Method to determine contextual road clearance for electrical vehicles

A system to determine a stranded electric vehicle resilience index of an area for an electric vehicle (EV), comprising:

• at least one memory configured to store computer executable instructions;
• and
• at least one processor configured to execute the computer executable instructions to:
• determine, from an application programming interface (API), one or more areas in a region with minimal EV charging capabilities;
• generate a first trained machine learning model to predict a first probability for a given EV to be stranded in the one or more areas based on a training feature dataset and the one or more areas in a region with minimal EV charging capabilities;
• label the one or more areas as one or more critical areas based on the first probability for the given EV to be stranded in the one or more areas;
• generate a second trained machine learning model based on the labelled one or more critical areas;
• and
• predict, using the second trained machine learning model and current features of a link to be traveled by the EV as derived from a map and one or more sensors along the link, a second probability for the EV to be stranded on the link.

A computer program product comprising a non-transitory computer readable medium having stored thereon computer executable instructions, which when executed by one or more processors, cause the one or more processors to carry out operations to determine a stranded electric vehicle resilience index of an area for an electric vehicle (EV), the operations comprising:

• determining, from an application programming interface (API), one or more areas in a region with minimal EV charging capabilities;
• generating a first trained machine learning model to predict a first probability for a given EV to be stranded in the one or more areas based on a training feature dataset and the
• one or more areas in a region with minimal EV charging capabilities;
• labelling the one or more areas as one or more critical areas based on the first probability for the given EV to be stranded in the one or more areas;
• generating a second trained machine learning model based on the labelled one or more critical areas;
• and
• predicting, using the second trained machine learning model and current features of a link to be traveled by the EV as derived from a map and one or more sensors along the link, a second probability for the EV to be stranded on the link.