Curriculum Vitae

Expert in reliability assessment, machine learning, infrastructure analytics, and software development with a proven track record of dissecting real-world datasets, crafting innovative solutions, and collaborating with interdisciplinary teams.

Download CV (PDF)

Education

Ph.D. in Civil and Environmental Engineering
Aug 2017 - Aug 2024
Rice University, Houston, TX
  • Research: Developed computational methods for infrastructure reliability and resilience assessment
  • Leveraged network science, dynamic programming, machine learning, deep learning, and Monte Carlo methods to improve risk assessment accuracy and efficiency
  • Created dynamic programming algorithms that reduced analysis time by over 3 orders of magnitude
B.Tech. and M.Tech. in Civil Engineering
Jul 2009 - Jun 2014
Indian Institute of Technology, Bombay

Leadership Experience

  • President, GradGames | Board and video games club (2020-2021)
  • Director of Programming, Indian Students At Rice | Cultural club (2019-2020)
  • Vice President, Earthquake Engineering Research Institute, Rice U. chapter | Professional society (2018-2019)
  • President, Avanti Fellows, IIT Bombay chapter | Non-profit for equitable access to education (2012-2013)

Technical Skills

Coding

  • Python
  • SQL
  • MATLAB
  • Bash
  • Git

Machine Learning

  • Scikit-learn
  • Keras & TensorFlow
  • Pandas
  • Computer Vision
  • XGBoost
  • CatBoost

Data Visualization

  • Matplotlib
  • Seaborn
  • Tableau
  • Plotly
  • D3.js

Cloud Computing

  • Microsoft Azure
  • Amazon Web Services (AWS)

Certifications

  • Microsoft Certified Azure Data Scientist Associate
  • Google Data Analytics Professional Certificate
  • Coursera Specializations: Deep Learning, Applied Software Engineering Fundamentals, Machine Learning Engineering for Production (MLOps)
  • Coursera Courses: Electric Industry Operations and Markets, Oil & Gas Industry Operations and Markets

Professional Experience

Research Scientist I
Aug 2024 - Present
Rice University, Houston, TX
  • Lead research projects to develop computational methods for infrastructure reliability assessment
  • Developed dynamic programming algorithms for radial infrastructure reliability assessment
Graduate Research Assistant
Aug 2017 - Aug 2024
Rice University, Houston, TX
  • Created synthetic electric grid models for risk, reliability, and resilience assessment
  • Developed dynamic programming techniques for infrastructure reliability analysis
  • Published research in several high impact journals with 150+ citations to date
Teaching Assistant
Aug 2020 - Dec 2020, Jan 2023 - Apr 2023
Rice University, Houston, TX
  • Courses: Risk-based Decision-making Under Uncertainty and Time-dependent System Reliability Methods
  • Led tutorials & designed assignments on risk quantification, probabilistic decision-making, and system reliability
  • Enhanced student engagement by integrating board games into coursework, including the use of Power Grid for network reliability assignments and Ticket to Ride for risk-based decision-making under uncertainty
Project Research Associate
May 2016 - Jun 2017
IIT Bombay, Mumbai, India
  • Contributed to structural steel design software (Osdag) for Indian design standards
  • Established best practices for version control, unit testing, coding standards, and documentation
  • Implemented features using PyQt5, PythonOCC, and sqlite3
  • Created cross-platform installation software for Linux and Windows using conda, bash, and NSIS
  • Supported outreach activities by creating tutorials and conducting workshops for academia and industry
Graduate Engineer (Structural)
Jul 2014 - Apr 2016
Walter P Moore
  • Engineered structural elements in the New Orleans International Airport – North Terminal Expansion
  • Created software tools for the analysis and optimal design of atypical components in the project
  • Analyzed wind tunnel test results and performed wind drift analysis of airport concourses
  • Developed Microsoft Excel spreadsheets for analysis and design using Visual Basic for Applications

Research Projects

Dynamic Programming for Assessing Reliability of Radial Infrastructure
Oct 2023 - Mar 2024
  • Engineered a dynamic programming approach to assess the reliability of radial infrastructure systems
  • Demonstrated the method's efficacy using real-world and synthetic infrastructure system models
  • Achieved a computational time reduction by about 1000x compared to Monte Carlo methods
Assessing Equity in Electric Power Outages
Oct 2022 - Oct 2023
  • Examined inequity in electric power outages at the block group level in a major US county
  • Utilized webscraping to gather data, and investigated disparities in outage metrics against economic and socio-demographic factors through correlation analysis, Gini coefficient, and equity gap analysis
  • Employed SQLite, pandas, sklearn, GitHub Actions, and geopandas for continous webscraping and analysis
  • Identified a significant correlation where higher income level blocks were associated with low outage metrics
Synthetic Models of Power Grid using Network Science & Computer Vision
May 2021 - Aug 2023
  • Created parametric power transmission network models using network analysis and equivalencing techniques
  • Detected utility poles from street view imagery using a Mask-RCNN model, achieving a precision of 0.77, surpassing the state-of-the-art RetinaNet-101's precision of 0.73
  • Applied Prim's algorithm to establish connectivity between utility poles forming minimum spanning trees
  • Deployed models for assessing power availability in Lumberton, North Carolina and Galveston Island, Texas
CNN and CAE based Sensor Fault Detection, Localization, and Correction
Aug 2019 - Dec 2021
  • Developed a Convolutional Neural Network model for sensor fault detection and classification, and specialized Convolutional Autoencoder models for reconstructing faulty sensor data across various fault types
  • Utilized TensorFlow, Google Colab, and Talos for model training and automated hyperparameter optimization
  • Achieved state-of-the-art accuracy of 98.7% in detection, 100% in localization, and 99% in reconstruction
  • Published research in Mechanical Systems and Signal Processing journal with 150+ citations to date
Reliability of Wind Turbine Systems with Multi-State Components
Aug 2020 - Sep 2021
  • Developed closed-form expressions for reliability and risk of wind turbine systems with multi-state components
  • Reduced computational cost by about 1000x in comparison to principled Monte Carlo methods by casting the closed-form expressions in a recursive formulation
NLP and LDA for Analyzing Abstracts of Successful NSF Grants
May 2019 - Jun 2019
  • Processed and analyzed text from successful NSF grant proposals to uncover emerging research trends
  • Leveraged natural language processing, Latent Dirichlet Allocation, and topic modeling to identify key themes
  • Findings were used to direct literature reviews and future grant applications in research group
Instance Segmentation of Nuclei in Biomedical Images
Jan 2018 - Apr 2018
  • Applied image processing & deep learning to identify & segment individual nuclei in diverse biomedical images
  • Created novel features to train deep learning models utilizing image processing strategies such as pixel intensity thresholding, gradient-based edge detection algorithms, and watershed segmentation
  • Assembled an ensemble of U-Net models that performed well even for edge cases
ML informed Stratified Sampling for Estimating Two-Terminal Reliability
Aug 2017 - Dec 2017
  • Developed a novel stratified sampling method to estimate two-terminal reliability in power networks
  • Achieved dimensionality reduction by ranking edges according to variable predictor importance
  • Employed AdaBoost with decision trees to identify key edges based on their impact on network reliability
  • Significantly reduced the number of simulations required for convergence, outperforming traditional methods such as naïve stratified sampling, antithetic variates, and Latin hypercube sampling

Publications

  1. Patil, J. & Dueñas-Osorio, L. (In Preparation). "Recursive technique for efficient computation of functional reliability of radial infrastructure systems."
  2. Patil, J., Lin, C.Y., Cha, E.J., & Dueñas-Osorio, L. (Under Review). "Integrating Synthetic Power Flow and Computer Vision Models for Assessing Building-Level Outages."
  3. Herkal, S., Patil, J., & Dueñas-Osorio, L. (Under Review). Closed-form reliability and risk assessment for the upkeep of multi-component and multi-state wind turbine systems.
  4. Nofal, O., Rosenheim, N., Kameshwar, S., Patil, J., Zhou, X., van de Lindt, J. W., ... & Wang, C. (2025). "Methodology for Interdependent Population–Building–Infrastructure Posthazard Functionality Assessment for Communities." Journal of Structural Engineering, 151(5), 04025048.
  5. Nofal, O., Rosenheim, N., Kameshwar, S., Patil, J., Zhou, X., van de Lindt, J. W., ... & Jeon, H. (2024). "Community‐level post‐hazard functionality methodology for buildings exposed to floods." Computer-Aided Civil and Infrastructure Engineering.
  6. Nofal, O., Rosenheim, N., Patil, J., Zhou, X., Kameshwar, S., van de Lindt, J. W., & Duenas-Osorio, L. (2023). "Community-level approach for a socio-physical flood post-hazard functionality assessment." In ASCE Inspire 2023 (pp. 339-348).
  7. Jana, D., Patil, J., Herkal, S., Nagarajaiah, S., & Duenas-Osorio, L. (2022). "CNN and Convolutional Autoencoder (CAE) based real-time sensor fault detection, localization, and correction." Mechanical Systems and Signal Processing, 169, 108723.
  8. Nofal, O., Rosenheim, N., Patil, J., Zhou, X., van de Lindt, J. W., Duenas-Osorio, L., & Cha, E. J. (2022). "Interdependent Households-Buildings-Networks Community-Level Post-Hazard Functionality Assessment Methodology." Proceedings of the 8th International Symposium on Reliability Engineering and Risk Management (ISRERM 2022), Hanover, Germany.
  9. Birchfield, A. B., Patil, J., Paredes, R., & Dueñas-Osorio, L. (2021, April). "Preliminary Analysis of Network Fragility and Resilience in Large Electric Grids." In 2021 IEEE Power and Energy Conference at Illinois (PECI) (pp. 1-6). IEEE.
Let's Connect