Autonomous Interpretation of Rock Drill Cuttings

Abstract

A computer-implemented method that autonomously performs rock drill cuttings interpretation is described herein. The method includes obtaining rock drill cuttings representations. The method also includes preprocessing the rock drill cuttings representations. The method also includes performing unsupervised image segmentation in order to obtain masked representations of such images discriminating rock types. The method also includes performing supervised learning through a custom Convolutional Neuronal Network using the segmented pictures as inputs and a continuous or discrete mineralogical or sedimentological variable of interest as the output. Additionally, the method includes autonomously predicting such mineralogical or sedimentological quantity from new rock drill cuttings pictures using the parameters of the unsupervised segmentation and the trained supervised model created for this purpose.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 obtaining, with one or more hardware processors, rock drill cuttings representations;   preprocessing, with the one or more hardware processors, the rock drill cuttings representations by applying at least one transformation to the rock drill cuttings representations;   segmenting, with the one or more hardware processors, the preprocessed rock drill cuttings representations into segmented pictures by inputting the preprocessed rock drill cuttings representations into a first machine learning model that outputs the segmented pictures, wherein the segmented pictures are masked images that include at least one rock type; and   predicting, with the one or more hardware processors, depth indexed mineralogical or sedimentological data using the segmented pictures input to a trained second machine learning model.   
     
     
         2 . The computer implemented method of  claim 1 , wherein the second machine learning model is trained to predict custom categories. 
     
     
         3 . The computer implemented method of  claim 1 , wherein the first machine learning model segments and groups individual rocks visible in each picture or frame using unsupervised learning. 
     
     
         4 . The computer implemented method of  claim 1 , wherein the trained second machine learning model is a supervised convolutional neural network. 
     
     
         5 . The computer implemented method of  claim 1 , wherein the rock drill cuttings representations are a high-definition video of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         6 . The computer implemented method of  claim 1 , wherein the rock drill cuttings representations are images of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         7 . The computer implemented method of  claim 1 , wherein the rock drill cuttings representations are microscope images of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         8 . An apparatus comprising a non-transitory, computer readable, storage medium that stores instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
 preprocessing rock drill cuttings representations by applying at least one transformation to the rock drill cuttings representations;   segmenting the preprocessed rock drill cuttings representations into segmented pictures by inputting the preprocessed rock drill cuttings representations into a first machine learning model that outputs segmented pictures, wherein the segmented pictures are masked images that include at least one rock type; and   predicting depth indexed mineralogical or sedimentological data using the segmented pictures input to a trained second machine learning model.   
     
     
         9 . The apparatus of  claim 8 , wherein the second machine learning model is trained to predict custom categories. 
     
     
         10 . The apparatus of  claim 8 , wherein the first machine learning model segments and groups individual rocks visible in each picture or frame using unsupervised learning. 
     
     
         11 . The apparatus of  claim 8 , wherein the trained second machine learning model is a supervised convolutional neural network. 
     
     
         12 . The apparatus of  claim 8 , wherein the rock drill cuttings representations are a high-definition video of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         13 . The apparatus of  claim 8 , wherein the rock drill cuttings representations are images of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         14 . The apparatus of  claim 8 , wherein the rock drill cuttings representations are microscope images of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         15 . A system, comprising:
 one or more memory modules;   one or more hardware processors communicably coupled to the one or more memory modules, the one or more hardware processors configured to execute instructions stored on the one or more memory models to perform operations comprising:   preprocessing the rock drill cuttings representations by applying at least one transformation to the rock drill cuttings representations;   segmenting the preprocessed rock drill cuttings representations into segmented pictures by inputting the preprocessed rock drill cuttings representations into a first machine learning model that outputs segmented pictures, wherein the segmented pictures are masked images that include at least one rock type; and   predicting depth indexed mineralogical or sedimentological data using the segmented pictures input to a trained second machine learning model.   
     
     
         16 . The system of  claim 15 , wherein the second machine learning model is trained to predict custom categories. 
     
     
         17 . The system of  claim 15 , wherein the first machine learning model is trained to segment and group individual rocks visible in each picture or frame using unsupervised learning. 
     
     
         18 . The system of  claim 15 , wherein the trained second machine learning model is a supervised convolutional neural network. 
     
     
         19 . The system of  claim 15 , wherein the rock drill cuttings representations are a high-definition video of cleaned rock drill cuttings transported on a cuttings belt from shakers. 
     
     
         20 . The system of  claim 15 , wherein the rock drill cuttings representations are images of cleaned rock drill cuttings transported on a cuttings belt from shakers.