Day 1: EO Data & AI/ML Fundamentals

Building the foundation for AI-powered Earth Observation

Date

November 17, 2025

Day 1: EO Data & AI/ML Fundamentals

Earth Observation Data, AI/ML Fundamentals & Geospatial Python

Building the essential skills for AI-powered satellite data analysis

Day 1 Overview

Welcome to Day 1 of the CoPhil EO AI/ML Training Programme! Today you’ll build a solid foundation in Earth Observation data and AI/ML fundamentals. By the end of the day, you’ll understand Copernicus missions, Philippine EO resources, and be ready to start building AI models.

NoteWhat You’ll Learn Today

This day provides the foundation for your AI/ML journey in Earth Observation. You’ll gain both theoretical understanding and hands-on experience with the tools and data that power modern EO applications.

Learning Objectives

By the end of Day 1, you will be able to:

  • Identify the characteristics and applications of Sentinel-1 and Sentinel-2 missions
  • Navigate Philippine EO platforms including PhilSA SIYASAT, NAMRIA Geoportal, and DOST-ASTI tools
  • Explain the AI/ML workflow for Earth Observation applications
  • Distinguish between supervised and unsupervised learning with EO examples
  • Understand neural network fundamentals and data-centric AI principles
  • Load and visualize vector data using GeoPandas
  • Read and process raster imagery using Rasterio
  • Query and filter satellite imagery collections in Google Earth Engine
  • Apply cloud masking and create temporal composites
  • Export processed EO data for AI/ML workflows

Today’s Schedule

Time Session Topic Materials
09:00-11:00 1 Copernicus Sentinel Data & PH EO Ecosystem Presentation, Demos
11:00-13:00 2 Core Concepts of AI/ML for EO Presentation, Case Studies
14:00-16:00 3 Hands-on Python for Geospatial Data Notebook 1
16:00-18:00 4 Introduction to Google Earth Engine Notebook 2

Training Sessions

Session 1

Copernicus Sentinel Data & Philippine EO Ecosystem

Learn about Europe’s flagship EO program and the Philippine agencies advancing EO in the country.

Go to Session 1

Session 2

Core Concepts of AI/ML for Earth Observation

Demystify AI/ML workflows, supervised vs unsupervised learning, neural networks, and data-centric approaches.

Go to Session 2

Session 3

Hands-on Python for Geospatial Data

Completed 2 hours

Master vector data with GeoPandas and raster data with Rasterio - the foundations of EO data processing.

Go to Session 3

Session 4

Introduction to Google Earth Engine

Completed 2 hours

Leverage cloud computing power to access, filter, and preprocess petabytes of Earth observation data.

Go to Session 4

Prerequisites

What You Need

Before starting Day 1:

Technical Setup:

All exercises run in Google Colaboratory - no local installation required! See our Setup Guide for detailed instructions.

Hands-on Notebooks

TipInteractive Learning

Day 1 includes two comprehensive Jupyter notebooks that you’ll work through during Sessions 3 and 4:

Both notebooks run in Google Colab with all dependencies pre-configured.

2025 Updates Highlighted

This training incorporates the latest 2025 developments in Earth Observation and AI:

  • Sentinel-2C operational (January 2025) - Three-satellite constellation with 5-day revisit
  • Sentinel-1C active - Restored dual-satellite SAR coverage
  • Copernicus Data Space Ecosystem - New data access platform with SentiBoard dashboard
  • PhilSA SIYASAT portal - Secure data archive for NovaSAR-1 and maritime monitoring
  • DOST P2.6B AI investment (until 2028) - SkAI-Pinas, DIMER, AIPI platforms
  • ESA Φsat-2 mission - On-board AI processing demonstration
  • NASA-IBM Geospatial Foundation Model - Open-source pre-trained model for EO
  • Data-centric AI paradigm - Emphasis on data quality over model complexity

What’s Next?

After completing Day 1, you’ll have the foundational knowledge to move to:

Day 2: Machine Learning for Earth Observation - Where you’ll apply supervised and unsupervised learning algorithms to real satellite imagery for land cover classification and change detection.


Need Help?

Throughout Day 1, you can:

ImportantTechnical Support

For technical issues during the training:

  • Google Colab issues: Check Setup Guide
  • Data access problems: See session-specific troubleshooting sections
  • General questions: Contact your instructors or teaching assistants

Day 1 is part of the CoPhil 4-Day Advanced Training on AI/ML for Earth Observation, funded by the European Union under the Global Gateway initiative and delivered in partnership with PhilSA and DOST.