Skip to content
View hannah-fathi's full-sized avatar
🦋
AI/ML Engineer
🦋
AI/ML Engineer
  • Shiraz university

Block or report hannah-fathi

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
hannah-fathi/README.md

Hi there 👋, I'm Hannah Fathi

M.Sc. Student in Artificial Intelligence and Robotics

Shiraz University


About Me

I am a research-oriented Master's student in Artificial Intelligence and Robotics at Shiraz University, driven by a strong passion for scientific inquiry, reproducible research, and continuous learning.

I ranked 1st among my classmates in Computer Engineering, received the official top-rank certificate, and graduated with a GPA of 18.4/20 (≈ 3.7/4.0).

My work focuses on developing interpretable and practical solutions at the intersection of Computer Vision, Medical AI, Remote Sensing / GeoAI, and Explainable Machine Learning. I am particularly interested in implementing research papers whose official code is not publicly available and in building end-to-end, reproducible pipelines that bridge classical methods with modern deep learning techniques.

During my Bachelor's studies, I fully taught the Operating Systems Laboratory course and prepared the complete course materials. In my Master's program, I serve as a Teaching Assistant for the Artificial Intelligence course, where I design homework assignments and educational content.

I am currently working on two interdisciplinary research papers and preparing my Master's thesis in the field of Remote Sensing.


🔭 Currently Working On

  • Two research papers in Medical Imaging and Construction Risk Management (in preparation)
  • Master's thesis in Remote Sensing / GeoAI

🌱 Research Interests

  • Computer Vision & Medical Image Analysis
  • Remote Sensing & Geospatial Artificial Intelligence (GeoAI)
  • Explainable AI & Interpretable Models
  • Graph Neural Networks & Kernel Methods
  • Fuzzy Systems & Soft Computing
  • Multi-Agent Reinforcement Learning
  • Bioinformatics & Computational Biology
  • Large Language Models

🚀 Featured Projects

Project Description Domain
Attention U-Net for Sentinel-2 Land Cover Segmentation Custom Attention U-Net with spectral indices for agricultural land cover semantic segmentation (mIoU 0.926) Remote Sensing / Deep Learning
Sentinel-2 Unsupervised Land Cover Labeling Explainable unsupervised pseudo-labeling pipeline with Google Earth Engine, spectral features, and ensemble clustering Remote Sensing / Unsupervised Learning
GeoAI Crop Mapping Platform with Satellite Foundation Models End-to-end GeoAI platform using AlphaEarth & Galileo embeddings for crop classification and vegetation analysis GeoAI / Foundation Models
Sliced Wasserstein Graph Kernel for Brain Network Diagnosis Independent reproduction of MICCAI 2023 paper on graph kernels for brain disease classification Medical AI / Graph Learning
Fuzzy Time Series from Scratch Complete from-scratch implementation of First-Order and High-Order Fuzzy Time Series with hierarchical back-off Soft Computing / Forecasting
Kernel Methods and Regularized Learning From-scratch Kernel SVM (CVXOPT), Kernel K-Means, and regularized regression methods Classical Machine Learning
Retinal Vessel Segmentation using Mathematical Morphology Fully interpretable vessel segmentation pipeline implemented from scratch using multi-scale morphological operations Medical Image Processing
Air Combat Multi-Agent Reinforcement Learning Multi-agent RL framework for autonomous decision-making in adversarial air combat scenarios with curriculum learning Reinforcement Learning

🛠️ Tech Stack & Tools

Languages & Frameworks
Python PyTorch TensorFlow / Keras Scikit-learn OpenCV NumPy Pandas

Specialized Domains
Google Earth Engine Remote Sensing GIS Graph Neural Networks Fuzzy Logic Kernel Methods Mathematical Morphology Reinforcement Learning

Others
Jupyter Git LaTeX QGIS


📫 Connect with Me


💬 A Note

I am passionate about conducting rigorous, transparent, and reproducible research.
I enjoy implementing scientific papers from scratch and developing practical AI systems that can be reliably used in real-world settings.

Feel free to explore my repositories — most of them include detailed documentation, experimental results, and complete pipelines.


⭐️ From hannah-fathi

Pinned Loading

  1. attention-unet-sentinel2-landcover-segmentation attention-unet-sentinel2-landcover-segmentation Public

    Deep learning-based semantic segmentation of Sentinel-2 multispectral imagery for agricultural land cover classification. The project uses a custom Attention U-Net with spectral indices (NDVI, NDWI…

    Jupyter Notebook

  2. AI-Teaching-and-Algorithm-Design AI-Teaching-and-Algorithm-Design Public

    Teaching Assistant repository for an undergraduate Artificial Intelligence course (Spring 2025), featuring original assignment and quiz design alongside from-scratch implementations of classical AI…

    Jupyter Notebook

  3. GeoAI-Crop-Mapping-Platform-with-Satellite-Foundation-Models GeoAI-Crop-Mapping-Platform-with-Satellite-Foundation-Models Public

    An end-to-end GeoAI platform for agricultural monitoring using satellite foundation model embeddings, AlphaEarth, Galileo representations, NDVI-based vegetation analysis, and machine learning based…

    Python

  4. sentinel2-unsupervised-landcover-labeling sentinel2-unsupervised-landcover-labeling Public

    An explainable unsupervised labeling pipeline for Sentinel-2 imagery using Google Earth Engine, spectral indices, clustering, and ensemble learning.

    Jupyter Notebook 1