




版權(quán)說(shuō)明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請(qǐng)進(jìn)行舉報(bào)或認(rèn)領(lǐng)
文檔簡(jiǎn)介
1、. :.;BP神經(jīng)網(wǎng)絡(luò)論文:石羊河流域農(nóng)業(yè)需水量預(yù)測(cè)及水資源優(yōu)化配置研討【中文摘要】位于西北干旱地域的石羊河流域是全國(guó)水資源短缺的主要流域之一。流域需水量以農(nóng)業(yè)灌溉為主,近年來(lái)隨著氣候的變化,人口的添加,各個(gè)行業(yè)需水量也在不斷的變化。水資源短缺勢(shì)必呵斥各個(gè)用水部門爭(zhēng)水的不良的景象,為了實(shí)現(xiàn)流域的可繼續(xù)開(kāi)展,有必要對(duì)流域的農(nóng)業(yè)需水量和水資源的優(yōu)化配置進(jìn)展研討。本文經(jīng)過(guò)搜集到的資料,對(duì)流域內(nèi)的農(nóng)業(yè)需水情況進(jìn)展研討得出如下成果:(1)運(yùn)用搜集到的氣候和作物資料,首先經(jīng)過(guò)BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)模型,建立了基于影響農(nóng)業(yè)需水量的11個(gè)影響因子在民勤、天祝和全流域的農(nóng)業(yè)需水量預(yù)測(cè)模型,經(jīng)檢驗(yàn)?zāi)P途容^高。(2)由
2、于BP神經(jīng)網(wǎng)絡(luò)模型建模需求的資料量大,勢(shì)必呵斥運(yùn)算的繁瑣。為了能在根底資料較少的情況下,對(duì)農(nóng)業(yè)需水量很好的預(yù)測(cè),本文經(jīng)過(guò)對(duì)影響流域農(nóng)業(yè)需水量的11個(gè)影響要素進(jìn)展相關(guān)性分析,確定了這些要素和農(nóng)業(yè)需水量的相關(guān)性,確立了影響流域需水量最重要的2個(gè)影響因子,即耕地面積和降水量;以及對(duì)流域需水量有明顯影響作用的6個(gè)影響因子,即耕地面積、降水、糧食作物面積、積溫、日照和年最高溫。(3)經(jīng)過(guò)多元回歸分析,建立了基于六個(gè)主要影響要素的流域需水量六元線性回歸模型。經(jīng)過(guò)對(duì)影響因子的進(jìn)一步優(yōu)化進(jìn)而建立了基于兩個(gè)最重要影響因子的二元線性回歸模型和BP神經(jīng)網(wǎng)絡(luò)模型,并用19992003年這5年的數(shù)據(jù)進(jìn)展精度檢驗(yàn),發(fā)現(xiàn)B
3、P神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)效果要好于二元線性回歸模型。(4)運(yùn)用灰色預(yù)測(cè)、指數(shù)平滑預(yù)測(cè)和二者的組合預(yù)測(cè),經(jīng)過(guò)只對(duì)歷年農(nóng)業(yè)需水量的分析,建立了石羊河流域農(nóng)業(yè)需水量的預(yù)測(cè)模型,對(duì)三種模型進(jìn)展精度檢驗(yàn),發(fā)現(xiàn)灰色預(yù)測(cè)的平均相對(duì)誤差絕對(duì)值為4.84%,二次指數(shù)平滑預(yù)測(cè)的平均相對(duì)誤差絕對(duì)值為6.14%,組合預(yù)測(cè)模型的的平均相對(duì)誤差絕對(duì)值最小,為4.04%。用確定的組合預(yù)測(cè)模型對(duì)全流域未來(lái)十年的農(nóng)業(yè)需水量進(jìn)展預(yù)測(cè),預(yù)測(cè)流域2004年流域的農(nóng)業(yè)需水量為17.677108m3,到2021年需水量將到達(dá)19.178108m3。(5)經(jīng)過(guò)思索了流域的經(jīng)濟(jì)效益、社會(huì)效益和生態(tài)效益,以流域綜合效益最大作為目的,利用農(nóng)作物種植構(gòu)造
4、的多目的模糊優(yōu)化模型原理,建立作物種植構(gòu)造的多目的模糊優(yōu)化模型,經(jīng)過(guò)確立的目的函數(shù),在面積和水量2個(gè)約束條件對(duì)目的函數(shù)進(jìn)展求解,從而確定了流域綜合效益最大下的主要作物種植面積?!居⑽恼縎hiyang River Basin, which is located in the northwest arid region, is one of the main basins where there exists water shortage. Water demand bases mainly on agricultural irrigation in the basin, which of e
5、ach industry constantly varies as the climate changes and the population increases in recent years. Water shortage certainly leads to the bad phenomenon that the departments of water consumption fight for water. Therefore, it is necessary to conduct the study of agricultural water requirements and o
6、ptimal allocation of water resources in order to realize the aim of sustainable development. In the paper, agricultural water use in the basin was studied by collected data, concluding the following results:(1)Meteorological data and crop data collected were used to establish the model of agricultur
7、al water demand prediction on the basis of 11 factors influencing agricultural water demand in Minqin, Tianzhu and the whole basin. The accuracy of the model was superior by testing.(2)There needed a large number of data to establish BP neural network model, which brought about tedious operation. Th
8、e correlation analysis of 11 factors was conducted that influenced agricultural water requirements so as to forecast agricultural water demand in the cases of fewer data. Then these factors and the correlation of agricultural water demand were determined as well as the most important factors affecti
9、ng the water requirements of the basin, that is, cultivated area and precipitation. 6 factors that obviously influencing water demand were also ascertained, namely cultivated area, precipitation, food crop area, accumulated temperature, sunshine and the average annual maximum temperature.(3)The hexa
10、tomic linear regression models of water requirements were established on the basis of 6 main factors multiple regression analysis by multiple regression analysis. The influencing factors were further optimized, thereby setting up binary linear regression model and BP neural network based on the two
11、best important factors. And five-year data from 1999 to 2003 were used to check up the accuracy, which proved that the prediction effect of BP neural network model was better than that of binary linear regression model.(4)The grey model, exponential smoothing model and their combined model were used
12、 to predict water demand. The forecasting model was built in the Shiyang River Basin by analyzing agricultural water requirements over the years. The precision of the three models was tested. Then it was dictated that the absolute of the average relative error of grey model was 4.84percent, binary e
13、xponential smoothing model 6.14percent and the combined model, the minimum of the three, 4.04percent. The combined model ascertained was utilized to predict the agricultural water demand in the basin in the coming 10 years. The prediction value in 2004 was 17.677108m3, and it reached 19.178108m3 in
14、2021.(5)Economic benefit, social benefit and ecological benefit were taken into account and the maximum comprehensive benefit was its final objective. The theory of the multi-objective fuzzy optimal model of the crop planting structure was used to establish the multi-objective fuzzy optimal model of
15、 the crop planting structure. The object function was solved by the object function established in the two conditionsarea and water yield. Thus, the main crop planting area was determined in the condition of the maximum comprehensive benefit.【關(guān)鍵詞】BP神經(jīng)網(wǎng)絡(luò) 組合預(yù)測(cè)模型 水資源優(yōu)化配置 農(nóng)業(yè)需水量【英文關(guān)鍵詞】BP neural network c
16、ombined prediction model optimal allocation of water resources agricultural water demand【目錄】石羊河流域農(nóng)業(yè)需水量預(yù)測(cè)及水資源優(yōu)化配置研討摘要5-6ABSTRACT6-7第一章 緒論10-171.1 研討背景及意義10-111.1.1 研討的背景10-111.1.2 研討意義111.2 需水量預(yù)測(cè)的研討進(jìn)展11-131.2.1 國(guó)外研討現(xiàn)狀11-121.2.2 國(guó)內(nèi)研討現(xiàn)狀12-131.3 農(nóng)業(yè)水資源優(yōu)化配置的研討進(jìn)展13-151.4 研討內(nèi)容、方法與技術(shù)道路15-171.4.1 研討內(nèi)容和方法151.4
17、.2 相關(guān)資料搜集151.4.3 技術(shù)道路圖15-17第二章 流域農(nóng)業(yè)需水量影響要素的變化分析17-242.1 研討區(qū)概略17-182.1.1 自然地理情況172.1.2 水資源情況17-182.1.3 農(nóng)作物種植情況182.2 流域典型區(qū)域的選取18-192.3 流域農(nóng)業(yè)需水量影響要素的變化19-242.3.1 作物種植面積的變化19-202.3.2 氣候資料的變化20-24第三章 基于BP 神經(jīng)網(wǎng)絡(luò)的農(nóng)業(yè)需水量預(yù)測(cè)24-303.1 模型引見(jiàn)24-263.2 建立預(yù)測(cè)模型263.3 模型精度的檢驗(yàn)26-293.4 本章小結(jié)29-30第四章 基于回歸分析的農(nóng)業(yè)需水量預(yù)測(cè)30-364.1 流域農(nóng)業(yè)需水量影響要素的相關(guān)性分析30-324.2 多元線性回歸分析324.2.1 回歸分析的原理324.2.2 多元線性回歸數(shù)學(xué)模型324.3 六元線性回歸32-334.4 二元線性回歸334.5 兩種模型的精度比較33-344.6 本章小結(jié)34-36第五章 基于組合模型的農(nóng)業(yè)需水量預(yù)測(cè)36-425.1 灰色預(yù)測(cè)模型36-375.2 指數(shù)預(yù)測(cè)模型37-385.2.1 一次指數(shù)平滑模型37-385.2.2 二次指數(shù)平滑模型385.2.3 三次指數(shù)平滑模型385.3 組合預(yù)測(cè)模型38-395.4 農(nóng)業(yè)需水量預(yù)測(cè)39-415.4.1 灰色預(yù)測(cè)395.4.2 指數(shù)平
溫馨提示
- 1. 本站所有資源如無(wú)特殊說(shuō)明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請(qǐng)下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請(qǐng)聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁(yè)內(nèi)容里面會(huì)有圖紙預(yù)覽,若沒(méi)有圖紙預(yù)覽就沒(méi)有圖紙。
- 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 人人文庫(kù)網(wǎng)僅提供信息存儲(chǔ)空間,僅對(duì)用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理,對(duì)用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對(duì)任何下載內(nèi)容負(fù)責(zé)。
- 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請(qǐng)與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時(shí)也不承擔(dān)用戶因使用這些下載資源對(duì)自己和他人造成任何形式的傷害或損失。
最新文檔
- 2025年機(jī)電工程核心知識(shí)點(diǎn)及試題及答案
- 軟考網(wǎng)絡(luò)工程師備考過(guò)程中應(yīng)注意的陷阱試題及答案
- 嵌入式硬件設(shè)計(jì)的規(guī)范試題及答案
- 2025年信息項(xiàng)目管理普及試題及答案
- 軟件設(shè)計(jì)師考試相關(guān)知識(shí)的深度挖掘試題及答案
- 網(wǎng)絡(luò)故障應(yīng)急處理試題及答案
- 全面理解軟件項(xiàng)目中的質(zhì)量管理過(guò)程試題及答案
- 汽車資訊自媒體行業(yè)深度調(diào)研及發(fā)展項(xiàng)目商業(yè)計(jì)劃書
- 殘疾人技能展示行業(yè)跨境出海項(xiàng)目商業(yè)計(jì)劃書
- 民族音樂(lè)會(huì)行業(yè)深度調(diào)研及發(fā)展項(xiàng)目商業(yè)計(jì)劃書
- 醫(yī)療機(jī)構(gòu)工作人員廉潔從業(yè)九項(xiàng)準(zhǔn)則自查自糾報(bào)告
- (正式版)JC∕T 60021-2024 石膏基自流平砂漿應(yīng)用技術(shù)規(guī)程
- 組織行為學(xué)考試題(附參考答案)
- 日雜店購(gòu)銷合同清單
- 非遺文化傳承課件
- 中空工序作業(yè)指導(dǎo)書
- 小程序合作協(xié)議書
- 天津市濱海新區(qū)2022-2023學(xué)年高二下學(xué)期期末數(shù)學(xué)試題(學(xué)生版)
- 2024年重慶市中考物理試卷真題A卷(含答案逐題解析)
- 交通安全與事故預(yù)防智慧樹(shù)知到期末考試答案章節(jié)答案2024年山東理工大學(xué)
- 資料員《專業(yè)管理實(shí)務(wù)》知識(shí)點(diǎn)必考必練試題庫(kù)200題(含詳解)
評(píng)論
0/150
提交評(píng)論