70 years of machine learning in geoscience in review

Unfortunately, and unlike other areas of research such as computer vision, there is a lack of large publicly-available annotated datasets for seismic interpretation that can be used to train and benchmark machine learning models. To address this problem, some researchers resort to annotating their own training and testing dataset. For example, in the Netherlands F3 block, Zhao, (2018) annotated 40 inlines, Di et al., (2018) annotated 12 inlines, while Rutherford Ildstad and Bormann, (2017) only annotated a single inline for their model. The limited number of annotated sections in understandable given that the annotation process is time-consuming, requires subject matter expertise, and can be quite subjective.

We have seen in the past years the flourishing of machine and deep learning algorithms in several applications such as image classification and segmentation, object detection and recognition, among many others. This was only possible, in part, because datasets like ImageNet -- with +14 million labeled images -- were created and made publicly available, providing researches with a common ground to compare their advances and extend the state-of-the-art. Although we have seen an increasing interest in machine learning in geosciences as well, we will only be able to achieve a significant impact in our community if we collaborate to build such a common basis. This is even more difficult when it comes to the Oil&Gas industry, in which confidentiality and commercial interests often hinder the sharing of datasets with others. In this letter, we present the Penobscot interpretation dataset, our contribution to the development of machine learning in geosciences, more specifically in seismic inte …

Recently, there has been increasing interest in using deep learning techniques for various seismic interpretation tasks. However, unlike shallow machine learning models, deep learning models are often far more complex and can have hundreds of millions of free parameters. This not only means that large amounts of computational resources are needed to train these models, but more critically, they require vast amounts of labeled training data as well. In this work, we show how automatically-generated weak labels can be effectively used to overcome this problem and train powerful deep learning models for labeling seismic structures in large seismic volumes. To achieve this, we automatically generate thousands of weak labels and use them to train a deconvolutional network for labeling fault, salt dome, and chaotic regions within the Netherlands F3 block. Furthermore, we show how modifying the loss function to take into account the weak training labels helps reduce false positives in the lab …

We consider big spatial data, which is typically produced in scientific areas such as geological or seismic interpretation. The spatial data can be produced by observation (e.g. using sensors or soil instrument) or numerical simulation programs and correspond to points that represent a 3D soil cube area. However, errors in signal processing and modeling create some uncertainty, and thus a lack of accuracy in identifying geological or seismic phenomenons. Such uncertainty must be carefully analyzed. To analyze uncertainty, the main solution is to compute a Probability Density Function (PDF) of each point in the spatial cube area. However, computing PDFs on big spatial data can be very time consuming (from several hours to even months on a parallel computer). In this paper, we propose a new solution to efficiently compute such PDFs in parallel using Spark, with three methods: data grouping, machine learning prediction and sampling. We evaluate our solution by extensive experiments on dif …

Unfortunately, and unlike other areas of research such as computer vision, there is a lack of large publicly-available annotated datasets for seismic interpretation that can be used to train and benchmark machine learning models. To address this problem, some researchers resort to annotating their own training and testing dataset. For example, in the Netherlands F3 block, Zhao, (2018) annotated 40 inlines, Di et al., (2018) annotated 12 inlines, while Rutherford Ildstad and Bormann, (2017) only annotated a single inline for their model. The limited number of annotated sections in understandable given that the annotation process is time-consuming, requires subject matter expertise, and can be quite subjective.