Using a Hilbert Curve for indexing is a pretty standard approach for geospatial queries. Nothing new here...
However, using a Hilbert Curve for sharding doesn't seem like the best approach. You can partition by anything you like, it doesn't have to be arbitrary points along your index. Using 1-dimension to shard 2D data isn't optimal.
For example, construct a heatmap of your 'load score' and shard based on that, in two dimensions. Then use an S2 curve to index inside that shard.
However, using a Hilbert Curve for sharding doesn't seem like the best approach. You can partition by anything you like, it doesn't have to be arbitrary points along your index. Using 1-dimension to shard 2D data isn't optimal.
For example, construct a heatmap of your 'load score' and shard based on that, in two dimensions. Then use an S2 curve to index inside that shard.