Special Issue on the Best Papers from the 2022 ACM SIGSPATIAL Conference

is in the context of deep learning over remotely sensed geospatial data.The challenge is in the large variance in data collection methods and the handling of geospatial metadata that make the application of deep learning methodology to remotely sensed data nontrivial.The introduced TorchGeo Python library integrates geospatial data into the PyTorch deep learning ecosystem.In addition to being open-source, one big advantage of TorchGeo is that it provides pre-trained models for satellite imagery and hence allowing for transfer learning on downstream remote sensing tasks with limited labeled data.The second article, titled "Urban Traffic Simulation with Shared Mobility Services: An Approach Using Spatiotemporal Network Kernel Density Estimation and MATSim " by Jalal Khalil