Metrics Of Models Evaluation for The Predictive Log Data and Vital Role of Machine Learning

Abstract

Traditional methods of measuring well logs are expensive, error-prone and time-consuming, which has led to the development of machine learning models that can predict well logging based on well-log data. This study aims to determine the most effective   metrics of model evaluation for predictive log by machine learning models for predicting of well logging based on available well-log data. The study covers a detailed explanation of the data-gathering and pre-processing techniques used.

 trained and evaluated based on their performance, namely linear regression, support vector machine (SVM), Neural Network (NN) and decision Trees (DT) models. The models were evaluated based on their Mean Squared Error, R squared, Mean Absolute Error and RMSE values, confusion matrix and ROC. Our results showed that the Decision Trees (DT) for MSE value of 10.86, achieving (RMSE) value of 3.29, (MAE) value of 2.225 and (R square) value of 0.92. These findings suggest that machine learning models can be a powerful tool for predicting of best training from well-log data, in particular, holds great promise for future modelling efforts in this area.