| 一種基于BP神經(jīng)網(wǎng)絡(luò)方法的HY-2A散射計(jì)反演風(fēng)場偏差訂正方案 |
| 作者:潘微1 2 3 邢建勇1 3 萬莉穎1 3 |
單位:1. 國家海洋環(huán)境預(yù)報(bào)中心, 北京 100081; 2. 廈門大學(xué)海洋與地球?qū)W院物理海洋學(xué)系, 廈門 361005; 3. 國家海洋環(huán)境預(yù)報(bào)中心 國家海洋局海洋災(zāi)害預(yù)報(bào)技術(shù)研究重點(diǎn)實(shí)驗(yàn)室, 北京 100081 |
| 關(guān)鍵詞:HY-2A散射計(jì) 偏差訂正 BP神經(jīng)網(wǎng)絡(luò) |
| 分類號:P732.1 |
|
| 出版年·卷·期(頁碼):2018·35·第二期(8-18) |
|
摘要:
|
| 針對HY-2A散射計(jì)風(fēng)矢量場數(shù)據(jù),利用BP神經(jīng)網(wǎng)絡(luò)方法,引入NDBC浮標(biāo)的降水海溫等環(huán)境要素,對HY-2A散射計(jì)風(fēng)場進(jìn)行偏差訂正。實(shí)驗(yàn)結(jié)果表明: BP神經(jīng)網(wǎng)絡(luò)方法對HY-2A散射計(jì)的風(fēng)速風(fēng)向均有較好的訂正效果,能有效修正HY-2A的風(fēng)速高估現(xiàn)象,風(fēng)速平均偏差由2.32 m/s改善至0.25 m/s;同時(shí)通過敏感性試驗(yàn),發(fā)現(xiàn)了各樣本輸入量以及各環(huán)境要素對實(shí)驗(yàn)結(jié)果的敏感性。 |
| Aiming at HY-2A scatter meter wind vector field data,using BP neural network method,with the introduction of NDBC buoy environmental elements,including SST and precipitation,we have made a bias correction in the HY-2A scatter meter wind field.Experiment results show that the BP neural network method has a good correction effect on HY-2A scattering wind speed and direction,which can effectively alleviated HY-2A wind speed overestimation,with the mean bias improving from 2.32 m/s to 0.25 m/s.At the same time by sensitivity test,we find the sensitivity of experiment result with the sample size and environmental factors. |
|
參考文獻(xiàn):
|
[1] 王東良, 姚小海, 孟雷, 等. 海洋二號衛(wèi)星散射計(jì)風(fēng)場產(chǎn)品真實(shí)性檢驗(yàn)及分析[J]. 海洋預(yù)報(bào), 2014, 31(4):47-53, doi:10.11737/j. issn.1003-0239.2014.04.007. [2] 苗俊剛, 劉大偉. 微波遙感導(dǎo)論[M]. 北京:機(jī)械工業(yè)出版社, 2013. [3] 馮士筰, 李風(fēng)岐, 李少菁. 海洋科學(xué)導(dǎo)論[M]. 北京:高等教育出版社, 1999. [4] Freilich M H, Dunbar R S. The accuracy of the NSCAT 1 vector winds:comparisons with National Data Buoy Center buoys[J]. Journal of Geophysical Research:Oceans, 1999, 104(C5):11231-11246. [5] Xing J Y, Shi J C, Lei Y H, et al. Evaluation of HY-2A scatterometer wind vectors using data from buoys, ERA-interim and ASCAT during 2012-2014[J]. Remote Sensing, 2016, 8(5):390. [6] Stiles B W, Yueh S H. Impact of rain on spaceborne Ku-band wind scatterometer data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(9):1973-1983. [7] Liu W T. The effects of the variations in sea surface temperature and atmospheric stability in the estimation of average wind speed by SEASAT-SASS[J]. Journal of Physical Oceanography, 1984, 14(2):392-401. [8] 邢建勇. 基于HY-2A多傳感器的風(fēng)反演精度和同化研究[D]. 北京:中國科學(xué)院大學(xué), 2016. [9] 何恩業(yè), 李海, 任湘湘, 等. BP人工神經(jīng)網(wǎng)絡(luò)在渤海灣葉綠素預(yù)測中的應(yīng)用[J]. 海洋預(yù)報(bào), 2008, 25(2):1-10. [10] 李世萍, 孔令彬, 肖瑋, 等. 基于BP神經(jīng)網(wǎng)絡(luò)的風(fēng)速觀測資料序列訂正模型[J]. 蘭州大學(xué)學(xué)報(bào)(自然科學(xué)版), 2013, 49(3):337-339, 346. [11] 盧君峰, 李少偉, 袁方超. 基于BP神經(jīng)網(wǎng)絡(luò)的廈門沿海風(fēng)暴潮預(yù)報(bào)應(yīng)用[J]. 海洋預(yù)報(bào), 2016, 33(4):9-16. [12] 邵利民, 傅剛, 曹祥村, 等. BP神經(jīng)網(wǎng)絡(luò)在臺風(fēng)路徑預(yù)報(bào)中的應(yīng)用[J]. 自然災(zāi)害學(xué)報(bào), 2009, 18(6):104-111. [13] Pensieri S, Bozzano R, Schiano M E. Comparison between QuikSCAT and buoy wind data in the Ligurian Sea[J]. Journal of Marine Systems, 2010, 81(4):286-296. |
|
服務(wù)與反饋:
|
|
【文章下載】【發(fā)表評論】【查看評論】【加入收藏】
|
|
|