What are you trying to do? Articulate your objectives using absolutely no jargon.
My past research explores developing Machine Learning algorithms to estimate UAS ground risk efficiently in order to create safer UAS routes through highly populated areas.
How is it done today, and what are the limits of current practice?
Common approaches to UAS ground risk assessment rely on physics-based models that can be very slow, making them unsuitable for dynamic and highly populated areas where people are constantly on the move.
What is new in your approach and why do you think it will be successful?
Using Machine Learning, the ground risk assessment can be done in a matter of seconds rather than potentially hours in order to create risk maps that quantify ground risk. This was studied during my PhD work where a Machine Learning algorithm was successful in generating risk maps for the the Georgia Tech area with low error.
Who cares? If you are successful, what difference will it make?
Drone users in urban areas and regulators can benefit by improving safety with lower risk routes.