes it possible, for each descriptor considered, to bring the acquired image closer to the images of rocks from the rock image database, and thus to classify the acquired image among families of images having the same properties.
- several characteristics (several descriptors) of the rock to be categorized are independently determined, which makes it possible to precisely determine the categorization of the rock.
- this step can use image processing (colors, shapes, dimensions %) to perform machine learning.
- machine learning uses a neural network, preferably a convolutional neural network.
- the convolutional neural network is particularly suitable for image processing.
- machine learning can be of any type, in particular a non-convolutional neural network, a random forest method, a support vector machine method (standing for “Support Vector Machine” or SVM), a of Gaussian processes.
- the rock to be categorized is categorized, by applying the decision tree constructed in step 1) with the descriptors determined in step 5).
- the decision tree constructed in step 1) we know the decisions of the decision tree, and we can therefore know the end of the branch of the decision tree which corresponds to the rock to be categorized. This branch then indicates the categorization of the rock.
- the rock to be categorized is an orthogneiss, which corresponds to the categorization performed by a geologist.
- the categorization of the rock can be displayed on a computer medium, for example a computer or a smart phone.
- this step is optional for the process.
- This step concerns updating the rock image database with the acquired images.
- the learning bases of each descriptor can be increased with each implementation of the method, which promotes the reliability and robustness of the method.
- the base of rock images can be updated, when the categorization of the rock has been validated by another method (a method according to the prior art, or by a geologist ).
- the invention relates to a method of exploiting the ground or the subsoil.
- the following steps are implemented: a) At least one rock from the ground and / or from the subsoil is categorized, by means of the method for categorizing a rock according to any one of the variants or combinations of variants described above; and b) The soil and / or the subsoil is exploited according to the categorization of the rock in the previous step.
- the operation may concern in particular the field of construction of buildings or works of art, or the field of the exploitation of raw materials, or the field of gas storage, the field of risk determination, etc.
- the constitution of rock outcrops and / or the subsoil is determined by categorizing the rock, and construction is carried out by adapting in particular the foundations, the structure of the construction according to the categorization of the rock.
- the rock to be categorized can be taken from the ground or from the subsoil in a slightly buried manner.
- the constitution of rock outcrops and / or subsoil is determined by categorizing the rock, and we carries out the exploitation of raw materials (the raw materials can be the rock itself, a material, for example a metal, or a fluid, for example hydrocarbons, present in the subsoil), by making it possible in particular to determine the suitable areas (i.e. drilling areas, areas to be dug for mines or quarries, etc. for the purpose of recovering raw materials), determine the methods and tools to be used (e.g. assisted recovery of hydrocarbons, drilling tools, the nature of explosive devices for mines or quarries, etc.).
- the rock to be categorized can be taken from deep in the subsoil, can result from drill cuttings, or can come from a brush, etc.
- the constitution of the subsoil is determined by categorizing the rock, and gas storage is carried out in the subsoil in an appropriate area, that is, that is to say in an underground zone capable of storing the gas without leakage.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR1914253A FR3104773B1 (fr) | 2019-12-12 | 2019-12-12 | Procédé de catégorisation d’une roche à partir d’au moins une image |
| PCT/EP2020/084389 WO2021115903A1 (fr) | 2019-12-12 | 2020-12-03 | Procede de categorisation d'une roche a partir d'au moins une image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4073694A1 true EP4073694A1 (fr) | 2022-10-19 |
Family
ID=69743498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP20816185.1A Pending EP4073694A1 (fr) | 2019-12-12 | 2020-12-03 | Procede de categorisation d'une roche a partir d'au moins une image |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US12339931B2 (fr) |
| EP (1) | EP4073694A1 (fr) |
| CA (1) | CA3157064A1 (fr) |
| FR (1) | FR3104773B1 (fr) |
| WO (1) | WO2021115903A1 (fr) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2760105C1 (ru) * | 2021-03-12 | 2021-11-22 | Публичное акционерное общество «Газпром нефть» | Система, машиночитаемый носитель и способ анализа керна по изображениям |
| CN116258876B (zh) * | 2023-02-06 | 2026-04-28 | 中国石油大学(北京) | 岩石薄片图像的描述文本的确定方法、存储介质及处理器 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3077619B1 (fr) * | 2013-12-05 | 2018-10-24 | Services Petroliers Schlumberger | Construction de modèle de noyau numérique |
| US10753918B2 (en) * | 2014-12-15 | 2020-08-25 | Saudi Arabian Oil Company | Physical reservoir rock interpretation in a 3D petrophysical modeling environment |
| US20170286802A1 (en) * | 2016-04-01 | 2017-10-05 | Saudi Arabian Oil Company | Automated core description |
| JP7187099B2 (ja) * | 2017-09-15 | 2022-12-12 | サウジ アラビアン オイル カンパニー | ニューラルネットワークを用いて炭化水素貯留層の石油物理特性を推測すること |
-
2019
- 2019-12-12 FR FR1914253A patent/FR3104773B1/fr active Active
-
2020
- 2020-12-03 WO PCT/EP2020/084389 patent/WO2021115903A1/fr not_active Ceased
- 2020-12-03 US US17/782,673 patent/US12339931B2/en active Active
- 2020-12-03 CA CA3157064A patent/CA3157064A1/fr active Pending
- 2020-12-03 EP EP20816185.1A patent/EP4073694A1/fr active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| US12339931B2 (en) | 2025-06-24 |
| FR3104773A1 (fr) | 2021-06-18 |
| WO2021115903A1 (fr) | 2021-06-17 |
| US20230008058A1 (en) | 2023-01-12 |
| CA3157064A1 (fr) | 2021-06-17 |
| FR3104773B1 (fr) | 2021-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4143567B1 (fr) | Procede de detection d'au moins un constituant geologique d'un echantillon de roche | |
| EP2846176B1 (fr) | Procédé d'exploitation d'un gisement souterrain comprénant au moins un affleurement géologique au moyen d'une photogrammétrie | |
| EP1503258A1 (fr) | Methode pour optimiser la production d'un gisement petrolier en presence d'incertitudes | |
| EP4073694A1 (fr) | Procede de categorisation d'une roche a partir d'au moins une image | |
| CA2558336A1 (fr) | Methode pour mettre a jour un modele geologique de reservoir a l'aide de donnees dynamiques | |
| FR3060152A1 (fr) | Classement automatique de rapports de forage avec un traitement pousse du langage naturel | |
| EP3647533A1 (fr) | Optimisation du forage d'un tunnelier en fonction d'interactions terrain/machine | |
| FR3058456A1 (fr) | Classification de fluides de fond de puits automatisee en utilisant des donnees de composante de spectroscopie principale | |
| FR3066224A1 (fr) | Procede et systeme pour forer un puits de forage et identifier une defaillance du trepan de forage par deconvolution des donnees de capteur | |
| WO2011030013A2 (fr) | Procédé de modélisation déterministe des écoulements en milieu poreux | |
| FR3081078A1 (fr) | Procédé de génération de cartes de probabilité prédictives d’éléments de réseaux d’hydrocarbures | |
| EP4208818A1 (fr) | Procede de detection et de comptage d'au moins un constituant geologique d'un echantillon de roche | |
| FR3036425A1 (fr) | ||
| CA3185043A1 (fr) | Methode pour determiner une interpretation en electrofacies de mesures realisees dans un puits | |
| EP3224653B1 (fr) | Méthode et dispositif de traitement de données de puits | |
| WO2021123209A1 (fr) | Procédé de segmentation d'une image d'entrée représentant un document comportant des informations structurées | |
| FR3054059A1 (fr) | Determination d'un age numerique pour des evenements geologiques au sein d'un schema | |
| FR3031605A1 (fr) | Filtrage et analyse de donnees par arbres multi-niveaux a variables composites | |
| WO2016132068A1 (fr) | Procédé de détermination de la bathymétrie à partir d'images satellitaires optiques quasi synchrones | |
| FR3146008A1 (fr) | Procede de caracterisation d’un defaut d’une canalisation | |
| FR3140647A1 (fr) | Procédé pour prédire une diagraphie pendant le forage d’un puits | |
| FR3119038A1 (fr) | Contrôle visuel d’un élément se déplaçant sur une ligne de production | |
| FR3060794A1 (fr) | Procede de determination de l'etat d'un systeme, procede de determination d'une methode de projection optimale et dispositif mettant en œuvre lesdits procedes | |
| Sharma et al. | Empirical Seabed Image Classification Using Labeled Machine Learning Techniques | |
| FR3052483A1 (fr) | Aide a la conduite d'un tunnelier par correlation entre mesures effectuees sur le tunnelier et donnees issues de sondages depuis la surface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20220712 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20240626 |