Interpretable Spatiotemporal Feature Selection for Solar Power Forecasts
Activity: Talk or presentation at external institutions/events › Talk/Presentation › Contributed
Persons and affiliations
- Markus Leyser - , Boysen TUD Research Training Group, Chair of Big Data Analytics in Transportation (TT) (Speaker)
- Pascal Kerschke - , Chair of Big Data Analytics in Transportation (TT) (Involved person)
- Lennart Schäpermeier - , Chair of Big Data Analytics in Transportation (TT) (Involved person)
Date
22 May 2024
Description
Feature selection methods that exploit spatiotemporal data structures are rare. Spatiotemporal feature importance measures are even rarer. We propose a set of feature importance scores that give insights into the spatial, temporal and variable dimensions of spatiotemporal datasets. To this end, we systematically aggregate feature importance scores of reduced models that were trained on dices of the spatiotemporal hypercube. The scores can be calculated from regression coefficients, or from any other upstream feature importance metric. In an extensive case study, we apply the developed methods to a challenging solar power forecasting task, demonstrating their effectiveness in a field closely related to energy meteorology, which is widely recognized as highly complex.Workshop
Title | COSEAL Workshop 2024 |
---|---|
Abbreviated title | COSEAL 2024 |
Duration | 21 - 23 May 2024 |
Website | |
Degree of recognition | International event |
Location | Dorint Hotel Dresden |
City | Dresden |
Country | Germany |