Jeehwan Bae : Paper of the week & Book of the month

Author  :  Moura-Bueno, J. M. Dalmolin, R. S. D. ten Caten, A. Dotto, A. C. Dematte, J. A. M. Year  : 2019 Title  :  Stratification of a local VIS-NIR-SWIR spectral library by homogeneity criteria yields more accurate soil organic carbon predictions Journal  :  Geoderma Comment   :    The aim of this research was to  i) characterize and identify differences among spectra obtained for subtropical soils samples, ii)  evaluate different pre-processing techniques and multivariate methods to propose SOC prediction models from  the spectral data and iii) evaluate the performance of SOC prediction models calibrated from the stratification of  a local library.  Spectral reflectance measurements were performed in the  laboratory with a spectroradiometer in the range of 350–2500 nm. Six pre-processing techniques were applied to  the spectra (including derivatives, normalization and non-linea...

Author  :  Tümsavaş Zeynal,  Tekin Yücel,  Ulusoy Yahya,  Mouazen Abdul M Year  : 2019 Title  :  Prediction and mapping of soil clay and sand contents using visible and near-infrared spectroscopy Journal  :  Biosystems engineering Comment   :    The aim of this research was to examine the potential of visible and near infrared (Vis -NIR) spectroscopy for the prediction and mapping of sand and clay fractions of soils.  This study demonstrated that soil sand and clay can be successfully  measured and mapped using Vis-NIR spectroscopy under both laboratory and  on-line scanning conditions.  A partial least squares  (PLS)  regression with leave-one-out  cross-validation analysis was carried out using the calibration set, and the resulting  model prediction ability was tested using the prediction set.   Models developed were used  to predict sand and ...

Author  :  Soltani, I.  Fouad, Y.  Michot, D.  Breger, P.  Dubois, R.  Cudennec, C. Year  : 2019 Title  :  A near infrared index to assess effects of soil texture and organic carbon content on soil water content Journal  :  European Journal of Soil Science Comment   :   Characterization of soil hydrodynamic properties is important for assessing the soil water regime. Over the last decades, diffuse reflectance spectroscopy (DRS)  techniques have been used increasingly. Methods based on DRS  offer several advantages compared with conventional ones because  they are rapid, cost-effective and non-destructive. Therefore, the  spread within the soil science community of soil spectroscopy in  the visible (vis), near (NIR) and mid-infrared (MIR) spectral ranges  enabled various physical, chemical and biological soil properties to  be assessed.  Spectra were con...

Author  :  Meihua Yang, Dongyun Xu, Songchao Chen, Hongyi Li  and Zhou Shi Year  : 2019 Title  :  Evaluation of Machine Learning Approaches to  Predict Soil Organic Matter and pH Using  vis-NIR Spectra Journal  :  Sensors Comment   :   Visible-near infrared (vis-NIR) spectroscopy with multivariate calibration can be used to effectively estimate soil properties. In this study, 523 soil samples were collected from paddy fields in the Yangtze Plain, China.  Four machine learning approaches—partial least squares regression (PLSR), least squares-support vector machines (LS-SVM), extreme learning machines (ELM) and the Cubist regression model (Cubist)—were used to compare the prediction accuracy based on vis-NIR full bands and bands reduced using the genetic algorithm (GA). The coefficient of determination (R2), root mean square error (RMSE), and ratio of performance to inter-quartile distance (RPIQ) we...

Author  :  Wenjuan Sun, Xinju Li, Beibei Niu Year  : 2018 Title  :  Prediction of soil organic carbon in a coal  mining area by Vis-NIR spectroscopy Journal  :  PLOS one Comment   :   Visible-near infrared (Vis-NIR) spectroscopy has been shown to be a rapid, timely and efficient tool for the prediction of soil organic carbon (SOC).   In this study, 104 soil samples were collected from the Baodian mining area of Shandong province. Vis-NIR reflectance spectra and SOC content were then measured under laboratory conditions.   The spectral data were first denoised using the Savitzky-Golay (SG) convolution smoothing method or the multiple scattering correction (MSC) method, after which the spectral reflectance (R) was subjected to reciprocal, reciprocal logarithm and differential transformations to improve spectral sensitivity.   Finally, regression models for estimating the SOC c...

Author  :  Eleanor Hobley, Markus Steffens, Sara L. Bauke & Ingrid Kögel-Knabner Year  : 2018 Title  :  Hotspots of soil organic carbon  storage revealed by laboratory  hyperspectral imaging Journal  :  Scientific Reports Comment   :   They tested the application  of laboratory hyperspectral imaging with a variety of machine learning approaches to predict OC  distribution in undisturbed soil cores.  Despite a  large increase in variance and reduction in OC content with increasing depth, the high resolution of the  images enabled statistically powerful analysis in spatial distribution of OC in the soil cores.  Laboratory hyperspectral imaging enables  powerful, fine-scale investigations of the vertical distribution of soil OC as well as hotspots of OC  storage in undisturbed samples, overcoming limitations of traditional soil sampling campaigns.