偏最小二乘回归
土壤水分
线性回归
校准
相关系数
决定系数
回归分析
土工试验
环境科学
化学
数学
分析化学(期刊)
土壤科学
矿物学
环境化学
统计
作者
Vahagn Muradyan,Garegin Tepanosyan,Shushanik Asmaryan,Lilit Sahakyan,Armen Saghatelyan,Timothy A. Warner
摘要
Aim of this study is to predict heavy metal (HM) concentrations in soils and plants using field remote sensing methods. The studied sites were an industrial town of Kajaran and city of Yerevan. The research also included sampling of soils and leaves of two tree species exposed to different pollution levels and determination of contents of HM in lab conditions. The obtained spectral values were then collated with contents of HM in Kajaran soils and the tree leaves sampled in Yerevan, and statistical analysis was done. Consequently, Zn and Pb have a negative correlation coefficient (p <0.01) in a 2498 nm spectral range for soils. Pb has a significantly higher correlation at red edge for plants. A regression models and artificial neural network (ANN) for HM prediction were developed. Good results were obtained for the best stress sensitive spectral band ANN (R2~0.9, RPD~2.0), Simple Linear Regression (SLR) and Partial Least Squares Regression (PLSR) (R2~0.7, RPD~1.4) models. Multiple Linear Regression (MLR) model was not applicable to predict Pb and Zn concentrations in soils in this research. Almost all full spectrum PLS models provide good calibration and validation results (RPD>1.4). Full spectrum ANN models are characterized by excellent calibration R2, rRMSE and RPD (0.9; 0.1 and >2.5 respectively). For prediction of Pb and Ni contents in plants SLR and PLS models were used. The latter provide almost the same results. Our findings indicate that it is possible to make coarse direct estimation of HM content in soils and plants using rapid and economic reflectance spectroscopy.
科研通智能强力驱动
Strongly Powered by AbleSci AI