<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body>
<div class="" style="word-wrap:break-word">
<div class="">This is an announcement of Elena Orlova's MS Presentation</div>
<div class="">===============================================</div>
<div class="">Candidate: Elena Orlova</div>
<div class=""><br class="">
</div>
<div class="">Date: Friday, November 11, 2022</div>
<div class=""><br class="">
</div>
<div class="">Time: 9 am CST</div>
<div class=""><br class="">
</div>
<div class="">Remote Location: <a href="https://uchicago.zoom.us/j/96838766484?pwd=UkZlVTYrWnVCMUplRzJKL09zQlNQQT09" class="">
https://uchicago.zoom.us/j/96838766484?pwd=UkZlVTYrWnVCMUplRzJKL09zQlNQQT09</a> </div>
<div class=""><br class="">
</div>
<div class="">Location: JCL 390</div>
<div class=""><br class="">
</div>
<div class="">M.S. Paper Title: Enhancing Subseasonal Climate Forecasting with Climate Model Ensembles and Machine Learning</div>
<div class=""><br class="">
</div>
<div class="">Abstract: Producing high-quality forecasts of key climate variables such as temperature and precipitation on sub-seasonal time scales has long been a gap in operational forecasting. Recent studies have shown promising results using machine learning
(ML) models to advance sub-seasonal forecasting (SSF), but several open questions remain. First, several past approaches use the average of an ensemble of physics-based forecasts as an input feature of these models. However, ensemble forecasts contain information
that can aid prediction beyond only the ensemble mean. Second, past methods have focused on average performance, whereas forecasts of extreme events are far more important for planning and mitigation purposes. Third, climate forecasts correspond to a spatially-varying
collection of forecasts, and different methods account for spatial variability in the response differently. Trade-offs between different approaches may be mitigated with model stacking. This paper describes the application of a variety of ML methods to predicting
monthly average precipitation and two meter temperature using physics-based predictions (ensemble members) and observational data such as relative humidity, pressure at sea level or geopotential height two weeks in advance for the whole continental U. S. Regression
and tercile classification tasks using linear models, random forests, convolutional neural networks, and stacked models are considered. The proposed models outperform common baselines such as historical averages and ensemble averages. This paper further includes
an investigation of feature importance and trade-offs between using the full ensemble or only the ensemble average.</div>
<div class=""><br class="">
</div>
<div class="">Advisors: Rebecca Willett</div>
<div class=""><br class="">
</div>
<div class="">Committee Members: Rebecca Willett, Ian Foster, and Yuxin Chen</div>
<div class=""><br class="">
</div>
<div class=""><br class="">
</div>
<div class=""></div>
</div>
<div class="" style="word-wrap:break-word">
<div class=""></div>
</div>
</body>
</html>