Based on machine learning techniques and airborne lidar, I developed and published R package to model visibility across diverse landscapes in the contiguous United States. This study introduced a novel method for spatially-exhaustive visibility mapping using airborne lidar and random forests that only requires a sparse sample of computationally expensive viewsheds.

The paper, published in the International Journal of Geographical Information Science, can be found here. The R package developed to support this work is available on my github page.