Courses taught at Penn State

CE 497: Introduction to AI/ML for Civil & Environmental Engineering & Water

This course offers a comprehensive introduction to Artificial Intelligence (AI) and Machine Learning (ML), equipping future engineers and scientists with cutting-edge AI/ML skills, preparing them for advanced AI tasks and making them proficient in solving complex problems with AI models. It bridges fundamental principles of ML with domain-relevant examples taken from Civil and Environmental Engineering and Geosciences, providing students with the skills necessary to train and run AI/ML models in their respective fields. By the end of the course, students will be familiar with AI model concepts and the usefulness of AI and ML models in their domains and industries. They will be exposed to handson coding exercises, model training, benchmarking and finetuning. The content related to statistics and maths is limited. For those unfamiliar with Python, the first few sessions of the course will include exercises on Python and PyTorch, a popular ML library in Python. AI algorithms to be covered include regularized linear regression, regression trees and random forest, boosting, convolutional and recurrent neural networks, unsupervised learning, generative models, and the effective use of generative AIs for AI model training. 

Graduate students or undergraduate students seeking deeper understanding of AI are highly recommended to take a companion one-credit course, CE 597 Mathematical and Research Aspects of AI/ML for Engineering & Sciences, which seek to build a stronger mathematical foundation and discuss physics-informed ML and other research-related topics.

Deep Learning for the Earth Sciences book cover, https://m.media-amazon.com/images/I/71yGcjOGRFL.jpg

CE 597: Mathematical and Research Aspects of AI/ML for Civil and Environmental Engineering and Geosciences (1 credit)

This advanced course delves into the mathematical foundations and research applications of Artificial Intelligence (AI) and Machine Learning (ML) for engineers and scientists. Designed for graduate students and advanced undergraduates seeking a deeper understanding of AI, this course builds on the concepts introduced in the companion course, CE 497 Introduction to AI/ML for Engineering & Sciences. Students without significant ML experiences are required to take the companion course concurrently. By the end of the course, students will have developed a robust mathematical understanding of AI/ML, gained experience with cutting-edge research techniques, and enhanced their ability to use and modify AI models in their research work.

Students will explore the advanced mathematics behind ML algorithms, including covariance, the chain rule, likelihood and operations in the latent space. The course covers critical topics such as the PyTorch Autograd engine, and the mathematical aspects of neural networks, including feedforward, recurrent, and convolutional neural networks, and ML model interpretation. In addition to the theoretical foundation, students will engage in research discussion related to physics-informed ML, review recent literature, and deliver a semester project, which can replace some of the unit exercises in the companion CE 497 course.

Flooded water around structure, https://www.usgs.gov/media/images/flooding-baraboo-river-wisconsin-june-2008

Long-term pavement performance figure, https://www.fhwa.dot.gov/publications/research/infrastructure/pavements/ltpp/15018/images/fig01.jpg

CE 461: Water Resources Engineering

Qualitative and quantitative description of the hydrologic cycle, flood and drought frequency analysis, climate and land use change impacts, risk analysis and uncertainty, water resource management at regional, national and global scale. This course studies hydrology from an engineering perspective, building students' analytical abilities of water resources problems using systematic approaches, describing practical ways of calculating rainfall, runoff, fluid flow, surface and subsurface water movement.

Text books:
Mays, Water Resources Engineering (Required)
Beven, K., Rainfall Runoff Modeling: The Primer (2012) (Optional)

An extra credit option is offered as a bonus to those who are interested in learning more about hydrology and watershed hydrologic modeling. Together we will go through the process of applying an advanced off-the-shelf hydrologic model to a watershed of interest. Practical GIS skills will also be learned during the process. This option will be a very rewarding experience in terms of both enhancing competitiveness and preparing for further studies.

 

Mays Water Resources Engineering Beven

 

CE 555: Groundwater Hydrology

Introduction to groundwater resource analysis, model formulation, simulation, and design of water resource systems using symbolic and numerical methods. I intend for this course to assist you in developing a qualitative and quantitative understanding of using mathematical models to evaluate groundwater resources in complex hydrologic settings. I want you to gain a theoretical foundation as well as practical hands-on experiences. You will learn Matlab skills, elements of finite difference methods and graphical/interactive groundwater modeling software.

Text books:
Freeze, R.A. and Cherry, J. A., Groundwater, Prentice Hall, Inc., 1979. (Required)
Marsily, Ghislain de., Quantitative hydrogeology: groundwater hydrology for engineers, 1986 (Optional)

Freeze de Marsily

CE 360: Fluid Mechanics

The course objective is to provide students with the fundamental physical and analytical principles of fluid mechanics through the understanding of the: conservation of mass, conservation of energy, and the conservation of momentum equations. The student will demonstrate the understanding of these fundamentals by solving problems dealing with: fluid properties, fluid statics, pressure on plane and curved surfaces, buoyancy and floatation, kinematics, systems, control volumes, conservation principles, ideal imcompressible flow, impulse-momentum, and flow of a real fluid.

Fluid mechanics is a prerequisite to all courses in hydrosystems and environmental engineering. It is typically offered fall and spring semesters and during summer session. A series of homework problems are assigned after each lecture and there are typically 3 examinations given during the semester and final examination during the final examination period.

Young