Biostratigraphy is the dating of rocks with the help of fossils. The make-up of any given biostratigraphic sample varies with the age and geography of the sample. In the oil and gas industry this is carried out by examining microfossils such as pollen, spores, algae, and marine plankton through a microscope.
Since the early 1900?s the study of microfossil has been done manually, identifying and counting the microfossils in each rock sample. This is a time-consuming work that requires a high degree of skill, where a single person only can analyse a handful of samples per day. Recent advances in pathology has enabled tissue samples to be scanned into a digital image and analysed by an Artificial Intelligence (AI) to help improve the identification of damaged or diseased cells. This project aims to adapt and improve these techniques for use in biostratigraphy. This requires high resolution 3D-scanning, development of AI image recognition and machine learning to accurately identify and count microfossils, in different orientations. By analysing the same samples both in a microscope and the scanned sample on a screen and by comparing the results we aim to determine if the resolution of the scanned samples is detailed enough for analysis of the same quality as analysis in a microscope.
The AI software is anticipated to contain 4 core modules, namely data processing, learning, object extraction and inspection. The learning module will expectably consists of few models, with possibilities for the end user to switch between models and to manage and evaluate data produced from learning experiments and predictions.
Biostratigraphy, using fossils to date rocks, is obligatory for all exploration wells drilled in the offshore Norwegian Sector. It is used to help understand the sub-surface geology and to correlate sections in wells both within fields and on a larger regional scale. Although biostratigraphic data was part of the digital revolution in the industry of the 1980’s, the actual study of the microfossils with a microscope and prepared glass slides has changed very little in the past decades.
By using image digitalisation and Artificial Intelligence a technique can be developed to scan microscope slides into a digital high-resolution image and an AI software specifically developed for this usage will find, identify and quantify the fossil content. With this new analysis method, we believe that we can not only decrease the time used for analyses but also obtaining data at a more statistically accurate level and mitigate human inconsistencies and biases.
With 3-dimentional microfossils that need to be identified in a 2-dimentional view, based on several morphological parameters, the image recognition software needs to identify fossils from different angles, poorly preserved and fragmented fossils, as well as partially hidden or folded fossils. A species can also have a morphological range and evolution. This morphological and evolutionary complexity is the base for the research needed to develop the AI software.
Within this project we intend to establish if the digital scans of the biostratigraphical samples have the resolution needed to be used for quantitative analyses, we will also develop a sample preparation process to reliably produce the best digital samples possible. We will then design and develop an Artificial intelligence software for clustering and classification of microfossils based on deep-learning based algorithms for detection and segmentation of microfossils and algorithms based on autoencoders for extracting features predictive of different fossil types.
