This is the repo for satellite imagery analysis using a deep-learning neural network. The content is part of my new course: Deep Learning Application for Earth Observation
- A short introduction to the Convolution Neural Network (CNN)
- Deep learning training dataset preparation guideline using ArcGIS Pro as well as the open source** method
- Land Use Land Cover Classification (image classification)
- Swimming pool and car detection (object detection)
- Building detection (image segmentation)
- Land Use Land Cover Mapping (mult-class image segmentation)
- Landslide detection using the SAR and Optical dataset
- Time series analysis with LSTM
- End-to-end deep learning with Google Earth Engine (GEE) dataset