Prediction of soil macro- and micro-elements in sieved and ground air-dried soils using laboratory-based hyperspectral imaging technique
作者： Mohammad Malmir , Iman Tahmasbian , Zhihong Xu , Michael B. Farrar , Shahla Hosseini Bai
DOI: 10.1016/J.GEODERMA.2018.12.049
关键词: Zinc 、 Soil water 、 Manganese 、 Soil texture 、 Phosphorus 、 Soil science 、 Materials science 、 Hyperspectral imaging 、 Soil test 、 Partial least squares regression
摘要: Abstract Hyperspectral image analysis in laboratory-based settings has the potential to estimate soil elements. This study aimed explore effects of particle size on element estimation using visible-near infrared (400–1000 nm) hyperspectral imaging. Images were captured from 116 sieved and ground samples. Data acquired images (HSI) used develop partial least square regression (PLSR) models predict available aluminum (Al), boron (B), calcium (Ca), copper (Cu), iron (Fe), potassium (K), magnesium (Mg), manganese (Mn), sodium (Na), phosphorus (P) zinc (Zn). The Al, Fe, K, Mn, Na P not predicted with high precision. However, developed PLSR B (R2CV = 0.62 RMSECV = 0.15), Ca (R2CV = 0.81 RMSECV = 260.97), Cu (R2CV = 0.74 RMSECV = 0.27), Mg (R2CV = 0.80 RMSECV = 43.71) Zn (R2CV = 0.76 RMSECV = 0.97) soils. reflectance also for (R2CV = 0.53 RMSECV = 0.16), RMSECV = 260.79), (R2CV = 0.73 RMSECV = 0.29), (R2CV = 0.79 RMSECV = 45.45) RMSECV = 0.97). RMSE different models, soils corresponding elements did significantly differ based Levene's test. Therefore, this indicated that it was necessary grind samples HSI.
harvard.edu
sci-hub.se 参考文章(76)
Ingunn Burud, Christophe Moni, Andreas Flo, Cecilia Futsaether, Markus Steffens, Daniel P. Rasse, Qualitative and quantitative mapping of biochar in a soil profile using hyperspectral imaging. Soil & Tillage Research. ,vol. 155, pp. 523- 531 ,(2016) , 10.1016/J.STILL.2015.06.020
Mohammed Kamruzzaman, Yoshio Makino, Seiichi Oshita, Rapid and non-destructive detection of chicken adulteration in minced beef using visible near-infrared hyperspectral imaging and machine learning Journal of Food Engineering. ,vol. 170, pp. 8- 15 ,(2016) , 10.1016/J.JFOODENG.2015.08.023
Bo Stenberg, Raphael A. Viscarra Rossel, Abdul Mounem Mouazen, Johanna Wetterlind, Visible and near infrared spectroscopy in soil science Advances in Agronomy. ,vol. 107, pp. 163- 215 ,(2010) , 10.1016/S0065-2113(10)07005-7
C. Verpoorter, V. Carrère, J.-P. Combe, Visible, near‐infrared spectrometry for simultaneous assessment of geophysical sediment properties (water and grain size) using the Spectral Derivative–Modified Gaussian Model Journal of Geophysical Research. ,vol. 119, pp. 2098- 2122 ,(2014) , 10.1002/2013JF002969
P. R. S. Vendrame, R. L. Marchão, D. Brunet, T. Becquer, The potential of NIR spectroscopy to predict soil texture and mineralogy in Cerrado Latosols European Journal of Soil Science. ,vol. 63, pp. 743- 753 ,(2012) , 10.1111/J.1365-2389.2012.01483.X
Agnar Höskuldsson, PLS regression methods Journal of Chemometrics. ,vol. 2, pp. 211- 228 ,(1988) , 10.1002/CEM.1180020306
Per Stenborg, JoséA.M. Demattê, Suzana Romeiro Araújo, Mats Söderström, Jan Eriksson, Christian Isendahl, Determining soil properties in Amazonian Dark Earths by reflectance spectroscopy Geoderma. ,vol. 237, pp. 308- 317 ,(2015) , 10.1016/J.GEODERMA.2014.09.014
Cécile Gomez, Philippe Lagacherie, Guillaume Coulouma, Regional predictions of eight common soil properties and their spatial structures from hyperspectral Vis–NIR data Geoderma. ,vol. 189-190, pp. 176- 185 ,(2012) , 10.1016/J.GEODERMA.2012.05.023
Yunzhao Wu, Jun Chen, Xinmin Wu, Qingjiu Tian, Junfeng Ji, Zhihao Qin, Possibilities of reflectance spectroscopy for the assessment of contaminant elements in suburban soils Applied Geochemistry. ,vol. 20, pp. 1051- 1059 ,(2005) , 10.1016/J.APGEOCHEM.2005.01.009
Ji Wenjun, Shi Zhou, Huang Jingyi, Li Shuo, In situ measurement of some soil properties in paddy soil using visible and near-infrared spectroscopy. PLOS ONE. ,vol. 9, ,(2014) , 10.1371/JOURNAL.PONE.0105708