Similarity Search is a tool that uses self-supervised learning to locate similar images/data across space and time. It is intended to augment the process of dataset gathering for scientific studies.
Machine-learning
- The geeml Python package makes it easier to extract satellite data from Google Earth Engine using parallel processing and the Google Earth Engine high volume endpoint.
- Transformers have achieved state of the art performance on remote sensing classification datasets and look set to make an impact on other common tasks such as segmentation and object detection.
- Check out this four-part series demonstrating how to use machine learning for detecting changes in land cover. Open source libraries and tools are used for this tutorial.
- Here you can find introductions and Jupyter Notebook examples on how to access Radiant MLHub API.
- This website provides a comprehensive and interactive catalog of reference benchmark datasets. Check it out here.
- The AiTLAS toolbox includes state-of-the-art machine learning methods for exploratory and predictive analysis of satellite imagery as well as repository of AI-ready earth observation datasets.
- This self-paced course contains a mixture of lectures and hands-on exercises for novice data science or remote sensing practitioners.
- Keep in touch with the latest in the ML4EO field and explore the latest tutorials and webinars designed to help you work efficiently with geospatial data and cloud-native practices.
- Check out this workflow demo for generating cropland maps with machine learning and CropHarvest, a global dataset for crop-type classification. Link to end-to-end workflow resources included.
