Krishna Panthi light_mode dark_mode

Clemson, SC 29631, USA

I'm a MS student in Computer Science at Clemson University. I have a deep passion for problem-solving. Here at Clemson, I've worked in variety of topics including reinforcement learning, time series predictions and diffusion models. Previously I was a software developer at MutualArt. Prior to that I received BE in Computer Engineering from Pulchowk Campus, Tribhuvan University.

Occasionally, I enjoy playing tennis, working out, hiking and making people laugh.

Reach me out at

💼 Experience

  • Developed AquaCrop-Richards, a new crop simulation model that integrates the Richards equation into AquaCrop. Implemented a numerical solver for 1-D Richards Equation. It was solved using finite difference method and modified Picard iteration. I also implemented Anderson Acceleration to make it converge in fewer Picard iterations.
  • Implemented deep reinforcement learning methods (PPO, DQN, SLBO) to optimize irrigation to obtain maximum profit using the AquaCrop-Richards as the learning environment.
  • Contribute to implement HydroQuantum Python library to do quantumm machine learning on hydrology related data. The associated paper has been published to Environment Modeling and Software.
  • Took lead to create teaching materials that were presented in WaterSoftHack 2025 workshop.
  • Developed internal tools for marketing and sales. The work involved developing web applications and background processes. Also implmented algorithms for matching the users with the appropriate consignments.
  • Implemented tools to track emails using pixel tracking.
  • Containerized multiple pre-built applications for faster deployment.
  • Got experience with multitude of technologies such as AWS, GraphQL, Mixpanel, .NET, Vue.js, Vuetify, etc.
  • Involved in development of PensionPro web. Worked as a full stack developer to migrate features from PensionPro desktop application to PensionPro web application.
  • Worked to build frontend components with Angular and it's material design framework.
  • On the backend side developed API endpoints and optimized stored procedures.

🎓 Education

Documents

Latest Projects

Quality of Life Analysis in San Antonio
This project represents a collaborative effort between the Better Future Institute (BFI) of San Antonio and Clemson University. The primary dataset consisted of 311 non-emergency service requests collected over a 14-month period, which was provided to the research team. This dataset was subsequently enriched with demographic and socio-economic data for San Antonio, sourced from the U.S. Census Bureau, to facilitate a comprehensive analysis.
Gaussian Shading With EDICT
This research implements Exact Diffusion Inversion via Coupled Transformation (EDICT) with the Gaussian Shading watermarking technique in diffusion models. The results show a slight improvement in the performance of Gaussian Shading. The implementation is tested on manipulated images after watermarking, and results in the table below shows better performance for most image manipulation methods, except for ColorJitter and Salt & Pepper Noise. For more details, please refer to our paper.

Latest Essays

We are very special!
This one morning I woke up and suddenly realized how special we are!