Machine Learning Toolkit
Intuitively predicting data using most popular machine learning algorithms, no coding needed
Quickly build models with intuitive workflow interface
i2G machine learning toolkit is customized for petroleum geoscientists working with wellbore data. The adjustable workflow interface makes it easy-to-use and save time for users. It does not require deep knowledge of machine learning as well as any coding skill.
Various machine learning methods to deal with different geological complexities
The Toolkit provides a wide range of regression and classification methods from linear/non-linear regression to more complex algorithms of Artificial Neural Network and Random Forest. They have been proven in successfully dealing with various G&G challenges from data correction, missing logs prediction to rock type classification and so on.
Easily sharing your trained model without sharing your data
The i2G machine learning projects have full access to data from multiple working projects for different fields/blocks, creating a unique way to share information from the data but the data itself. This helps independent consultants and service companies, who own a large amount of data, to be able to transfer "knowledge" from one project to another without violating data confidentiality.
Built-in evaluation metrics for minimizing model uncertainties
Evaluation of training model is greatly supported by available metrics such as convergence plot and confusion matrix. This essential step increases the reliability of prediction results by avoiding being overfitting.
Easily eliminate unwanted input data due to strong filtering capability
The user has full control over which input data to feed into the training, validation and prediction by using a set of discriminators and/or zone constraint. This helps to filter out irrelevant input data such as bad hole intervals and/or unusual lithologies.
© 2023. Revotech International. All Rights Reserved