【摘要】：在高光譜數(shù)據(jù)預(yù)處理、土壤有機(jī)質(zhì)高光譜敏感波段提取基礎(chǔ)上,建立多元線性回歸、最鄰近法、裝袋算法、多元感知器、隨機(jī)森林5種遙感估測模型。用10折交叉驗(yàn)證方法,借助相關(guān)系數(shù)、絕對誤差、均方根誤差、相對誤差、相對均方根誤差5個指標(biāo),對遙感估測模型結(jié)果進(jìn)行精度評價,選擇精度最高的模型進(jìn)行濕地土壤有機(jī)質(zhì)遙感估測和空間分析。結(jié)果表明:土壤有機(jī)質(zhì)高光譜敏感波段主要集中在925、1 144、1 477、1 780 nm 4個波段;在預(yù)測土壤有機(jī)質(zhì)的5種模型中,多元線性回歸模型預(yù)測精度最高,隨機(jī)森林次之;土壤有機(jī)質(zhì)空間分布呈現(xiàn)由洲灘中間向四周逐漸增加的帶狀分布格局;新濟(jì)洲沼澤地土壤有機(jī)質(zhì)含量最高,為2.22%;靠近沼澤的林地次之;植被覆蓋度較低的農(nóng)地和裸地的土壤有機(jī)質(zhì)最低,為0.43%;這種土壤有機(jī)質(zhì)空間分布格局與研究區(qū)土壤類型的帶狀分布存在密切聯(lián)系。
[Abstract]:On the basis of preprocessing of hyperspectral data and extraction of hyperspectral sensitive bands of soil organic matter, five kinds of remote sensing estimation models including multivariate linear regression, nearest neighbor method, bagging algorithm, multivariate perceptron and random forest were established. The accuracy of remote sensing estimation model was evaluated by 10 fold cross validation method with the help of five indexes: correlation coefficient, absolute error, root mean square error and relative root mean square error. The model with the highest precision was selected to estimate the soil organic matter in wetland by remote sensing and spatial analysis. The results showed that the hyperspectral sensitive bands of soil organic matter were mainly located in the four bands of 925 ~ (14) ~ (44) ~ (14) ~ (7) ~ (7) ~ 1 780 nm, among the 5 models for predicting soil organic matter, the multivariate linear regression model had the highest prediction accuracy, followed by the random forest. The spatial distribution of soil organic matter showed a zonal distribution pattern gradually increasing from the middle to the periphery of the beach, the content of soil organic matter in the swamp of Xinji Island was the highest (2.22), and the forest land near the marsh was the second. The soil organic matter of farmland with low vegetation coverage and bare land was the lowest, which was 0.43. The spatial distribution pattern of soil organic matter was closely related to the zonal distribution of soil types in the study area.
【作者單位】： 南京林業(yè)大學(xué)林學(xué)院;
【基金】：國家自然科學(xué)基金項(xiàng)目(31170679)資助 江蘇高等學(xué)校大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練計劃項(xiàng)目(201510298051Z)資助 江蘇高校品牌專業(yè)建設(shè)工程項(xiàng)目(TAPP,PPZY2015A062)資助
【分類號】：S153.621

【相似文獻(xiàn)】

相關(guān)博士學(xué)位論文 前2條

1 姜利;九宮山垂直帶土壤有機(jī)質(zhì)礦化特征及其穩(wěn)定性機(jī)制[D];華中農(nóng)業(yè)大學(xué);2016年

2 湯水榮;日本東北地區(qū)稻田土壤有機(jī)質(zhì)和秸稈分解的溫度敏感性以及對水分的響應(yīng)[D];華中農(nóng)業(yè)大學(xué);2017年

相關(guān)碩士學(xué)位論文 前2條

1 王磊;基于成像光譜技術(shù)的耕地土壤有機(jī)質(zhì)遙感監(jiān)測方法研究[D];河南理工大學(xué);2016年

2 鄧文悅;長期施肥對江西稻田土壤有機(jī)質(zhì)與土壤微生物功能多樣性的影響[D];西北大學(xué);2017年

，

本文編號：2397936