In the fast-growing digital world, our mission is to assist subsurface scientists and engineers to develop their automation skills in innovative ways.
You will learn Python programming from the initial steps to automate geo-challenges.
What specifically more?
To handle structured datasets, Pandas provides a rich capability for data manipulation, preparation, reading, and writing a data file. Plenty of easy-to-remember functions would help a user to be as productive in Pandas as they can be in Excel. Dataframes can be easily converted to other formats that users would prefer.
You will learn to use the SciPy and Numpy library for numerical computations. Numpy can handle datasets from one to higher dimensions. Arrays are much faster in the Machine Learning process than other formats.
You can visualize the data using the matplotlib package in both 2D and 3D. Handling big size data and reproducibility are two noticeable capabilities of this library compared to Microsoft Excel. Seaborn is also an important plotting package in python for statistical data visualization.
Machine Learning is a hot topic in all sectors. Using the scikit-learn library, you will implement almost all steps of the ML process as well as common ML algorithms. For deep learning, Artificial Neural Network, TensorFlow will be used to predict target variables.
Python is a popular programming language, easy to learn, has a readable code structure, and comes with a lot of powerful libraries. This course is designed for geoscientists and subsurface engineers to get familiar with python programming from basic to intermediate level. Unlike other Python training courses, the learners will be exposed to real and common geoscientific examples. By the end of this course, you will be able to read well logs and seismic data, implement some basic computation, and visualize the result.
Recommended duration: 3 days
Geoscientists can develop computer models/algorithms that improve estimation accuracy automatically through the experience. These applications are working iteratively to minimize error function. When it comes to complicated and non-linear problems, Machine Learning can provide appropriate solutions. In this course, both supervised and unsupervised learning will be covered for both regression and classification problems.
Recommended duration: 3 days
Deep learning neural network is a branch of Machine Learning that uses algorithms inspired by the structure and function of the human brain. In this course, you will be introduced to the artificial neural network (ANN) basic concepts, the current applications of ANN, and how to use the TensorFlow library for supervised deep learning. You will work to estimate both regression and multi-class classification geoscience problems.
Recommended duration: 2-3 days
The path that learners came through the courses can lead to a productive project. The Capstone project can be designed based on your team's interest. There will no specific topic to be taught. Data Energy will accompany learners to come up with a standard format that can be accessible in the project time frame. We will be there in all steps to get your final work done in a professional manner.
Recommended duration: 1-2 days