Complex Systems Summer School 2017-Tutorials

Complex Systems Summer School 2017 Home Surveys/Evaluations Logistics Payment Instructions Faculty Panel Questions Faculty Publications Lecture Slides Participants Schedule Background Readings Software Projects & Working Groups Project Group Meeting Schedule Sign Up Sheet for Meetings with Project Liaison Presentation Sign Up Page Project Presentations Final Papers Tutorials After Hours Restaurant Guide Resource Guide Photos TShirts Viniegra Essay

Nonlinear Time Series Analysis using Empirical Dynamic Modeling (EDM)

Hey all, I've done some work with non-linear time series analysis using empirical dynamic modeling (Sugihara et al., 2012). If anyone is interested in these approaches, I'd be happy to give a tutorial on the R EDM package that can be used to look for 1. nonlinearity in time-series, 2. causality between variables, and 3. optimizing combinations of system variables to create "equation-free mechanistic models". I've used this method looking at marine phytoplankton time-series, combining several species and environmental variables. The final product was messy, but helped identify important system variables in ecosystems :)

References:

Online walk-through of the R EDM package [1]!

• Sugihara, George et al. “Detecting Causality in Complex Ecosystems.” Science 338.6106 (2012): 496–500. Web.
  
• Ye, Hao et al. “Equation-Free Mechanistic Ecosystem Forecasting Using Empirical Dynamic Modeling.” Proceedings of the National Academy of Sciences 112.13 (2015): E1569–E1576. Web.
  

Interested Participants:

• Zhiya Zuo. Thanks for this! Is there a desired time/location?

--> No plan for a time/location yet...I'm waiting to see if there is enough interest. I would be happy to do this whenever.

• Kayla Sale
• Jake Weissman
• Ximo Pechuan
• Markus Junginger
• Alicia Kraay
• Kyle Lemoi
• Anand Nair
• Carla Rivera