NSF Funded research assistant to Professor Lei Wang of Purdue University. Conducting project "Predicting and Interpreting Atmospheric Blocking Using Convolutional Neural Networks and Explainable-AI Techniques". Developing convolutional neural networks with techniques of transfer learning and layer-wise relevance propagation to improve generalization and interpretability. Preliminary model accuracies of 85%, 78%, 75%, and 68%, at 3, 5, 7, and 10 lead days, indicate that the machine learning approach for predicting and explaining atmospheric blocking enhances the accuracy of 7+ day weather forecasts and demonstrates consistency with physical interpretations. Related publication "Predicting and Interpreting Atmospheric Blocking Using Convolutional Neural Networks and Explainable-AI" is in progress, and has been accepted to present a research poster at AMS 2025.

Leader and program ambassador for an undergraduate research team focused on the development of image processing and machine learning algorithms in Python, such as edge detectors, convolutional neural networks, the YOLO architectures, and vision transformers to achieve object detection, classification, and area segmentation in deep learning pipelines involving dataset processing, model training and validation, and evaluation metrics. Worked under the direction and mentorship of Professors Edward Delp, PhD and Carla Zoltowski, PhD.

Completed four data science research projects designed to replicate work performed by previous researchers in the Iyer-Biswas Group (Physics). Projects involved data-driven analysis using Python. Used linear regression, statistical analysis, and sampling algorithms, such as Markov Chain Monte Carlo, to investigate autocatalytic reaction networks and perform microscopic image filtering for analysis of the behavioral and physical interactions within cellular living systems.

Undergraduate research assistant to Professor Lei Wang through the Purdue Summer Undergraduate Research Fellowship (SURF) program. Used knowledge of convolutional neural networks and explainable artificial intelligence techniques to develop machine learning models that predict the early onset of weather phenomena such as atmospheric blocking to enhance forecasting of extreme weather events. Improved extreme weather forecasting tools provide communities an opportunity to prepare in advance and reduce the risk of casualties and property damage. Project selected for a research talk at the 2024 Purdue Summer Research Conference.

As ambassador of Vertically Integrated Projects at Purdue, represent the research program at University events and research workshops, build community among current VIP students, enhance visibility of program with prospective students, develop and implement events and activities, host office hours, increase student success through mentoring, and advise VIP administrators on program improvements.

Invited to participate in an alpha testing program to evaluate new product features.

As a member of the Product and Engineering team, use the AngularJS framework coupled with Java Spring Boot to develop, test, and deploy various micro-service features for a web application product. Collaborate with team members in the Scrum/Agile framework for efficient and productive software development. Presented the developed features at team and departmental meetings.

Developed a visualization tool in Python that displays snow profiles based on accumulated avalanche forecast data from the NWAC (Northwest Avalanche Center), in collaboration with Michael Town, PhD. Users input large raw data sets into the tool, from multiple avalanche forecasts, to determine the stability of snowpack. Goal of the project was to help backcountry travelers evaluate probability of avalanche in specific regions prior to embarking on trips. Tool has been incorporated into Lakeside School's Advanced Physics and Engineering class for annual Snow Science Trip.