Data Sci. for a Changing Clmt

3 Credits · Level: Graduate, Undergraduate

This course will introduce students to methods in data science applied to problems relating to climate change. Students should have a minimum of high school calculus and an introductory level statistics course. Topics will include: • Data analysis: time series analysis, regression, attribution, spatial kriguing, frequentist versus Bayesian methods • Model forecasting: Artificial neural networks, Kalman filters, model validation • Simulation modeling: sampling the parameter space, uncertainty quantification, Bayesian parameter estimation • Sampling methods for inference: Gibbs Sampler, Metropolis Hastings, Sampling Importance Ratios • Model evaluation: bias correction, weighting models.