Rasha Alsahwi Headshot

Rasha Alshawi

Assistant Professor

Full-Time Faculty

Biography

Rasha Alshawi is an assistant professor in the MS in Data Science program at the University of San Francisco, specializing in deep learning and computer vision. Her research focuses on using AI to automate the inspection and monitoring of underground infrastructure, helping detect issues early and improve the safety and efficiency of maintenance. She has contributed to projects with the U.S. Army Corps of Engineers, applying deep learning to enhance the inspection of floodwater control structures. Passionate about using AI to solve real-world problems, Rasha is also committed to mentoring the next generation of computer scientists. Outside of her academic work, she enjoys charcoal drawing and spending time in nature.

Expertise

  • Semantic segmentation

  • Deep learning model development

  • Dataset curation and annotation

  • Infrastructure monitoring technologies

  • Transformer-based NLP models

Research Areas

  • Machine learning
  • Computer vision
  • Natural language processing and named entity recognition
  • AI applications in public safety and urban planning

Education

  • PhD, Engineering and Applied Science, University of New Orleans, 2025
  • MS, Information Technology, Middle Technical University, 2017

Prior Experience

  • Research Assistant, Gulf States Center for Environmental Informatics, University of New Orleans (2023–2025)
  • Teaching Assistant, University of New Orleans (2022–2023)
  • Research Assistant, University of New Orleans and Arizona State University (2022)

Selected Publications

  • Alshawi, Rasha. (2025) DAU-Net: A Dual-Attentive U-Net for Enhanced Semantic Segmentation in Underground Infrastructure Inspection. IEEE Sensors Journal.

  • Alshawi, Rasha. (2024) Imbalance-Aware Culvert-Sewer Defect Segmentation Using an Enhanced Feature Pyramid Network. IEEE Transactions on Systems, Man and Cybernetics.

  • Alshawi, Rasha. (2024) SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

  • Alshawi, Rasha (3rd). (2024) Deep Learning Based Fault Detection Method in DC Motor Start. IEEE Power Engineering Letters.

  • Alshawi, Rasha. (2023) Depth-Wise Separable U-Net Architecture with Multiscale Filters to Detect Sinkholes. Remote Sensing (MDPI).