利用机器学习技术对高级散射计(ASCAT)海面风进行垂直外推

IF 3.6 Q3 GREEN & SUSTAINABLE SCIENCE & TECHNOLOGY Wind Energy Science Pub Date : 2023-04-28 DOI:10.5194/wes-8-621-2023
Daniel Hatfield, C. Hasager, Ioanna Karagali
{"title":"利用机器学习技术对高级散射计(ASCAT)海面风进行垂直外推","authors":"Daniel Hatfield, C. Hasager, Ioanna Karagali","doi":"10.5194/wes-8-621-2023","DOIUrl":null,"url":null,"abstract":"Abstract. The increasing demand for wind energy offshore requires more hub-height-relevant wind information, while larger wind turbine sizes require measurements at greater heights. In situ measurements are harder to acquire at higher atmospheric levels; meanwhile the emergence of machine-learning applications has led to several studies demonstrating the improvement in accuracy for vertical wind extrapolation over conventional power-law and logarithmic-profile methods. Satellite wind retrievals supply multiple daily wind observations offshore, however only at 10 m height. The goal of this study is to develop and validate novel machine-learning methods using satellite wind observations and near-surface atmospheric measurements to extrapolate wind speeds to higher heights. A machine-learning model is trained on 12 years of collocated offshore wind measurements from a meteorological mast (FINO3) and space-borne wind observations from the Advanced Scatterometer (ASCAT). The model is extended vertically to predict the FINO3 vertical wind profile. Horizontally, it is validated against the NORwegian hindcast Archive (NORA3) mesoscale model reanalysis data. In both cases the model slightly over-predicts the wind speed with differences of 0.25 and 0.40 m s−1, respectively. An important feature in the model-training process is the air–sea temperature difference; thus satellite sea surface temperature observations were included in the horizontal extension of the model, resulting in 0.20 m s−1 differences with NORA3. A limiting factor when training machine-learning models with satellite observations is the small finite number of daily samples at discrete times; this can skew the training process to higher-/lower-wind-speed predictions depending on the average wind speed at the satellite observational times. Nonetheless, results shown in this proof-of-concept study demonstrate the limited applicability of using machine-learning techniques to extrapolate long-term satellite wind observations when enough samples are available.\n","PeriodicalId":46540,"journal":{"name":"Wind Energy Science","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Vertical extrapolation of Advanced Scatterometer (ASCAT) ocean surface winds using machine-learning techniques\",\"authors\":\"Daniel Hatfield, C. Hasager, Ioanna Karagali\",\"doi\":\"10.5194/wes-8-621-2023\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract. The increasing demand for wind energy offshore requires more hub-height-relevant wind information, while larger wind turbine sizes require measurements at greater heights. In situ measurements are harder to acquire at higher atmospheric levels; meanwhile the emergence of machine-learning applications has led to several studies demonstrating the improvement in accuracy for vertical wind extrapolation over conventional power-law and logarithmic-profile methods. Satellite wind retrievals supply multiple daily wind observations offshore, however only at 10 m height. The goal of this study is to develop and validate novel machine-learning methods using satellite wind observations and near-surface atmospheric measurements to extrapolate wind speeds to higher heights. A machine-learning model is trained on 12 years of collocated offshore wind measurements from a meteorological mast (FINO3) and space-borne wind observations from the Advanced Scatterometer (ASCAT). The model is extended vertically to predict the FINO3 vertical wind profile. Horizontally, it is validated against the NORwegian hindcast Archive (NORA3) mesoscale model reanalysis data. In both cases the model slightly over-predicts the wind speed with differences of 0.25 and 0.40 m s−1, respectively. An important feature in the model-training process is the air–sea temperature difference; thus satellite sea surface temperature observations were included in the horizontal extension of the model, resulting in 0.20 m s−1 differences with NORA3. A limiting factor when training machine-learning models with satellite observations is the small finite number of daily samples at discrete times; this can skew the training process to higher-/lower-wind-speed predictions depending on the average wind speed at the satellite observational times. Nonetheless, results shown in this proof-of-concept study demonstrate the limited applicability of using machine-learning techniques to extrapolate long-term satellite wind observations when enough samples are available.\\n\",\"PeriodicalId\":46540,\"journal\":{\"name\":\"Wind Energy Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2023-04-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Wind Energy Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5194/wes-8-621-2023\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"GREEN & SUSTAINABLE SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Wind Energy Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5194/wes-8-621-2023","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GREEN & SUSTAINABLE SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

摘要海上风能需求的增加需要更多与轮毂高度相关的风力信息,而更大的风力涡轮机尺寸需要在更高的高度进行测量。在更高的大气水平下,现场测量更难获得;与此同时,机器学习应用的出现导致了几项研究表明,与传统的幂律和对数剖面方法相比,垂直风外推的精度有所提高。卫星风力反演提供了多个海上每日风力观测,但仅为10 m高。这项研究的目标是开发和验证新的机器学习方法,利用卫星风观测和近地表大气测量将风速外推到更高的高度。机器学习模型是根据气象桅杆(FINO3)的12年并置海上风测量和高级散射仪(ASCAT)的星载风观测进行训练的。对该模型进行了垂直扩展,以预测FINO3的垂直风廓线。在水平方向上,它与挪威后预报档案(NORA3)中尺度模式再分析数据进行了验证。在这两种情况下,模型都略微高估了风速,差异为0.25和0.40 m s−1。模型训练过程中的一个重要特征是海气温差;因此,卫星海面温度观测结果被包括在模型的水平扩展中,结果为0.20 m s−1与NORA3的差异。用卫星观测训练机器学习模型时的一个限制因素是离散时间的每日样本数量有限;这可能会使训练过程偏离到更高/更低的风速预测,这取决于卫星观测时间的平均风速。尽管如此,这项概念验证研究的结果表明,在有足够样本的情况下,使用机器学习技术推断长期卫星风观测的适用性有限。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Vertical extrapolation of Advanced Scatterometer (ASCAT) ocean surface winds using machine-learning techniques
Abstract. The increasing demand for wind energy offshore requires more hub-height-relevant wind information, while larger wind turbine sizes require measurements at greater heights. In situ measurements are harder to acquire at higher atmospheric levels; meanwhile the emergence of machine-learning applications has led to several studies demonstrating the improvement in accuracy for vertical wind extrapolation over conventional power-law and logarithmic-profile methods. Satellite wind retrievals supply multiple daily wind observations offshore, however only at 10 m height. The goal of this study is to develop and validate novel machine-learning methods using satellite wind observations and near-surface atmospheric measurements to extrapolate wind speeds to higher heights. A machine-learning model is trained on 12 years of collocated offshore wind measurements from a meteorological mast (FINO3) and space-borne wind observations from the Advanced Scatterometer (ASCAT). The model is extended vertically to predict the FINO3 vertical wind profile. Horizontally, it is validated against the NORwegian hindcast Archive (NORA3) mesoscale model reanalysis data. In both cases the model slightly over-predicts the wind speed with differences of 0.25 and 0.40 m s−1, respectively. An important feature in the model-training process is the air–sea temperature difference; thus satellite sea surface temperature observations were included in the horizontal extension of the model, resulting in 0.20 m s−1 differences with NORA3. A limiting factor when training machine-learning models with satellite observations is the small finite number of daily samples at discrete times; this can skew the training process to higher-/lower-wind-speed predictions depending on the average wind speed at the satellite observational times. Nonetheless, results shown in this proof-of-concept study demonstrate the limited applicability of using machine-learning techniques to extrapolate long-term satellite wind observations when enough samples are available.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Wind Energy Science
Wind Energy Science GREEN & SUSTAINABLE SCIENCE & TECHNOLOGY-
CiteScore
6.90
自引率
27.50%
发文量
115
审稿时长
28 weeks
期刊最新文献
Swinging motion of a kite with suspended control unit flying turning manoeuvres A sensitivity-based estimation method for investigating control co-design relevance An actuator sector model for wind power applications: a parametric study Experimental validation of a short-term damping estimation method for wind turbines in nonstationary operating conditions Quantifying the impact of modeling fidelity on different substructure concepts – Part 2: Code-to-code comparison in realistic environmental conditions
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1