Predictive utilization of physical resources

Techniques for transportation speed prediction and transit time estimation are provided. In an example, a computer system generates a first input to a first machine learning model based on temporal information, road segment information, and attribute information for road segments in a geographic region. The computer system receives a first output of the first machine learning model. The first output indicates a predicted speed value associated with a road segment for a transportation resource. The computer system generates a second input to a second machine learning model based on the first input, the predicted speed value, and properties associated with a transportation load. The computer system receives a second output of the second machine learning model. The second output indicates a distribution of a time length for transporting the transportation load using the transportation resource. The second output is usable in deploying the transportation resource for transporting the transportation load.