Ammar Riyadh

Experience

• 

  The University of British Columbia

  Jan 2019 - Apr 2019

  Math and Science Tutor

  •Assisted freshmen students in introductory math and science courses and delivered concepts and theories clearly and comprehensively.• Strategically presented content that is specified towards the student's level and way of thinking

• 

  The University of British Columbia

  Aug 2019 - Sept 2019

  Orientation Leader

  - Assigned to help freshmen students to adjust and familiarize with the University’s campus- Addressed questions/inquiries about campus life and University academics

• 

  Ballard Power Systems

  Sept 2021 - May 2022

  Stack Test Engineer

  • Built fuel cell stacks using company hardware and manufactured cell membranes for performance testing. Stack building demands meticulous hands-on application to ensure a specific alignment of cell membranes to avoid hazardous chemical leakage during testing procedures.• Conducted numerous data analysis reports using modified Excel data crunchers, demonstrating performance, input demand, and resistivity against the baseline model.• Developed strategic troubleshooting procedures to resolve station and software malfunctions that often resulted in testing delays and would require attention to detail as fuel cell stations are programmed on scrutinized safety protocols.• Collaborated in a multi-disciplinary engineering environment to execute a wide variety of fuel cell testing that induced overcoming equipment limitations and exploring unexpected results.• Produced weekly PowerPoint presentations entailing test procedures and a complete analysis of test results which were then presented to the team and clients. Show less

• 

  The University of British Columbia

  Jan 2024 - now

  •Conducted H&H analyses by designing and implementing a comprehensive hydraulic model using EPANET and ArcGIS for water systems, focusing on water quality evaluations, pumping and storage assessments, and optimizing chlorine management.•Employed Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, showcasing their enhancedability to incorporate temporal information and predict chlorine decay. •Investigated the factors influencing chlorine decay in water distribution systems using advanced machine learning methodologiesand explainable AI (XAI) techniques.• Demonstrated the impact of optimal sensor placement on predictive accuracy, advocating for a data-focused approach over asensor-dense strategy. •Enhanced the interpretability and reliability of ML models, providing actionable insights for water management professionals.• Designed a Bench Scale Pipe Loop System with different pipe materials to study the distinct change of water quality in distribution systems • Utilizing differential UV absorbance to investigate NOM characterization and potential Disinfection-By-Product formation• Analyzing potential microbial regrowth in distribution systems at dead end mains and contamination scenarios. Show less • Organizing events and initiatives to encourage intellectual and social collaboration.• Empowerment through networking opportunities, conferences, and workshops.• Strong commitment to making a tangible difference in the student community.• Mission to cultivate a sense of belonging and a dynamic, supportive university community.• Pivotal role in shaping the graduate experience at our university.• In-depth understanding of the needs and aspirations of the student body.• Focus on amplifying student engagement and fostering inclusivity. Show less

  • Masters of Applied Science - Research Assistant

    May 2023 - now

  • Student at Large Representative - SUO Graduate Student Committee

    Jan 2024 - Jul 2024
• 

  KWR Water Research Institute

  Jun 2024 - now

  Water Infrastructure / Hydro informatics Intern

  • Conducted statistical data analysis and applied Amazon’s DeepAR model for machine learning to predict tomato plant performance over the next 12 hours, identifying the most influential water quality parameters affecting growth.• Developed, calibrated, and maintained hydraulic models to support KWR network TUBES, improving water management and forecast accuracy for hydraulic parameters• Utilized computer vision and image processing to develop ML models that analyze microscope photographs of biofilms in transparent pipes, identifying key parameters describing biofilm variation under different flow conditions.• Assisting in the development of a digital twin of the TUBES network by supporting data acquisition, and developing ML models for predicting water quality and hydraulic parameters.• Implementing transfer learning techniques to adapt ML models for full-scale distribution systems, addressingdifferences between simulated environments and actual network conditions.• Participating in regular meetings with the supervisory team, reflecting on the potential transposition of developed models to real-life DWDS scenarios for Smart Water Futures, and gained experience in handling experimental data of drinking water distribution systems. Show less