Carleton University
Improving Wind Speed and Power Prediction Through Dynamic Surface Parameterization and Spatiotemporal Machine Learning
Abstract
dc:description.abstractAccurate prediction of wind speed and wind power remains a central challenge in the field of wind energy research. Numerical Weather Prediction models often struggle to represent near-surface processes that dominate wind behavior. Meanwhile, previous work in machine learning approaches show the need for incorporating non-local atmospheric information to capture the spatiotemporal drivers of wind power variability. This study develops a dynamic aerodynamic roughness length parameterization using observed and simulated information. Applied across three sites, the results reveal strong temporal patterns not captured by static roughness bounds and its implementation produces improvements in modeled near-surface winds. In addition, a spatiotemporal random forest framework to predict wind farm power output is developed using a regional network of pressure measurements. Across three sites, the random forest models demonstrate that non-local, lagged pressure data carry strong predictive value and exhibit physically interpretable results. Incorporating dynamic roughness length further improves power prediction accuracy.
Degree
thesis:*- Name thesis:degree_name
- Master of Applied Science (M.App.Sc.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Engineering, Sustainable Energy
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Srivastava, Siddhant
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- Copyright © 2026 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en