Course & Workshop

October 22-26, 2023

Instructor: Dr. Amir Ismael, Ph.D.

Who Should Attend

The course is designed for geologists, geophysicists and reservoir engineers and exploration development staff.

Course Content

1. Introduction
   1.1. What are big data, data analytics, and machine learning?
   1.2. History of ML.
   1.3. Types of data analytics
   1.4. Geoscience database (Numerical and Non-numerical data types).
   1.5. Scales, resolutions, and Integration of common geologic data.

   2. A brief review of statistical measures.

   2.1. Random variable.
   2.2. Common types of geologic data analysis.
   2.2.1. Univariate analysis
   2.2.2. Bivariate analysis
   2.2.3. Time series analysis
   2.2.4. Spatial analysis
   2.2.5. Multivariate analysis.

   3. Basic steps in ML-based modeling

   3.1. Identification of the problem.
   3.2. Learning Approaches.
   3.2.1. Supervised learning
   3.2.2. Unsupervised learning
   3.2.3. Semi-supervised learning.
   3.2.4. Reinforcement Learning.

   4. Data Pre-processing

   5. Data labeling and ML-based modeling

   5.1. Data splitting and model training.
   5.2. Model Validation and testing.
   5.3. Model evaluation.

   6. A brief review of popular ML algorithms in geosciences.

   6.1. K-means clustering.
   6.2. Regression (linear and logistic) (K-Nearest Neighbor (KNN)).
   6.3. Terminologies used in Regression and Classification problems.
   6.4. Principal Component Analysis (PCA).
   6.5. Ensemble classification models (Support vector machine (SVM)).
   6.6. Decision tree.
   6.7. Random forest.
   6.8. Artificial neural networks.
   6.8.1. Shallow ANN.
   6.8.2. Deep ANN.
   6.9. Convolutional neural network.

   7. Applications of ML in subsurface geosciences (Examples and case study)

   7.1. Outlier detection.
   7.2. Petrophysical log analysis.
   7.3. Fracture classification.
   7.4. Seismic data analysis
   7.5. Use of seismic attributes in ML applications.
   7.6. Use of seismic inversion in ML applications.
   7.7. ML for seismic facies clustering and classification.
   7.8. Fault classification.
   7.9. Seismic-based rock property prediction.
   7.10. Machine learning tools and software.

Location

First day will be held at the Holiday Inn Maadi Hotel, in Cairo. The participants will fly the next day to Hurghada. The course will be continued in Hurghada.

Course Fees

Inclusive of refreshment and lunch at the Holiday Inn Maadi Hotel. Air Ticket Cairo/Hurghada return and accommodation in Hurghada.

Instructor Profile

DR. A. ISMAIL

has obtained his Ph.D. in 2020 from Helwan University. He is EREX Consultant for Seismic Interpretation and Modeling. His work involved using Neural Network Technique and Seismic Attributes for prospect identification. He is a faculty advisor and supervisor of the AAPG (American Association of Petroleum Geologists). He published tens of papers in reputable magazines and societies.

RECENT CONFERENCE ABSTRACTS:

1. Gammaldi, S., Ismail, A. and Zollo, A., 2022. The updated multi-2D image of the gas accumulation zone inferred by seismic attributes and AVO analysis at the Solfatara Volcano, Italy (No. EGU22-11885). Copernicus Meetings.

2. Khalil, A., Nawawy, M., Ismail, A., 2021. Shallow Offshore Seabottom Geotechnical Modeling Using One Channel Acoustic Streamer at Kuala Sanglang, Perlis, Peninsular Malaysia. In The Arab Conference on Astronomy and Geophysics (ID. 197).

3. Gammaldi, S., Ismail, A., Chiuso, T. and Zollo, A., 2020, May. The multi-2D seismic imaging of the Solfatara Volcano, Italy, inferred by seismic attributes. In EGU General Assembly Conference Abstracts (p. 16478).

4. Ismail, A., Ewida, H. F., Al-Ibiary, M. G., Gammaldi, S., & Zollo, A., 2019. Neural network technique and seismic attributes, west offshore Nile Delta, Egypt. Petroleum Geology Student Contest – 3rd edition, Calvello, Italy 2019. doi: 10.3301/ABSGI.2019.06