Machine Learning

Intuitively predicting data using most popular machine learning algorithms, no coding needed

Robust workflow implemented by machine learning experts

Besides Regression model and Classification model, non-linear regression method and Self-Organizing Map (SOM) are also supported. This is a nonlinear approach to model the relationship between the input curves and the target curve. The relationships are modeled using nonlinear predictor functions, so called nonlinear models, whose unknown model parameters are estimated from the data. Self-organizing Map is a unique tool for facies classification by both supervised and unsupervised modes. The tool provides a robust workflow from model construction to model validation which is critical to make sure the output brings actual geological meaning. Emsemble Boosting SOM and Distributed Ensemble SOM algorithms are also two supported algorithms which provides more options to deal with a wide range of geological complexities.

Various machine learning methods to deal with different geological complexities

I2G supports both regression and classification methods ranging from Decision Tree to Artificial Neural Network. Our supporting Classification methods include:
•   Decision Tree Classification
•   KNN Classification
•   Logistic Classification
•   Neural Network Classification
•   Random Forest Classification
Here is the list of supporting regression methods:
•   Decision Tree Regression
•   Huber Regression
•   Lasso Regression
•   Linear Regression
•   Neural Network Regression
•   Random Forest Regression
•   SVM Regression
•   Xgboost Regression

Flexibility in configuring model inputs and architectures

I2G machine learning toolkit is such open for user to adjust many advanced parameters that the user has full control on model configuration. This is to avoid using i2G as a “black box”. For the user who is new to machine learning, default parameters are set to have reasonably good values to start with.