Contact Information

  • Eliza Ganguly
    (405) 888-4199


Graduate Student seeking an entry level Data Scientist /Machine Learning Engineer role in Oil and Energy industry. Skilled researcher with 3 years of experience, 4 publications, 2 awards and 1 feature article on implementation of data-driven methods in solving energy-related problems. Proficient in analyzing complex, multi-gigabyte subsurface image/well log/production data to extract valuable insights; automating and optimizing processes, reducing time complexity; facilitating in key decision making; building, training and validating scalable machine learning algorithms to predict trends, conduct forecasts and detect anomalies. Passionate about taking up leadership roles to drive the digital transformation in the energy industry.




Houston, The Woodlands, Sugar Land


Machine Learning Researcher - Chevron Center of Research, Texas A&M University (TAMU), 9/2020 – 5/2021
• Developed a scalable method for lithofacies identification from well log data using unsupervised models (KMeans, Hierarchical
clustering). Assessed model performance using intrinsic metrics like silhouette score, Davies-Bouldin Index, Dunn Index.
• Reduced processing time by 15 minutes per well by building an automated data consolidation workflow to integrate log, well
inventory and surface topography data for approximately 200 wells.

Graduate Research Assistant - Texas A&M University (TAMU), 8/2019 – 8/2020
• Designed 2 novel statistical metrics for quantification of 3-D fluid connectivity during various Enhanced Oil Recovery (EOR) stages
for a dataset of 4050 HI-RES µCT images of carbonate core. The metrics exhibit correlation coefficient >0.8 for all stages.

Graduate Research Assistant - University of Oklahoma, 8/2018 – 8/2019
• Programmed scalable supervised learning models for image segmentation of SEM maps of organic-rich shales into 4 solid
components with an accuracy of ~95%. Evaluated model performance using precision, recall, F1, confusion matrix & ROC curve.
• Engineered 16 features to be extracted from the SEM image data to build a robust model for segmentation (Random Forest).
• Improved the performance of the classification model by 16% by implementing hyperparameter optimization methods.

Research Intern (solar cell) - Indian Institute of Engineering Science & Technology, Shibpur (IIEST), 1/2018 – 4/2018

Awards and Certifications

1. TAMU SPE Machine Learning intermediate challenge (2021) winner.
2. Chevron Center of Research Excellence (CoRE) Fellowship for 2020 – 2021
3. SPWLA Foundation Grant 2020 – grant provided in response to significant contribution to petrophysics


Packages: NumPy, SciPy, Pandas, Matplotlib, Lasio, Zmapio, OpenCV, Scikit-learn, Keras, TensorFlow
Programming/Tools/Software: Python, R, SQL, Weka, Tableau, Petra, Petrel; MS Excel, Word, PowerPoint
Machine Learning: Decision Tree, Gradient Boosting, SVM, Logistic Regression, KNN, K-Means, Neural Network


M.S. in Petroleum Engineering, Texas A&M University, College Station, TX, 5/2021 (GPA: 3.6/4.0)

B.S. in Chemical Engineering, SRM Institute of Science and Technology, India, 6/2018 (GPA: 3.6/4.0)