Chapter 1: Data Production/processing
- Large Scale Data Harmonization
Chapter 2: Data Analysis
- Tools NASA FIRMS (HLS applications and dynamic tiling capabilities)
- Interactive HLS notebook for analysis and visualization
Chapter 3: Theory & Application of Geospatial Foundation Model
- Overview of Geo-spatial Foundation Model
- Fine-tune HLS foundation model for specific use-cases:
Chapter 4: Interactive Exploration of Fine-tuned Model
Our lecture will focus on utilizing cloud-based resources to prepare analysis and train and validate machine learning models. Here are some reading materials to get started:
Foundations of Machine Learning:
- Crash Course: Google Machine Learning Crash Course
- A Gentle Introduction to Machine Learning: Towards Data Science Article
Machine Learning for Image-Based Tasks:
- A Simple CNN Model Beginner Guide: Kaggle Tutorial
- Beginner's Guide for Convolutional Neural Network (CNN) - ConvNets: Towards Data Science Article
Image Segmentation:
- Document on Image Segmentation: Fritz AI
Foundation Models:
- Beginner's Guide to Using Foundation Models in ML Projects: Labellerr Blog
- AI Foundations Part 1: Transformers: Fabricated Knowledge Article
Hyperparameter Tuning:
- Parameter Optimization for Machine Learning Models: DataCamp Tutorial
To familiarize yourself with Kubernetes and OpenShift, which we will be leveraging for training, refer to the following resources:
Kubernetes:
- What is Kubernetes: Red Hat
- Introduction to Kubernetes: YouTube Video
OpenShift:
- Definition of Red Hat OpenShift: TechTarget
- Introduction to OpenShift: YouTube Video