Will is a graduate of CU Boulder with degrees in computer science and geography. He is working on constructing new solutions to accessing and working with high volume spatial datasets mainly pertaining to snow water equivalent. He believes there is a wealth of knowledge stored within new data sources, however there is a serious lack of work being done to make this data accessible to larger audiences.  

Will is passionate about open source science and the power of python. He has worked on several projects related to developing better tools for accessing  geospatial data in python and simplifying the programming knowledge needed to obtain data for geospatial analysis. One of his main projects at Earth Lab has been the development of SWEpy, a python library for simplifying access to temperature brightness data. SWEpy allows novice and expert python programmers alike access, subset, and process data for analyzing snow water equivalent. 

In addition to open source development, he has spent time applying deep learning to projecting snowpack metrics using cutting edge techniques designed for precipitation forecasting. His model involved combining the power of long short term memory recurrent neural networks with convolutional neural networks; this style of network, called a ConvLSTM is quite good at multi-step time series forecasting on spatio-temporal data. 

When he isn't in front of a computer, Will enjoys trail running and backpacking.