Name: Pham Minh Quang
Location: Hanoi, Vietnam 🇻🇳
University: UET - VNU Hanoi
Major: Aerospace Engineering
Specialization:
  - Information Technology
  - Avionics Systems
GPA: 3.2/4.0
Status: Final Year Student

🔬 Final Thesis: Advanced Soil Salinity Mapping
🛰️ Technology: CYGNSS Satellite Data + ML
📍 Region: Mekong Delta, Vietnam
📄 Publication: Journal of Science (VNU)

research_areas = {
    "AI_ML": [
        "Deep Learning",
        "Ensemble Methods",
        "Optimization Algorithms"
    ],
    "Remote_Sensing": [
        "CYGNSS Satellite Data",
        "Landsat & Sentinel",
        "Multi-source Integration"
    ],
    "Applications": [
        "Environmental Monitoring",
        "Soil Salinity Mapping",
        "Disaster Risk Assessment"
    ],
    "Tools": [
        "ArcGIS, QGIS, GEE",
        "PyTorch, XGBoost",
        "GeoPandas, Rasterio"
    ]
}

🇬🇧 English: IELTS 7.5 🇻🇳 Vietnamese: Native

📋 Project Overview

A comprehensive framework integrating CYGNSS satellite data with multi-source remote sensing datasets to create high-resolution soil salinity maps for the Mekong Delta region using advanced machine learning algorithms.

🎯 Key Achievements

• ✅ 98% Accuracy with ensemble ML models
• ✅ Processed CYGNSS observations
• ✅ Integrated 15+ environmental variables
• ✅ Validated with field stations
• ✅ Published in Journal of Science (VNU)
• ✅ Generated risk maps

⚙️ Technical Stack

ML: Random Forest, XGBoost, LightGBM, CatBoost
Data: CYGNSS L1/L3,...
Tools: Python, PyTorch, GDAL, Rasterio
GIS: ArcGIS Pro, QGIS, Google Earth Engine

📊 Research Metrics

🔬 Innovation

• CYGNSS-based salinity mapping in Vietnam
• Multi-source data fusion approach
• Real-time prediction capability
• Scalable framework

Objective: Geospatial flood risk assessment using ensemble ML

Highlights:

• 📊 AUC > 0.95
• 🗺️ High-resolution hazard maps
• 🎯 Multi-criteria analysis
• ⚡ Real-time prediction

Tech: Python, RF, XGBoost, QGIS, GEE

Objective: Landslide risk assessment using ML

Highlights:

• 🤖 5+ ML algorithms compared
• 📈 F1-score > 0.8
• 🗺️ Actionable hazard maps
• 📊 Feature importance analysis

Tech: Python, CatBoost, ArcGIS

Objective: Enhanced flood prediction with optimization

Highlights:

• 🔄 ML + GA/PSO/ACO
• 📈 15% accuracy boost
• ⚡ Optimized hyperparameters
• 🎯 Robust predictions

Tech: Python, Genetic Algorithms, PSO

Year: 2023

Year: 2023

• Learned core ML algorithms: Linear Regression, KNN, SVM, Decision Trees
• Data preprocessing & model evaluation
• Hands-on projects using Python & Scikit-learn

Year: 2023

• AI fundamentals & problem-solving techniques
• Basics of Reinforcement Learning
• Implemented AI models through real-world simulations

Achievement: Excellent Academic Performance
Institution: UET - VNU Hanoi

Title: Advanced Soil Salinity Mapping using CYGNSS
Journal: Journal of Science: Earth and Environmental Sciences, VNU
Impact: Environmental monitoring & sustainable agriculture

Achievement: Academic Excellence
Recognition: Consistent high performance

🎯 Responsibilities & Contributions:

• 🌍 Lead Researcher on CYGNSS satellite data processing for soil salinity mapping
• 📊 Collaborated with 5+ researchers on environmental monitoring projects
• 💡 Contributed to 2+ research publications in peer-reviewed journals
• 🛠️ Created interactive visualization dashboards for research insights

🔬 Technical Achievements:

• Processed CYGNSS satellite observations
• Integrated 15+ environmental variables from multiple sources
• Achieved high prediction accuracy with ensemble models
• Validated results with ground truth stations
• Developed scalable framework for real-time predictions

📊 Impact Metrics

Data_Processed:
  CYGNSS
  Auxiliary Data: "Enviromental", "Meteorological",...

Models_Developed:
  Ensemble_ML: "5 algorithms"
  Accuracy: "high"
  Validation: "ground truth stations"

Publications:
  Journal_Papers: 1
  Conference: "In preparation"
  
Time_Saved:
  Automation: "50% reduction"
  Pipeline: "Fully automated"

Collaboration:
  Researchers: "5+ members"