Skip to content
View DesislavaLebessis's full-sized avatar
  • München

Highlights

  • Pro

Block or report DesislavaLebessis

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DesislavaLebessis/README.md

Hi, I'm Desislava

Data Scientist | AI & Sustainability | Citizen Scientist

I work at the intersection of machine learning, climate data analysis, and responsible AI. I combine self-directed learning with hands-on projects, from stellar light curves to geothermal climate anomalies.


Featured Projects

Automated classification of pulsating variable stars using deep learning (ResNet18 + Transfer Learning). F1-Score: 0.802 | PyTorch | Transfer Learning | Astronomy

As a volunteer citizen scientist at Zooniverse / SuperWASP I manually classify stellar light curves. This project automates that process using machine learning.

A 75-year climate anomaly study of a geothermally active region in Bulgaria (1950-2024) using ERA5 reanalysis data. pandas | scipy | matplotlib | Open-Meteo API

The research question: does geothermal activity produce measurable, persistent climate differences over 75 years? The answer is yes, with statistically stable results over the entire observation period.


Skills and Tools

Languages: Python

ML and Data: PyTorch, scikit-learn, pandas, NumPy, matplotlib, Jupyter

Domains: Time Series Analysis, Computer Vision, NLP and LLMs, Bayesian Statistics

Sustainability and AI: Energy-Efficient AI, Environmental Impact of AI Systems, AI Ethics and Bias


Selected Certifications

Certificate Provider
Google Data Analytics Professional Certificate Coursera / Google
Efficient AI for Weather Forecasting openHPI
Practical Computer Vision with PyTorch openHPI
Time Series Analysis openHPI
Quantum Machine Learning (with IBM Quantum) openHPI
Introduction to Bayesian Data Analysis openHPI
Energy-Efficient Software Development openHPI
Environmental Impacts of AI Systems openHPI
AI Bias - Understanding and Mitigation openHPI
Sustainability Reporting Greenomy / Position Green

About Me

I am a student of Economics at FernUniversitat in Hagen, Germany. As a volunteer citizen scientist at Zooniverse / SuperWASP I classify stellar light curves. I am passionate about AI for sustainability and responsible, energy-efficient AI. I am a self-taught data scientist who builds real projects with real data.


Connect

LinkedIn GitHub

Pinned Loading

  1. superwasp-pulsator-detection superwasp-pulsator-detection Public

    Machine Learning model for automatic pulsator detection in SuperWASP light curves. F1-Score 0.802

    Jupyter Notebook 1