Search for: All records

Climate change is one of the greatest challenges facing humanity, and we, as machine learning (ML) experts, may wonder how we can help. Here we describe how ML can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by ML, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the ML community to join the global effort against climate change. 

Abstract. When wind blows over dry snow, the snow surface self-organizesinto bedforms such as dunes, ripples, snow waves, and sastrugi. Thesebedforms govern the interaction between wind, heat, and the snowpack, butthus far they have attracted few scientific studies.We present the first time-lapse documentation of snow bedform movement and evolution, as part of a series of detailed observations of snow bedform movement in the Colorado Front Range.We show examples of the movement of snow ripples, snow waves, barchan dunes,snow steps, and sastrugi. We also introduce a previously undocumentedbedform: the stealth dune. These observations show that (1) snow dunesaccelerate minute-by-minute in response to gusts, (2) sastrugi and snow stepspresent steep edges to the wind and migrate downwind as those edges erode,(3) snow waves and dunes deposit layers of cohesive snow in their wake, and(4) bedforms evolve along complex cyclic trajectories. These observationsprovide the basis for new conceptual models of bedform evolution, based onthe relative fluxes of snowfall, aeolian transport, erosion, and snowsintering across and into the surface. We find that many snow bedforms aregenerated by complex interactions between these processes. The prototypicalexample is the snow wave, in which deposition, sintering, and erosion occurin transverse stripes across the snowscape.