Data-driven large-scale spatial planning framework for determining size and location of offshore wind energy development: A case study of China

Yanwei Sun, Hongying Ai, Ying Li, Run Wang and Renfeng Ma

Applied Energy, 2024, vol. 367, issue C, No S0306261924007712

Abstract: Offshore wind energy (OWE) is now considered as a vital renewable energy source in numerous coastal countries due to high potential, vast ocean areas, and the scarcity of onshore land resources. Therefore, solving spatial siting decision issues are extremely important for identifying the potential suitable regions and enacting developing strategies for future offshore wind energy facilities. In this study, a data-driven methodological framework was proposed for addressing complex planning problems of offshore wind energy sources by taking into account a set of suitability criteria clusters: resources endowments, oceanographic features, Land–Sea interactions, and potential conflict with current maritime activities. Through linking 6084 samples of existing offshore wind turbines and 12 spatial explaining factors, a high-efficient machine learning regression and classification model, Random Forest algorithm, was conducted to predict ideal size and location of offshore wind energy facilities at the grid cell level. The methodology was applied to the related offshore areas of China with about 18,400 km of coastline. Results highlight that location suitability of OWE farms is greatly determined by water depth and distances from fishing areas, whereas capacity size of wind turbines depended on the synergistic effect of multiple factors. Suitability and size maps were developed to determine the most suitable locations and optimal wind installation capacity in the sea space. Under existing wind power technical conditions, almost 15.6% of marine areas within 50 m water depth (approximately 251 GW) was classified as having above moderate wind energy suitability. The proposed ensemble learning framework provides efficient and useful practical tools for addressing the spatial planning issues of offshore wind farms, and informing policy development from the perspectives of both siting and size.

Keywords: Offshore wind energy; Spatial planning; Explainable machine learning; China (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261924007712
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:367:y:2024:i:c:s0306261924007712

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2024.123388

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().