2024 ASEE Annual Conference & Exposition

Courses based on experiential learning provide an excellent avenue to promote problem-solving and collaborative skills among the students in STEM. However, the current engineering curriculum does not have sufficient project-based learning emphasizing collaborative research on renewable energy to support the government’s goal of Net Zero emissions by 2050. So, we plan to develop and implement a project-based learning course to model and analyze renewable energy systems using machine learning methods. The course will be offered in modules covering several supervised and unsupervised machine learning algorithms. Moreover, video lectures and tutorials will be provided for analysis and evaluation of data sets of various technologies with computational tools for each machine learning model. This experiential learning experience will cater to our diverse student population of veterans and underrepresented groups (In 2019, Hispanic were 37% and Black were 26.9% at Houston Engineering Center). The proposed plan is designed to engage students in ways that have been shown to increase retention of students in STEM fields, therefore, the program will also help increase the number of and diversity of graduates fully prepared to pursue careers in engineering.
Project outcomes are to (1) develop and implement effective machine learning instructional, and training modules for sustainability projects using experiential learning, (2) promote a data-driven approach to solving engineering problems for complex problems in science and engineering, and (3) train future leaders on topics related to sustainability. Moreover, the modules will become readily accessible to other students and faculty at the university, and other global academic institutions. The students will be provided the qualitative and quantitative data collected from the experiments to analyze using the machine learning modules prepared by the instructor for the class. These modules will enable students to acquire the relevant knowledge and skills for data-driven modeling. Various program assessment tools will be used, including pre-and post-course Likert-based quantitative surveys completed by students to measure the success of the project.