基于星载高光谱数据的南京新济洲湿地土壤有机质估测研究
发布时间：2019-01-01 18:18
【摘要】：在高光谱数据预处理、土壤有机质高光谱敏感波段提取基础上,建立多元线性回归、最邻近法、装袋算法、多元感知器、随机森林5种遥感估测模型。用10折交叉验证方法,借助相关系数、绝对误差、均方根误差、相对误差、相对均方根误差5个指标,对遥感估测模型结果进行精度评价,选择精度最高的模型进行湿地土壤有机质遥感估测和空间分析。结果表明:土壤有机质高光谱敏感波段主要集中在925、1 144、1 477、1 780 nm 4个波段;在预测土壤有机质的5种模型中,多元线性回归模型预测精度最高,随机森林次之;土壤有机质空间分布呈现由洲滩中间向四周逐渐增加的带状分布格局;新济洲沼泽地土壤有机质含量最高,为2.22%;靠近沼泽的林地次之;植被覆盖度较低的农地和裸地的土壤有机质最低,为0.43%;这种土壤有机质空间分布格局与研究区土壤类型的带状分布存在密切联系。
[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.
【作者单位】： 南京林业大学林学院;
【基金】：国家自然科学基金项目(31170679)资助 江苏高等学校大学生创新创业训练计划项目(201510298051Z)资助 江苏高校品牌专业建设工程项目(TAPP,PPZY2015A062)资助
【分类号】：S153.621
本文编号：2397936
[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.
【作者单位】： 南京林业大学林学院;
【基金】：国家自然科学基金项目(31170679)资助 江苏高等学校大学生创新创业训练计划项目(201510298051Z)资助 江苏高校品牌专业建设工程项目(TAPP,PPZY2015A062)资助
【分类号】：S153.621
【相似文献】
相关博士学位论文 前2条
1 姜利;九宫山垂直带土壤有机质矿化特征及其稳定性机制[D];华中农业大学;2016年
2 汤水荣;日本东北地区稻田土壤有机质和秸秆分解的温度敏感性以及对水分的响应[D];华中农业大学;2017年
相关硕士学位论文 前2条
1 王磊;基于成像光谱技术的耕地土壤有机质遥感监测方法研究[D];河南理工大学;2016年
2 邓文悦;长期施肥对江西稻田土壤有机质与土壤微生物功能多样性的影响[D];西北大学;2017年
，本文编号：2397936
本文链接：https://www.wllwen.com/kejilunwen/nykj/2397936.html
