Through collaborative engagement and deep industry experience, Enthought builds tailored, results-driven solutions in the language of energy. Together, we deliver faster ways to reach critical insights and decisions via data and analytics.
Enthought brings together scientific understanding with computational excellence. With our cross functional expertise, we can solve problems more effectively and holistically to achieve better business outcomes.
Unlocking the potential of deep learning in seismic interpretation starts with data – the ability to categorize, model and manage it quickly and consistently. Further, geophysicists need to be highly efficient at producing labeled data to train deep learning models to deliver high quality interpretations in a fraction of the time it typically takes. Enthought’s Subsurface AI Seismic brings this to life. With as few as three interpreted seismic lines, the pattern recognition-based deep learning models enable you to create robust predictions across the entire seismic volume.
Frac operations are rich with potentially valuable data. However, integrating it and using it to improve performance can be challenging. Enthought scientists’ oilfield domain expertise, analytical software development and infrastructure skills, enable collaboration to identify the opportunities and develop the right software technologies.
Core and Thin Sections
The full capabilities of today’s machine learning are now available for thin section image interpretation. With the VirtualCore custom deep learning application, geoscientists can easily label, annotate, and interpret a small subset of the thin section data. Customized artificial intelligence and machine learning models learn from the geoscientist, providing suggestions and analyzing the entire image.
10X Efficiency Gain and Improved Classification Using Deep Learning
Use AI techniques to efficiently extract mineralogy and grain size statistics from thin sections Thin sections provide the closest examination of in situ rock properties,…
Integrating Weather and Renewable Energy Sources Data for 2.5 Million Viewers
Educating and developing a culture of responsible energy consumption The EnergizAIR project is presented both to show the innovative technology and methodology to solve the…
Manual Processes for CSEM Replaced by Computational Tools and Strategies
Shell needed a way to effectively visualize a new scientific measurement Controlled-Source Electromagnetic sounding (CSEM) is a new tool for marine oil exploration. Sensitive electric…
Predicting Pore Pressure From Very Limited Data Sets
ConocoPhilips wanted to make pore pressure predictions with limited data sets Logs from two wells and a limited set of 2D and 3D seismic were…
AI/Machine Learning Techniques Quantify AVA Seismic Analysis Uncertainty
Help ConocoPhillips apply advanced AI techniques to Amplitude Versus Angle (AVA), seismic analysis Amplitude Versus Angle (AVA), seismic analysis is a well-established oil exploration tool….
Model-Based Approach to Rock Physics Improves Predictions
ConocoPhillips wanted a more flexible way to model rock physics An important activity in characterizing reservoirs is constructing models of rock physics, which represent how…
Applying Machine Learning to Subsurface Data Reduces Uncertainty
Overcome slow and tedious nature of core analysis Core analysis provides ground truth data of rock properties, and can be time consuming and expensive to…
Digital Transformation in Practice
For digital leaders who will share a practical framework for digital transformation options, and how to avoid common pitfalls. Gain insights into: Making key strategic…
Get More From Your Core
What: Presentation, demo, and Q&A with Brendon Hall, Energy Solutions Group, Enthought Oil and gas industry professionals who are looking for ways to extract more…
Accelerating Seismic Interpretation with Machine Learning
Determine if AI and machine learning techniques can be used to more efficiently analyze seismic volumes Seismic is the first field measurement in the oil…
Case Study: 10X Efficiency Gain and Improved Classification Using Deep Learning
Modern microscopes generate high-resolution images of thin sections at multiple polarization angles. These gigapixel images provide a massive dataset of texture and color features that can be used to extract mineralogy and grain size statistics— but the size of this data makes it impossible to assimilate manually.
The Enthought team was challenged to create an AI-based assistant that gives petrophysicists the ability to quickly visualize and analyze hundreds of thin section images. Here's how we did it.