本文選題：大氣光學(xué)湍流強(qiáng)度 + 預(yù)報(bào)模式��； 參考：《中國(guó)科學(xué)技術(shù)大學(xué)》2017年碩士論文

【摘要】：大氣光學(xué)湍流是大氣中的一種重要現(xiàn)象,當(dāng)它發(fā)生時(shí),會(huì)對(duì)在其中傳輸?shù)墓馐a(chǎn)生影響,因此長(zhǎng)期觀測(cè)大氣光學(xué)湍流強(qiáng)度有助于地面激光設(shè)備的使用和天文臺(tái)選址的搭建,但實(shí)際中因?yàn)榇钶d觀測(cè)平臺(tái)的成本較高,長(zhǎng)期大范圍觀測(cè)大氣光學(xué)湍流強(qiáng)度難以實(shí)現(xiàn),因此找到一種能夠準(zhǔn)確預(yù)報(bào)大氣光學(xué)湍流強(qiáng)度的方法有助于解決這一問題。本論文基于在成都和德令哈兩種不同地區(qū)所做的實(shí)驗(yàn),介紹了后向傳播神經(jīng)網(wǎng)絡(luò)與支持向量機(jī)兩種預(yù)報(bào)大氣光學(xué)湍流的辦法,建立兩個(gè)模型,并比較了兩種模型的效果,主要結(jié)論如下:(1)經(jīng)過訓(xùn)練好的后向傳播神經(jīng)網(wǎng)絡(luò)模型能夠基本準(zhǔn)確的表現(xiàn)出成都地區(qū)的大氣光學(xué)湍流強(qiáng)度Cn2的日變化特征,而且在夜間的預(yù)報(bào)也更貼近觀測(cè)值,平均相對(duì)誤差率為3.03%,但是與觀測(cè)結(jié)果相比,預(yù)報(bào)結(jié)果的峰值會(huì)有一小時(shí)的超前;在德令哈地區(qū)的實(shí)驗(yàn)表明,BP模型也能表現(xiàn)出該地區(qū)的基本日變化特征,平均相對(duì)誤差率為3.53%,該地區(qū)Cn2的轉(zhuǎn)換時(shí)刻明顯,尤其是在18:00大氣光學(xué)湍流強(qiáng)度會(huì)出現(xiàn)突然下降,后向傳播神經(jīng)網(wǎng)絡(luò)模型能夠準(zhǔn)確的表現(xiàn)出這一變化。(2)支持向量機(jī)模型通過循環(huán)確定關(guān)鍵參數(shù)后也被證明可以用來估算近地面的大氣光學(xué)湍流強(qiáng)度Cn2,成都地區(qū)的實(shí)驗(yàn)表明通過支持向量機(jī)模型能夠表現(xiàn)出該地區(qū)的大氣光學(xué)湍流的日變化特征,平均相對(duì)誤差率為2.81%;在德令哈地區(qū)也進(jìn)行了相應(yīng)的實(shí)驗(yàn)進(jìn)行驗(yàn)證,使用支持向量機(jī)建立模型在該地區(qū)做出了9天的預(yù)測(cè)結(jié)果與觀測(cè)值吻合基本較好,能夠明顯表現(xiàn)出該地區(qū)大氣光學(xué)湍流強(qiáng)度Cn2的日變化特征,平均相對(duì)誤差率為3.38%,Cn2的頻數(shù)分布圖表明其與觀測(cè)值的分布相似,均滿足高斯分布。(3)通過在成都和德令哈地區(qū)的兩次實(shí)驗(yàn)表明,經(jīng)過訓(xùn)練的兩種模型均能夠通過一天的數(shù)據(jù)得到隨后6至9天的大氣光學(xué)湍流強(qiáng)度Cn2的預(yù)報(bào),相關(guān)分析、平均絕對(duì)誤差和相對(duì)誤差等統(tǒng)計(jì)量的分析均表明,這兩種模型能夠準(zhǔn)確表現(xiàn)出這兩個(gè)地區(qū)近地面的大氣光學(xué)湍流強(qiáng)度的變化,后向傳播神經(jīng)網(wǎng)絡(luò)模型的相對(duì)誤差率等統(tǒng)計(jì)量略大于支持向量機(jī)模型,但兩者差距不大,均能夠表現(xiàn)出良好的非線性特征。
[Abstract]:Atmospheric optical turbulence is an important phenomenon in the atmosphere. When it occurs, it will affect the beam which is transmitted in it. Therefore, the long-term observation of atmospheric optical turbulence intensity is helpful to the use of ground laser equipment and the establishment of the site selection of the observatory. However, in practice, the high cost of carrying the observation platform is high and the atmospheric light is observed for a long time in a large range. It is difficult to realize the turbulence intensity, so finding a method to predict the intensity of atmospheric optical turbulence is helpful to solve this problem. Based on the experiments in two different regions in Chengdu and Delingha, this paper introduces the two methods of predicting atmospheric optical turbulence in the back propagation neural network and support vector machine, and establishes two methods. The results of the two models are compared and the main conclusions are as follows: (1) the trained back propagation neural network model can basically accurately show the diurnal variation characteristics of atmospheric optical turbulence intensity Cn2 in Chengdu, and also more close to the night forecast, the average relative error rate is 3.03%, but the results are compared with the observation results. The peak value of the forecast results will be ahead of an hour, and the experiment in Delingha shows that the BP model can also show the basic diurnal variation of the region. The average relative error rate is 3.53%. The transition time of Cn2 in this area is obvious, especially at 18:00, the atmospheric optical turbulence intensity will drop suddenly, and the backward propagation neural network model is used. The model can accurately show this change. (2) the support vector machine model is also proved to be used to estimate the atmospheric optical turbulence intensity Cn2 in the near ground. The experiment in Chengdu region shows that the support vector machine model can show the diurnal variation characteristics of atmospheric optical turbulence in this area. The error rate is 2.81%, and the corresponding experiments are also carried out in Delingha. The support vector machine model has been established in the area for 9 days and the results are in good agreement with the observed values. It can obviously show the diurnal variation characteristics of the atmospheric optical turbulence intensity Cn2 in this area, the average relative error rate is 3.38%, the frequency of Cn2. The distribution diagram shows that it is similar to the distribution of the observed values and satisfies Gauss distribution. (3) through two experiments in Chengdu and Delingha, the trained two models can obtain the prediction, correlation analysis, mean absolute error and relative error of the atmospheric optical turbulence intensity of 6 to 9 days after one day of data. The quantitative analysis shows that the two models can accurately show the change of atmospheric optical turbulence intensity near the ground in the two regions, and the relative error rate of the back propagation neural network model is slightly larger than the support vector machine model, but the gap between the two models is not large, and all of them can show good nonlinear characteristics.
【學(xué)位授予單位】：中國(guó)科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：P427.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 青春;吳曉慶;李學(xué)彬;朱文越;黃印博;饒瑞中;蔡俊;;典型地區(qū)高空大氣光學(xué)湍流模擬研究[J];光學(xué)學(xué)報(bào);2016年05期

2 青春;吳曉慶;王海濤;汪平;;成都地區(qū)近地面大氣折射率結(jié)構(gòu)常數(shù)的統(tǒng)計(jì)分析[J];大氣與環(huán)境光學(xué)學(xué)報(bào);2015年05期

3 青春;吳曉慶;李學(xué)彬;朱文越;饒瑞中;梅海平;;WRF模式估算麗江高美古大氣光學(xué)湍流廓線[J];中國(guó)激光;2015年09期

4 田啟國(guó);柴博;吳曉慶;姜鵬;紀(jì)拓;金鑫淼;周宏巖;;移動(dòng)式極地大氣參數(shù)測(cè)量系統(tǒng)I.研制與試觀測(cè)[J];極地研究;2015年02期

5 吳曉軍;王紅星;李筆鋒;劉傳輝;;近海面大氣折射率結(jié)構(gòu)常數(shù)統(tǒng)計(jì)特性分析[J];光學(xué)學(xué)報(bào);2015年04期

6 王紅帥;姚永強(qiáng);劉立勇;;基于天氣預(yù)報(bào)模式預(yù)報(bào)阿里天文站大氣光學(xué)湍流[J];光學(xué)學(xué)報(bào);2013年03期

7 王紅帥;姚永強(qiáng);錢璇;劉立勇;王益萍;李俊榮;;大氣光學(xué)湍流模型計(jì)算方法[J];天文學(xué)報(bào);2012年06期

8 李云波;黃小毛;余軍浩;趙亞明;;近海面大氣光學(xué)湍流計(jì)算模型的比較與改進(jìn)[J];光學(xué)學(xué)報(bào);2012年11期

9 錢燕珍;孫軍波;余暉;陳佩燕;;用支持向量機(jī)方法做登陸熱帶氣旋站點(diǎn)大風(fēng)預(yù)報(bào)[J];氣象;2012年03期

10 張樂堅(jiān);程明虎;田付友;;人工神經(jīng)網(wǎng)絡(luò)及支持向量機(jī)在降雨量預(yù)報(bào)中的應(yīng)用[J];高原氣象;2010年04期

相關(guān)博士學(xué)位論文 前3條

1 曾紹華;支持向量回歸機(jī)算法理論研究與應(yīng)用[D];重慶大學(xué);2006年

2 劉靖旭;支持向量回歸的模型選擇及應(yīng)用研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2006年

3 田英杰;支持向量回歸機(jī)及其應(yīng)用研究[D];中國(guó)農(nóng)業(yè)大學(xué);2005年

，

本文編號(hào)：1932300