首页|基于高光谱的退化高寒草甸土壤碳氮磷含量反演研究

基于高光谱的退化高寒草甸土壤碳氮磷含量反演研究

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
以黄河源区为研究区域，选取退化高寒草甸作为研究样地，通过野外调查采样，结合室内土壤养分与土壤高光谱数据测量，分析退化高寒草甸土壤植被及养分特征，对土壤高光谱数据进行数学变换与土壤养分含量相关系数计算，采用偏最小二乘回归(PLSR)和反向传播神经网络(BPNN)方法分别建立土壤有机碳、全氮、全磷含量的反演模型。结果表明:PLSR建立的土壤有机碳和土壤全磷含量预测模型优于BPNN模型，预测效果更好，其中，土壤有机碳含量PLSR预测模型建模集R2=0。9585，RMSE=0。1079，验证集R2=0。9493，RMSE=0。1210，模型精度较高，可以进行准确估算，土壤全磷含量PLSR预测模型建模集R2=0。7497，RMSE=0。2391，验证集R2=0。5977，RMSE=0。2445，达到基本估算要求;BPNN建立的土壤全氮含量预测模型优于PLSR模型，其建模集R2=0。8772，RMSE=0。7663，验证集R2=0。6887，RMSE=0。8556，模型精度较好，达到基本估算要求。
Inversion of carbon,nitrogen and phosphorus contents in degraded alpine meadow soil based on hyperspectral analysis
The study took the Yellow River source area as the research area,the degraded alpine meadow was selected as the research sample site,the soil vegetation and nutrient characteristics of degraded alpine meadow were analyzed through field survey sampling,combined with indoor soil nutrient and soil hyperspectral data measurement,the mathematical transformation of soil hyperspectral data was performed and the correlation coefficient with soil nutrient content was calculated.The inverse models of soil organic carbon,total nitrogen and total phosphorus contents were established by partial least squares regression(PLSR)and back propagation neural network(BPNN)methods,respectively.The results showed that the soil organic carbon and soil total phosphorus content prediction models established by PLSR were better than the BPNN models,it had better prediction effects,in which the modeling set R2=0.9585 and RMSE=0.1079 for the PLSR prediction model of soil organic carbon content and the validation set R2=0.9493 and RMSE=0.1210 had higher model accuracy and could be accurately estimated.The modeling set R2=0.7497,RMSE=0.2391,validation set R2=0.5977,RMSE=0.2445 of the PLSR prediction model for total phosphorus content met the basic estimation requirements;The prediction model for total soil nitrogen content established by BPNN was better than the PLSR model with modeling set R2=0.8772,RMSE=0.7663,validation set R2=0.6887,RMSE=0.8556,the model accuracy was better and met the basic estimation requirements.

Yellow River source areadegraded alpine meadowsoil carbon,nitrogen and phosphorushyperspectral remote sensinginversion model

柴瑜、李希来、马盼盼、徐文印、段成伟、把熠晨

展开 >

青海大学农牧学院,青海 西宁 810016

黄河源区 退化高寒草甸 土壤碳氮磷 高光谱遥感 反演模型

国家自然科学基金项目青海省自然科学基金创新团队项目高等学校学科创新引智计划项目青海省科技创新创业团队项目

U21A201912020-ZJ-904D18013

2024

10.11838/sfsc.1673-6257.23436

中国土壤与肥料
中国农业科学院农业资源与农业区划研究所 中国植物营养与肥料学会

中国土壤与肥料

CSTPCD北大核心
影响因子：1.197
ISSN：1673-6257
年,卷(期)：2024.(6)