Read here about Microsoft's open source machine learning library, that provides datasets, transforms, samplers, and pre-trained models specific to geospatial data.
Archive: Deep-learning
- Learn how to fine-tune Esri's deep learning models (available through ArcGIS Living Atlas of the World) and refine them with your own training data to improve accuracy for your area of interest.
- Introducing a new Python package named geospatial-ml that enables to install commonly used Python packages for geospatial analysis and machine learning with only one command.
- Check out this new method and impressive results of unsupervised semantic segmentation.
- Check here for a deep learning method for building height estimation using high-resolution multi-view imagery over urban areas.
- Satellighte is a Python image classification library with a purpose to establish a light structure to classify satellite images, but to obtain robust results.
- This article explains how to train a segmentation model for classifying the use of cropland, based on a land cover dataset for South America.
- Determine the location of a given street view image by matching it against a collection of geo-tagged satellite images. Read more about it here.
- This workflow generates automatic contours for agricultural parcels, given Sentinel-2 images. It uses Sentinel Hub to download the imagery and a ResUnet-a architecture.
- ESRI has released 10 new pre-trained deep learning models to Living Atlas. These models are available as deep learning packages (DLPKs) that can be used with different ESRI products.
