Remote Sensing | Truong Tuan Nghia

Pursuing Three Master's Programs Simultaneously

Sat, 01 Mar 2025 00:00:00 +0000

Why Three Programs?

When I graduated with a BSc in Data Science from USTH in 2025, I realized that my research interests lie at the intersection of multiple fields:

AI & IoT (HUST) — to dive deep into AI applications in biomedicine, specifically antimicrobial resistance prediction
Space Sciences (USTH) — to continue Earth Observation research, a field I started during my internship at VNSC
Teaching Methodology of Informatics (HNUE) — to teach and share knowledge effectively

Each program complements the others: AI is the tool, Space is the application, Teaching is how I share.

Time Management

Principles

Prioritize the nearest deadline
Leverage overlap between courses (e.g., ML assignments at HUST can use satellite data from USTH)
Start thesis research early, don’t wait until the final year

Tools

Notion — task and deadline management
Google Calendar — class and meeting schedules
Git/GitHub — code and research document management

Advice

If you’re considering multiple programs simultaneously:

Ensure the programs complement each other
Talk to your advisors at each program beforehand
Be prepared to sacrifice leisure time
Find ways to share research outputs across programs

SAR Remote Sensing: From Theory to Deforestation Detection

Fri, 01 Dec 2023 00:00:00 +0000

What is SAR Remote Sensing?

SAR (Synthetic Aperture Radar) is a remote sensing technology that uses radar waves instead of visible light. Its biggest advantage: it works day and night, through clouds.

This is particularly important in Vietnam — where cloud cover is nearly year-round, making optical imagery (Landsat, Sentinel-2) often unusable.

The Two Satellites I Used

Sentinel-1 (ESA)

C-band (5.4 GHz)
Revisit cycle: 6 days
Free and open data
Good for rapid change monitoring

ALOS-2 (JAXA)

L-band (1.2 GHz)
Better canopy penetration → sensitive to forest structure
Revisit cycle: 14 days
Paid data (but available for research)

Methodology

Data acquisition — download SAR images from Copernicus Hub (Sentinel-1) and JAXA (ALOS-2)
Preprocessing — radiometric calibration, speckle filtering, geocoding (using SNAP)
Change analysis — multi-temporal comparison, change index calculation
Classification — identify deforested areas using thresholds and dual-band combination
Validation — compare with ground truth and optical imagery

Results

Combining both satellites (C-band + L-band) yielded significantly better results than using either alone:

L-band (ALOS-2) is sensitive to major structural changes in forests
C-band (Sentinel-1) adds information about surface-level changes

Results were published at the GIS-IDEAS 2023 conference.

Tools to Get Started

If you want to start with SAR remote sensing:

SNAP (ESA) — free SAR image processing software
QGIS — open-source GIS
Python + snappy — processing automation
Google Earth Engine — cloud processing (free for research)

A Combination of ALOS-2, Sentinel-1 Imagery for Rapid Deforestation Detection in Vietnam

Wed, 01 Nov 2023 00:00:00 +0000

Rapid Deforestation Detection Using ALOS-2 and Sentinel-1 SAR Imagery

Mon, 01 May 2023 00:00:00 +0000

Overview

Research project at the Vietnam National Space Center (VNSC), Earth Observation Application Department. Goal: use satellite radar imagery (SAR) to rapidly detect deforested areas in Vietnam.

I participated as an intern (05/2023 – 11/2023).

My Contributions

Studied fundamentals of Earth Science and Geophysics
Practiced SAR (Synthetic Aperture Radar) image processing
Combined data from two satellites: ALOS-2 (JAXA) and Sentinel-1 (ESA)
Analyzed forest cover changes over time

Tech Stack

SNAP (ESA) — SAR image processing
QGIS — spatial analysis, visualization
Python — data processing

Results

Co-authored a paper at the international GIS-IDEAS 2023 conference:

“A Combination of ALOS-2, Sentinel-1 Imagery for Rapid Deforestation Detection in Vietnam”

Ngo Duc Anh, Vu Anh Tuan, Truong Tuan Nghia