Abstract: The disclosure relates to a method and system for downhole processing of data, such as images, including using a set of downhole sensors to measure parameters relative to the borehole at a plurality of depths and azimuths and detecting predetermined features of the borehole, using a downhole processor, with a trained machine-learning model and extracting characterization data, characterizing the shape and position of the predetermined features that are transmitted to the surface. It also provides a method and system for providing an image of a geological formation at the surface including transmitting a first dataset to the surface that will be used for reconstructing an image at the surface, downhole processing of a second dataset to detect predetermined features and extract characterization data that are transmitted at the surface and displaying a combined image comprising the predetermined features overlaid on the first image.

Abstract: Apparatus and methods for ascribing one of multiple predetermined sub-classes to multiple pixels of an image of an unknown rock sample retrieved from a geological formation. The ascription utilizes a deep learning model trained with an annotated training dataset. The annotated training dataset includes multi-pixel images of known rock samples and, for each known rock sample image, which sub-class corresponds to at least a subset of pixels of that image. For each pixel of the unknown rock sample image having an ascribed sub-class, which one of predetermined meta-classes is associated with that pixel is derived based on the sub-class ascribed to that pixel. The meta-classes represent different predetermined rock types. At least one property of the formation is predicted utilizing the ascription-derived meta-classes, including which rock type(s) are present in the formation.

Abstract: Apparatus and methods for ascribing one of multiple predetermined sub-classes to multiple pixels of an image of an unknown rock sample retrieved from a geological formation. The ascription utilizes a deep learning model trained with an annotated training dataset. The annotated training dataset includes multi-pixel images of known rock samples and, for each known rock sample image, which sub-class corresponds to at least a subset of pixels of that image. For each pixel of the unknown rock sample image having an ascribed sub-class, which one of predetermined meta-classes is associated with that pixel is derived based on the sub-class ascribed to that pixel. The meta-classes represent different predetermined rock types. At least one property of the formation is predicted utilizing the ascription-derived meta-classes, including which rock type(s) are present in the formation.

Abstract: The disclosure relates to a method and system for downhole processing of data, such as images, including using a set of downhole sensors to measure parameters relative to the borehole at a plurality of depths and azimuths and detecting predetermined features of the borehole, using a downhole processor, with a trained machine-learning model and extracting characterization data, characterizing the shape and position of the predetermined features that are transmitted to the surface. It also provides a method and system for providing an image of a geological formation at the surface including transmitting a first dataset to the surface that will be used for reconstructing an image at the surface, downhole processing of a second dataset to detect predetermined features and extract characterization data that are transmitted at the surface and displaying a combined image comprising the predetermined features overlaid on the first image.

Abstract: This method comprises: obtaining a first module for labelling images by machine learning on the basis of a first training corpus; obtaining a second training corpus from the first training corpus, by replacing, in the first training corpus, each of a portion of first labels by a replacement label, two first labels being replaced by one and the same replacement label; obtaining a second module for labelling images by machine learning on the basis of the second training corpus; obtaining the system for labelling images comprising: a first upstream module obtained from a portion of the first module, a second upstream module obtained from a portion of the second module and a downstream module designed to provide a labelling of an image on the basis of first descriptive data provided by the first upstream module and of second descriptive data provided by the second upstream module.