Advancing the predictive power of Earth system models through understanding
of the structure and function of Arctic terrestrial ecosystems
Science Highlights
Mapping Vegetation Communities using Convolutional Neural Networks
Artificial intelligence applied to multiple remote sensing datasets accurately represents shrub distribution across hillslopes at the Kougarok field site.
Landscape Mapping using Remote Sensing and Neural Networks
A convolutional neural network (CNN) approach produced highly accurate vegetation classifications. Hyper-spectral datasets (e.g., AVIRIS) were most useful for our machine learning approaches. Accurate and high-resolution datasets generated using our approach are needed for Arctic models.
Microtopography Determines How CO2 and CH4 Exchanges Respond to Temperature and Precipitation in Polygonal Tundra
Microtopographic variation among troughs, rims, and centers strongly affects the movement of surface water and snow and thereby affects soil water contents and active layer development.
Field Measurements of Photosynthetic Biochemistry Provide Improved Representation of Gas-Exchange in ESMs
Study highlights the poor representation of Arctic photosynthesis in TBMs, and provides the critical data necessary to improve our ability to project the response of the Arctic to global environmental change.