Following up on #GeoTorchAI :

With a few minor changes, I managed to run the #STResNet #bicycle flow prediction example of @geotorchai 🥳

The OD matrix size is rather modest (covering a grid with 21x12 cells), but hey, it's a start

https://github.com/anitagraser/GeoTorchAI/blob/f64cea879fdb846a2761b86ddefb5a946357b727/binders/prediction_spatiotemporal.ipynb

#geoai #resnet #torch #gischat #SpatialDataScience

What got me particularly excited about @geotorchai is the mention of applications of #DeepLearning on #spatiotemporal non-imagery datasets, including #MobilityDataScience prediction tasks such as: #TrafficVolume and #TrafficFlow prediction

https://github.com/DataSystemsLab/GeoTorchAI

#GeoTorchAI #GeoAI

#GeoAI library ecosystem for #EO is 🔥

Two important contributions (with unfortunately similar names) to look out for:

1️⃣ #TorchGeo #DeepLearning with #RemoteSensing data
https://github.com/microsoft/torchgeo

2️⃣ @geotorchai (formerly #GeoTorch) #spatiotemporal deep learning framework on top of #PyTorch and @apachesedona for #imagery and non-imagery data
https://github.com/DataSystemsLab/GeoTorchAI

#SpatialDataScience #geospatial #GIScience #EarthObservation #ML #MachineLearning #DataEngineering #GISChat #Sedona #GeoTorchAI