引用文章

基于水稻冠层高光谱的叶片SPAD值估算模型研究


@article{J2010143,
	author = { 孙小香 至  王芳东 至  郭熙 至  赵小敏 至  谢文},
	title = {基于水稻冠层高光谱的叶片SPAD值估算模型研究},
	journal = {江西农业大学学报},
	volume = {40},
	number = {03},
	year = {2018},
	keywords = {高光谱; 水稻; SPAD值; 主成分分析; 支持向量回归; 逐步多元线性回归},
	abstract = {分别为1.803、2.295。对比发现主成分分析结合支持向量机模型可以很好地预测叶片SPAD值。
        },

	url = {http://jxndxuebao.com/index.php/jxnydxxb/article/view/2010143},
	pages = {444--453}
}

@article{J2010143,
	author = {SUN Xiao-xiang and WANG Fang-dong and GUO Xi and ZHAO Xiao-min and XIE Wen},
	title = {The Estimation Models of Rice Leaf SPAD Value Based on Canopy Spectrum},
	journal = {ACTA AGRICULTURAE UNIVERSITATIS JIANGXIENSIS},
	volume = {40},
	number = {03},
	year = {2018},
	keywords = {hyper-spectrum; rice; SPAD value; principle component analysis; support vector regression; stepwise multiple linear regression},
	abstract = {=-0.834), respectively.Different models had different precision, RMSE of the CP-SMLR model and the CP-SVR model were 2.926 and 3.895, RPD were 2.064 and 1.55, respectively.RMSE of the PCA-SMLR model and the PCA-SVR model were 3.349 and 2.631, RPD were 1.803and 2.295, respectively.Among the tested models, the best prediction model for rice leaves SPAD value was PCA-SVR model which has high accuracy.
        },

	url = {http://jxndxuebao.com/index.php/jxnydxxb/article/view/2010143},
	pages = {444--453}
}

阅读工具

引用文章

基于水稻冠层高光谱的叶片SPAD值估算模型研究


@article{J2010143,
	author = { 孙小香 至  王芳东 至  郭熙 至  赵小敏 至  谢文},
	title = {基于水稻冠层高光谱的叶片SPAD值估算模型研究},
	journal = {江西农业大学学报},
	volume = {40},
	number = {03},
	year = {2018},
	keywords = {高光谱; 水稻; SPAD值; 主成分分析; 支持向量回归; 逐步多元线性回归},
	abstract = {分别为1.803、2.295。对比发现主成分分析结合支持向量机模型可以很好地预测叶片SPAD值。
        },

	url = {http://jxndxuebao.com/index.php/jxnydxxb/article/view/2010143},
	pages = {444--453}
}

@article{J2010143,
	author = {SUN Xiao-xiang and WANG Fang-dong and GUO Xi and ZHAO Xiao-min and XIE Wen},
	title = {The Estimation Models of Rice Leaf SPAD Value Based on Canopy Spectrum},
	journal = {ACTA AGRICULTURAE UNIVERSITATIS JIANGXIENSIS},
	volume = {40},
	number = {03},
	year = {2018},
	keywords = {hyper-spectrum; rice; SPAD value; principle component analysis; support vector regression; stepwise multiple linear regression},
	abstract = {=-0.834), respectively.Different models had different precision, RMSE of the CP-SMLR model and the CP-SVR model were 2.926 and 3.895, RPD were 2.064 and 1.55, respectively.RMSE of the PCA-SMLR model and the PCA-SVR model were 3.349 and 2.631, RPD were 1.803and 2.295, respectively.Among the tested models, the best prediction model for rice leaves SPAD value was PCA-SVR model which has high accuracy.
        },

	url = {http://jxndxuebao.com/index.php/jxnydxxb/article/view/2010143},
	pages = {444--453}
}