Satellite Image Analysis: A Hands-On Workshop

To equip participants with the skills to apply Vision Transformers (ViTs) to remote-sensing image analysis, focusing on tasks like land cover classification, object detection, climate pattern recognition, and disaster mapping using advanced deep learning methods.

• Introduce Vision Transformers and their application in satellite image analysis

• Enable hands-on experimentation with publicly available geospatial datasets

• Teach model customization and fine-tuning techniques

• Promote responsible AI usage in environmental and humanitarian applications

• Foster interdisciplinary innovation at the intersection of AI and Earth science

• Review of CNN architectures in remote sensing (ResNet, UNet, etc.)
• Introduction to Vision Transformers (ViT): How they work
• Why ViTs are suited for remote-sensing imagery (large context, less inductive bias)
• Comparison: ViT vs CNN in scene classification

• Colab demo using pretrained ViT and CNN for a sample land scene classification task using EuroSAT or BigEarthNet dataset

• Problem of land-cover change detection (LCCD) and its applications (urbanization, deforestation)
• Architectures adapted for temporal change detection (Siamese ViTs, TimeSFormer)
• Pipeline: Preprocessing → Patch Embedding → Transformer Blocks → Classification head

• Visual result comparison (before/after images and heatmaps)

• Challenges of training ViTs with small labeled data
• Strategies: Transfer learning, self-supervised learning (DINO, MAE), adapter layers
• Case studies in remote sensing: Agriculture crop mapping, disaster response

• Colab demo: Fine-tuning a ViT model on a small custom dataset

• Understand the fundamentals of Vision Transformers and how they compare to CNNs

• Process and analyze high-resolution satellite imagery using deep learning

• Train and fine-tune ViTs for various geospatial applications

• Build a portfolio project on remote sensing with ViT-based models

• Receive a certificate demonstrating proficiency in AI + remote sensing

• Geospatial and remote-sensing professionals

• AI/ML engineers and computer vision researchers

• Earth scientists, environmental engineers, and urban planners

• Students and researchers in space science, climate, or deep learning

• Government/NGO professionals working with Earth observation data