01DVJNW

A.A. 2022/23

2022/23

Data science and machine learning for engineering applications

This course explores how new algorithms in the Data Science (DS), Machine Learning (ML), and Deep Learning (DL) disciplines can help engineering applications become smarter. These emerging disciplines could play a significant role and substantially impact various sectors. Thus, they could lead to new opportunities to develop cutting-edge and unconventional engineering applications. The course focuses on designing and implementing data-driven processes to extract knowledge from data and support decision-making. The course first introduces the data science process, focusing on its main phases. It then provides a theoretical and practical understanding of data mining and machine learning algorithms commonly used to analyze large and heterogeneous data in engineering scenarios. The course also introduces the Python language and state-of-the-art data mining and machine learning libraries to design and develop machine learning-based applications. Many laboratory sessions, based on a learning-by-doing approach, allow experimental activities on all the phases of a standard data science process - data preparation and cleaning, data exploration and characterization, machine learning algorithm selection and tuning, result assessment - using the most widespread open-source tools and libraries.

Data science and machine learning for engineering applications/Reservoir geomechanics (Reservoir Geomechanics)

The course provides the fundamentals of rock behaviour in relation to field operations in reservoirs. The main objective of the course is to teach students: 1) how rocks respond to the modification of the underground state of stress in relation to oil and gas production and gas storage 2) the models and methods used to solve practical problems. To reach this objective the following subjects are explained during the course: fundamentals of continuum mechanics, the role of fluids in rock behaviour, drained and undrained conditions, interpretation of laboratory tests, elasto-plastic models for predicting rock behaviour and methods of analysis for evaluating rock failure in oil and gas reservoirs.

Data science and machine learning for engineering applications

This course explores how new algorithms in the Data Science (DS), Machine Learning (ML), and Deep Learning (DL) disciplines can help engineering applications become smarter. These emerging disciplines could play a significant role and substantially impact various sectors. Thus, they could lead to new opportunities to develop cutting-edge and unconventional engineering applications. The course focuses on designing and implementing data-driven processes to extract knowledge from data and support decision-making. The course first introduces the data science process, focusing on its main phases. It then provides a theoretical and practical understanding of data mining and machine learning algorithms commonly used to analyze large and heterogeneous data in engineering scenarios. The course also introduces the Python language and state-of-the-art data mining and machine learning libraries to design and develop machine learning-based applications. Many laboratory sessions, based on a learning-by-doing approach, allow experimental activities on all the phases of a standard data science process - data preparation and cleaning, data exploration and characterization, machine learning algorithm selection and tuning, result assessment - using the most widespread open-source tools and libraries.

Data science and machine learning for engineering applications/Reservoir geomechanics (Reservoir Geomechanics)

The course provides the fundamentals of rock behaviour in relation to field operations. The main objective of the course is to teach students: 1) how rocks respond to the modification of the underground state of stress in relation to oil and gas production and storage 2) the models and methods used to solve practical problems. To reach this objective the following subjects are explained during the course: fundamentals of continuum mechanics, the role of fluids in rock behaviour, drained and undrained conditions, interpretation of laboratory tests, elasto-plastic models for predicting rock behaviour and methods of stability analysis for evaluating rock failure in oil and gas reservoirs. The subject is linked to resources geology, geophysical exploration and monitoring, reservoir modeling.

Data science and machine learning for engineering applications

• Knowledge of the main phases characterizing a data science and machine learning process for a real-life engineering application. • Knowledge of the major data mining algorithms for classification, regression, clustering, and association rule mining. • Knowledge of the major machine learning and deep learning algorithms. • Knowledge of the Python language. • Knowledge of the major data mining and machine learning libraries. • Ability to design, implement and evaluate a data science process. • Ability to design, implement and evaluate a machine learning and deep learning algorithm. • Ability to use and tune data mining and machine learning algorithms. • Students will acquire all the above abilities by exploiting state-of-the-art machine learning algorithms in engineering applications.

Data science and machine learning for engineering applications/Reservoir geomechanics (Reservoir Geomechanics)

Upon completion of the course, the student should be able to: 1) Identify the appropriate rock mechanical properties and select the tests necessary to characterize the rock material with reference to a given field problem; 2) Predict the hydro-mechanical response of porous rocks in field operations; 3) Solve practical problems: wellbore stability, hydraulic fracturing, stress change induced by reservoir production and gas injection.

Data science and machine learning for engineering applications

• Knowledge of the main phases characterizing a data science and machine learning process for a real-life engineering application. • Knowledge of the major data mining algorithms for classification, regression, clustering, and association rule mining. • Knowledge of the major machine learning and deep learning algorithms. • Knowledge of the Python language. • Knowledge of the major data mining and machine learning libraries. • Ability to design, implement and evaluate a data science process. • Ability to design, implement and evaluate a machine learning and deep learning algorithm. • Ability to use and tune data mining and machine learning algorithms. • Students will acquire all the above abilities by exploiting state-of-the-art machine learning algorithms in engineering applications.

Upon completion of the course, the student should be able to: 1) Identify the appropriate rock mechanical properties and select the tests necessary to characterize the rock material with reference to a given field problem; 2) Predict the hydro-mechanical response of porous rocks in field operations; 3) Solve practical problems: wellbore stability, hydraulic fracturing, stress change induced by reservoir production and gas injection.

Data science and machine learning for engineering applications

Basic programming skills.

The student must know the fundamental principles of Linear Algebra, Physics I, and Resources Geology

Data science and machine learning for engineering applications

Basic programming skills.

The student must know the fundamental principles of Linear Algebra (matrix calculus), Physics I (Particle dynamics; Dynamics of a rigid body, Mechanics of fluids) and Resources Geology (all the program)

Data science and machine learning for engineering applications

• Data science process: main phases (0.2 cfu) • Data collection, cleaning, transformation and enrichment, and feature engineering (0.3 cfu) • Data mining algorithms: classification and clustering (0.8 cfu) • Machine learning and deep learning algorithms (0.6 cfu) • Introduction to Python and data mining and machine learning libraries (e.g., scikit-learn) (1.0 cfu) • Case study analysis (0.6 cfu) • Design in the lab of data science process and machine learning and deep learning algorithms for engineering applications (2.5 cfu)

1) Continuum mechanics. >The state of stress and strain >Constitutive laws: Theory of elasticity and plasticity; Creep 2) Failure mechanics: Mohr-Coulomb, Hoek & Brown, Griffith, Jaeger strength criteria 3) Mechanical properties of rocks from lab tests 4) Elements of Critical state Soil Mechanics. Modified Cam Clay Model 5) In situ state of stress: geostatic and in fault regime 6) Compaction and subsidence of reservoirs during depletion 7) Stresses around boreholes. Stability during drilling: geomechanical aspects 8) Principles of hydraulic fracturing 9) Stress change during gas storage 9) Stress change during gas storage

Data science and machine learning for engineering applications

• Data science process: main phases (0.2 cfu) • Data collection, cleaning, transformation and enrichment, and feature engineering (0.3 cfu) • Data mining algorithms: classification and clustering (0.8 cfu) • Machine learning and deep learning algorithms (0.6 cfu) • Introduction to Python and data mining and machine learning libraries (e.g., scikit-learn) (1.0 cfu) • Case study analysis (0.6 cfu) • Design in the lab of data science process and machine learning and deep learning algorithms for engineering applications (2.5 cfu)

1) Continuum mechanics. >The state of stress and strain >Constitutive laws: Theory of elasticity and plasticity; Creep 2) Failure mechanics: Mohr-Coulomb, Hoek & Brown, Griffith, Jaeger strength criteria 3) Mechanical properties of rocks from lab tests 4) Elements of Critical state Soil Mechanics. Modified Cam Clay Model 5) In situ state of stress: geostatic and in fault regime 6) Compaction and subsidence of reservoirs during depletion 7) Stresses around boreholes. Stability during drilling: geomechanical aspects 8) Principles of hydraulic fracturing 9) Stress change during gas storage 9) Stress change during gas storage

Data science and machine learning for engineering applications

Data science and machine learning for engineering applications

Data science and machine learning for engineering applications

The course includes lectures and practices on the course topics, particularly on data science process design, data preprocessing, and machine learning and deep learning algorithms (3.5 CFU). The course includes laboratory sessions on the data science processes and machine learning algorithms for engineering applications (2.5 CFU). Laboratory sessions allow experimental activities on the most widespread tools and libraries. Students will prepare a written report on a group project assigned during the course and discuss it with the professor.

The course is organized in theoretical and practical lessons. During the practical lessons the students have to solve exercises by applying the theory explained in lectures. The interpretation of lab tests and the solution of practical problems are developed in the Informatic Lab

Data science and machine learning for engineering applications

The course includes lectures and practices on the course topics, particularly on data science process design, data preprocessing, and machine learning and deep learning algorithms (3.5 CFU). The course includes laboratory sessions on the data science processes and machine learning algorithms for engineering applications (2.5 CFU). Laboratory sessions allow experimental activities on the most widespread tools and libraries. Students will prepare a written report on a group project assigned during the course and discuss it with the professor.

The course is organized in theoretical and practical lessons. During the practical lessons the students have to solve exercises by applying the theory explained in lectures. The interpretation of lab tests and the solution of practical problems are developed in the Informatic Lab

Data science and machine learning for engineering applications

Copies of the slides used during the lectures, examples of written exams and exercises, and manuals for the activities in the laboratory will be made available. All teaching material is downloadable from the course website or the teaching Portal. Book (only a few chapters needed) - Tan, Steinbach and Karpatne, Kumar; 'Introduction to data mining', 2 ed., Pearson, 2019 - Bellini, Alessandro and Guidi, Andrea; ‘Python e machine learning’, McGraw-Hill Education, 2022

Reference Books: Fjaer, Holt, Horsrud, Raaen & Risnes, Petroleum related Rock Mechanics, 2nd edition, Elsevier, Oxford, 2008. Brady & Brown Rock Mechanics, 3rd edition, Kluwer Academic Publisher, Dordrecht, 2004 Lancellotta, 2009. Geotechnical Engineering, 2nd edition, Taylor & Francis, New York The slides presented during lectures will be periodically uploaded on the web site of the course.

Data science and machine learning for engineering applications

Copies of the slides used during the lectures, examples of written exams and exercises, and manuals for the activities in the laboratory will be made available. All teaching material is downloadable from the course website or the teaching Portal. Book (only a few chapters needed) - Tan, Steinbach and Karpatne, Kumar; 'Introduction to data mining', 2 ed., Pearson, 2019 - Bellini, Alessandro and Guidi, Andrea; ‘Python e machine learning’, McGraw-Hill Education, 2022

Reference Books: Fjaer, Holt, Horsrud, Raaen & Risnes, Petroleum related Rock Mechanics, 2nd edition, Elsevier, Oxford, 2008. Brady & Brown Rock Mechanics, 3rd edition, Kluwer Academic Publisher, Dordrecht, 2004 Lancellotta, 2009. Geotechnical Engineering, 2nd edition, Taylor & Francis, New York The slides presented during lectures will be periodically uploaded on the web site of the course.

Data science and machine learning for engineering applications

**Modalità di esame:** Elaborato progettuale in gruppo; Prova scritta in aula tramite PC con l'utilizzo della piattaforma di ateneo;

**Modalità di esame:** Prova orale obbligatoria;

Data science and machine learning for engineering applications

**Exam:** Group project; Computer-based written test in class using POLITO platform;

**Exam:** Compulsory oral exam;

Data science and machine learning for engineering applications

Gli studenti e le studentesse con disabilità o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unità Special Needs, al fine di permettere al/la docente la declinazione più idonea in riferimento alla specifica tipologia di esame.

Data science and machine learning for engineering applications

**Exam:** Group project; Computer-based written test in class using POLITO platform;

**Exam:** Compulsory oral exam;

Data science and machine learning for engineering applications

The exam includes a group project and a written part. The final score is defined by considering both the evaluation of the group project and the written part. The teacher may request an integrative test to confirm the obtained evaluation. Learning objectives assessment The written part will assess - the knowledge of the data preparation techniques and the major data mining algorithms for classification, regression, clustering, and association rule mining. - the knowledge of the machine learning and deep learning for engineering applications. The group project will assess - the ability to design, implement and evaluate a complete data science process, including the evaluation and tuning of machine learning algorithms and result assessment for a specific engineering application. - the working knowledge of the Python language and the major data mining and machine learning libraries. Exam structure and grading criteria The group project consists in designing and implementing a data science process, based on machine learning algorithms, for solving a data analytics task related to a specific engineering application. The project is assigned after 6 weeks of lectures. The evaluation of the group project is based on the performance and accuracy of the proposed solution, in terms of standard quality measures (e.g., prediction accuracy), and completeness (i.e., in depth analysis of each phase of the designed process and motivation for selecting given techniques and algorithms). The written part covers the theoretical part of the course. It includes multiple choice and box-to-fill questions related to the theoretical part of the course (data cleaning, data pre-processing, data mining algorithms, data science process, machine learning and deep learning algorithms). For multiple choice questions, wrong answers are penalized. The score of each question will be specified in the exam text. The written exam lasts 60 minutes. Textbooks, notes, electronic devices of any kind are not allowed. The maximum grade for the group project is 20. The maximum grade for the written part is 12. The final grade is given by the sum of the two parts. The exam is passed if the grade of the group project is greater than or equal to 10, the grade of the written part is greater than or equal to 8, and the overall grade is greater than or equal to 18. If the final score is strictly greater than 31 the registered score will be 30 with honor.

Compulsory oral exam. The exam is aimed at evaluating knowledge, competences and skills acquired during the course. The student should be able to carry out stability analyses, to select strength parameters and to evaluate the effect of water pressure in a given case. The exam will be oral in a classroom of the Politecnico di Torino. A calendar will be published on the course page after the term for exam enrollment and every day a group of students will give the exam. The oral exam comprises 3 main questions. Questions are related to the topics explained in class. Questions consist of discussion of a given topic and/or the solution of a practical exercise. Rules during oral exam: >closed book; >the equation sheet provided in the course material is allowed; >pocket calculator and pen; >the student must show his/her identity document

In addition to the message sent by the online system, students with disabilities or Specific Learning Disorders (SLD) are invited to directly inform the professor in charge of the course about the special arrangements for the exam that have been agreed with the Special Needs Unit. The professor has to be informed at least one week before the beginning of the examination session in order to provide students with the most suitable arrangements for each specific type of exam.

© Politecnico di Torino

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY