[Virtual] GFDL Formal Seminar

Thu, Oct 22, 2020, 2:00 pm to 3:00 pm

Much of climate science is viewed as a signal-to-noise problem and the field has many statistical methods for extracting the signal of interest. Here, we argue that artificial neural networks (ANNs) are an additional useful tool for the “climate toolbox”. As an example, we demonstrate their utility for extracting forced climate patterns from model simulations and observations whereby the ANN identifies patterns that are complex, non-linear combinations of signal and noise. While neural networks are often viewed as black boxes, we further demonstrate how to visualize what the network has learned using recent advances in visualization tools within the computer science community. This approach suggests that viewing climate patterns through an AI lens has the power to uncover new insights into climate variability and change.

Location: 
Virtual
Speaker(s): 

[Virtual] David Bradford Energy and Environmental Policy Seminar

Mon, Oct 26, 2020, 12:15 pm to 1:15 pm
Location: Zoom

[Virtual] Environmental Geology & Geochemistry Seminar (EGGS)

Tue, Oct 27, 2020, 12:30 pm to 1:20 pm
Location: Virtual

[Virtual] Energy Table

Tue, Oct 27, 2020, 3:00 pm to 4:00 pm
Location: Virtual

[Virtual] GFDL Lunchtime Seminar

Wed, Oct 28, 2020, 12:00 pm to 1:00 pm
Location: Virtual

[Virtual] GFDL Formal Seminar

Thu, Oct 29, 2020, 2:00 pm to 3:00 pm
Location: Virtual

[Virtual] David Bradford Energy and Environmental Policy Seminar

Mon, Nov 2, 2020, 12:15 pm to 1:15 pm
Location: Zoom

[Virtual] PEI Faculty Seminar

Tue, Nov 3, 2020, 12:30 pm to 1:30 pm
Location: Zoom

[Virtual] GFDL Formal Seminar

Thu, Nov 5, 2020, 2:00 pm to 3:00 pm
Location: Virtual

[Virtual] David Bradford Energy and Environmental Policy Seminar

Mon, Nov 9, 2020, 12:15 pm to 1:15 pm
Location: Zoom

[Virtual] Environmental Geology & Geochemistry Seminar (EGGS)

Tue, Nov 10, 2020, 12:30 pm to 1:20 pm
Location: Virtual