• Operated and troubleshooted state of the art astronomy equipment in order to retrieve high quality astronomical research data such as images of galaxies, nebulas, variable stars, and standard fields.• Set up astronomical data processing software on new technology to assist with data reduction and data processing for the interpretation of research data.• Communicated with professors to assist in gathering observational data for their respective research projects.• Wrote a python package and created a custom command line tool to automatically process an entire nights worth of data.

• Created weekly labs for BYU's "Tools for Data Science" course (CS 280) which included data acquisition, workflow management software, machine learning deployment, cloud computing, and data visualization.• Refined curriculum for BYU's "Intro into Data Science" course (CS 180) which included writing Colab notebooks for students to write data visualization code and to become familiar with popular data science packages such as pandas.•Wrote midterms to assist in evaluating student's knowledge that they've gained throughout the courses. • Tutored students in data science related material and taught them concepts such as gradient descent, clustering analysis with k-means, and traditional data exploration techniques.• Graded student labs in BYU's "Computer Vision" course (CS 450). Material graded included hough transform, segmentation, homographies, image stitching, and deep learning.

• Presented poster at the 53rd Lunar and Planetary Science Conference on super resolution and gave a talk at the 55th Lunar and Planetary Science Conference on synthetically generated craters.• Developed a dataset of craters to train a diffusion model to create new images of craters that don't exist for the purpose of understanding "Crater Space".• Created a system using SOTA deep learning and computer vision algorithms to de-speckle and super-resolve synthetic aperture radar (SAR) on other planetary surfaces with an emphasis on Titan. Results were presented at LPSC in 2022.• Wrote a classification neural network using PyTorch to determine if a satellite image has fluvial or desert geomorphologies. The resultant accuracy of the model was 91%.• Wrote an algorithm that uses Meta's Segment Anything Model to automatically segment bacteria in an unsupervised fashion.• Performed an extensive literary review on the state of the art computer vision algorithms, and brainstormed ways to use those algorithms to enhance astronomy and planetary science imagery.

• Polished and redesigned the terrain generation system to allow for new modulation in the terrain generation code.• Added a system to create dynamically sized 3D craters based on a gaussian distribution for each of the parameters.• Created the preliminary terrain textures for the Lunar surface through using Unity's shader graph.

• Wrote C# scripts to control the user interface, switch between rovers, and rotate the moon.• Created the title screen; responsible for UI design, programming, and 3D graphics. • Implemented a system to generate 3D generated terrain with data obtained from the LRO’s digital elevation map of the Moon. The system includes chunk generation, parallel processing, mesh generation, and image processing.• Designed a local terrain system to generate rocks and craters from a study conducted by JPL on the lunar surface.

• Lead a group of 12 students in writing a 7 page research grant proposal for LSpace's NWPEE Academy.• Developed the concept for an algorithm that would be used for training rovers using reinforcement learning by developing synthetic terrain based on satellite imagery of a planet's surface.• Researched current state of the art techniques for image segmentation, and computer vision systems for robotic object detection.

• Researched and selected various instruments to be implemented in the MAGMA rover in order to research and survey Martian caves.• Developed the science subsystem using block diagrams and N^2 diagrams for the functionality and communication between the various instruments.• Selected a scientifically interesting landing site the using JMars software and satellite imagery from the Mars Reconnaissance Orbiter.• Obtained the requirements, risk-management, project-management, systems, heat-transfer, and siemans-nx skill badges.

• Developed ETL systems to regularly fetch product information from platform apis which was then stored it in a data warehouse for future use.• Constructed a robust image match system to detect copyright images provided by the brand.• Designed a dynamic web scraping bot to simulate real customers behavior through the use of graph theory.• Produced an automated data verification script that alerts developers for any inconsistencies inside of the production database.