Chemometric soil analysis on the determination of specific bands for the detection of magnesium and potassium by spectroscopy

Demattê, José Alexandre Melo; López, Luciano Espino; Marques, Karina Patrícia Prazeres; Rodella, Arnaldo Antonio

doi:10.1016/j.geoderma.2016.11.013

Cited by 37 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The prediction accuracy for SOM content in this study was comparable and often better than the accuracies obtained by other techniques for SOC and SOM with R 2 values of 0.81 [81], 0.74 [82], 0.67 [83], and 0.81 [84]. There are two challenges in the application of LIBS C line to quantitative analysis of SOM content: (1) interference from Fe lines; and (2) interference from inorganic carbon in the soil. The interference by Fe lines can be easily reduced using multivariate methods.…”

Section: Somsupporting

confidence: 64%

“…The traditional agricultural production system is facing a great challenge of meeting the human demand for food due to the rapid increase in world population [1,2]. It is generally accepted that developing precision agriculture, based on real-time monitoring of soil fertility, crop growth, and environmental change to increase grain production, plays a vital role in alleviating the pressure of grain demand [3,4].…”

Section: Introductionmentioning

confidence: 99%

“…The built model was then used for the prediction of soil properties according to the soil LIBS spectra. The specific objectives of this study are: (1) to simultaneously predict soil properties and nutrients in various types of farmland soils using the LIBS technique and (2) to compare the prediction accuracies of full LIBS spectra and characteristic LIBS spectral lines for various soil properties and nutrients.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast and Simultaneous Determination of Soil Properties Using Laser-Induced Breakdown Spectroscopy (LIBS): A Case Study of Typical Farmland Soils in China

et al. 2019

Soil Syst.

View full text Add to dashboard Cite

Accurate management of soil nutrients and fast and simultaneous acquisition of soil properties are crucial in the development of sustainable agriculture. However, the conventional methods of soil analysis are generally labor-intensive, environmentally unfriendly, as well as time- and cost-consuming. Laser-induced breakdown spectroscopy (LIBS) is a “superstar” technique that has yielded outstanding results in the elemental analysis of a wide range of materials. However, its application for analysis of farmland soil faces the challenges of matrix effects, lack of large-scale soil samples with distinct origin and nature, and problems with simultaneous determination of multiple soil properties. Therefore, LIBS technique, in combination with partial least squares regression (PLSR), was applied to simultaneously determinate soil pH, cation exchange capacity (CEC), soil organic matter (SOM), total nitrogen (TN), total phosphorus (TP), total potassium (TK), available phosphorus (AP), and available potassium (AK) in 200 soils from different farmlands in China. The prediction performances of full spectra and characteristic lines were evaluated and compared. Based on full spectra, the estimates of pH, CEC, SOM, TN, and TK achieved excellent prediction abilities with the residual prediction deviation (RPDV) values > 2.0 and the estimate of TP featured good performance with RPDV value of 1.993. However, using characteristic lines only improved the predicted accuracy of SOM, but reduced the prediction accuracies of TN, TP, and TK. In addition, soil AP and AK were predicted poorly with RPDV values of < 1.4 based on both full spectra and characteristic lines. The weak correlations between conventionally analyzed soil AP and AK and soil LIBS spectra are responsible for the poor prediction abilities of AP and AK contents. Findings from this study demonstrated that the LIBS technique combined with multivariate methods is a promising alternative for fast and simultaneous detection of some properties (i.e., pH and CEC) and nutrient contents (i.e., SOM, TN, TP, and TK) in farmland soils because of the extraordinary prediction performances achieved for these attributes.

show abstract

Section: Somsupporting

confidence: 64%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast and Simultaneous Determination of Soil Properties Using Laser-Induced Breakdown Spectroscopy (LIBS): A Case Study of Typical Farmland Soils in China

et al. 2019

Soil Syst.

View full text Add to dashboard Cite

show abstract

“…Soil VIS-NIR spectra often contain redundant wavelength information and can increase the model complexity [23,24,58,59]. It could be observed that the SVM models based on the selected spectral variables yielded superior model performance relative to the full-spectrum SVM models for SOM, regardless of FOD transformations (Tables 1 and 2 and Figure 12b).…”

Section: Discussionmentioning

confidence: 97%

Combining Fractional Order Derivative and Spectral Variable Selection for Organic Matter Estimation of Homogeneous Soil Samples by VIS–NIR Spectroscopy

Hong

Chen

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Visible and near-infrared (VIS-NIR) spectroscopy has been extensively applied to estimate soil organic matter (SOM) in the laboratory. However, if field/moist VIS-NIR spectra can be directly applied to estimate SOM, then much of the time and labor would be avoided. Spectral derivative plays an important role in eliminating unwanted interference and optimizing the estimation model. Nonetheless, the conventional integer order derivatives (i.e., the first and second derivatives) may neglect some detailed information related to SOM. Besides, the full-spectrum generally contains redundant spectral variables, which would affect the model accuracy. This study aimed to investigate different combinations of fractional order derivative (FOD) and spectral variable selection techniques (i.e., competitive adaptive reweighted sampling (CARS), elastic net (ENET) and genetic algorithm (GA)) to optimize the VIS-NIR spectral model of moist soil. Ninety-one soil samples were collected from Central China, with their SOM contents and reflectance spectra measured. Support vector machine (SVM) was applied to estimate SOM. Results indicated that moist spectra differed greatly from dried ground spectra. With increasing order of derivative, the spectral resolution improved gradually, but the spectral strength decreased simultaneously. FOD could provide a better tool to counterbalance the contradiction between spectral resolution and spectral strength. In full-spectrum SVM models, the most accurate estimation was achieved by SVM model based on 1.5-order derivative spectra, with validation R 2 = 0.79 and ratio of the performance to deviation (RPD) = 2.20. Of all models studied (different combinations of FOD and variable selection techniques), the highest validation model accuracy for SOM was achieved when applying 1.5 derivative spectra and GA method (validation R 2 = 0.88 and RPD = 2.89). Among the three variable selection techniques, overall, the GA method yielded the optimal predictability. However, due to its long computation time, one alternative was to use CARS method. The results of this study confirm that a suitable combination of FOD and variable selection can effectively improve the model performance of SOM in moist soil.

show abstract

“…Já a Organização Internacional para Padronização (ISO, acrônimo em inglês) por meio de sua norma 20473 de 2007, define a região visível do espectro entre 400 e 780 nm e subdivide o infravermelho em três partes, sendo: a) infravermelho próximo (NIR): 780 -3.000 nm; b) infravermelho médio (MIR): 3.000 -50.000; c) infravermelho distante (FIR): 50.000 -1.000.000 nm. Na ciência do solo é comum ainda subdividir os espectros como: a) visível (vis): 400 -800 nm; b) infravermelho próximo (NIR): 800 -1.100; c) infravermelho de ondas curtas (SWIR): 1.100 -2.500 nm (LUGASSI et al, 2014;DEMATTÊ et al, 2017).…”

Section: Espectroscopia De Reflectância Vis-nirunclassified

Sensoriamento proximal de solo para a quantificação de atributos químicos e físicos

Eitelwein¹

View full text Add to dashboard Cite

Proximal soil sensing: quantification of physical and chemical soil attributes The objective of this work was to investigate soil sensing techniques and to analyze the potential for their use directly in the field. Four distinct steps were developed to meet the following objectives: a) to compare and evaluate the potential of predicting soil attributes with three portable spectrometers (vis-NIR) in a controlled environment; B) to evaluate the on-the-go prediction of pH, P and K using optical sensors (vis-NIR reflectance) and electrochemical techniques (ion-selective pH and K electrodes) in an experimental area with induced variability; C) assemble and test a field platform with electrical, electrochemical and optical sensors; D) to evaluate the potential of predicting soil texture using a portable X-ray fluorescence spectroscopy equipment. In the first step the vis-NIR spectral reflectance readings of the three equipments evaluated were very similar, with correlation coefficients above 0.86 in the 400 to 1800 nm range. When compared in this spectral region, the equipment produced very similar prediction models, with slight superiority for the FieldSpec system. The models showed to be more promising for the prediction of soil texture in relation to chemical attributes. In the second step the field readings using ion-selective pH and K electrodes presented a high correlation with the laboratory analyzes. The evaluations showed that soil conditions with low moisture significantly affect the readings. Despite the high correlation, the field values need to be corrected for the desired laboratory methodology. Prediction models of P, K and pH using field-vis-NIR spectrometry showed low precision. The tests of the Multisensors Soil Platform (MSP) in the third stage demonstrated that it is possible to use electric, electrochemical and optical sensors in the same platform. The electrical conductivity (EC) readings showed that this parameter was related with soil texture, acting as an indicator of variability and allowing the identification of texture transitions. The pH measured by MSP exhibited correlations below those verified in the second step. However, some atypical results were verified, such as the higher correlation between pH in CaCl 2 and MSP than in H 2 O. The vis-NIR reflectance readings using the MSP resulted in good sand and clay prediction models, allowing the creation of high resolution maps of these parameters. Portable X-ray fluorescence spectroscopy was efficient for estimating soil texture. The sand and clay contents were estimated both by simple linear regressions and multiple regressions with R² values above 0.60. Total Fe was the main element used in these regression models.

show abstract

Chemometric soil analysis on the determination of specific bands for the detection of magnesium and potassium by spectroscopy

Cited by 37 publications

References 37 publications

Fast and Simultaneous Determination of Soil Properties Using Laser-Induced Breakdown Spectroscopy (LIBS): A Case Study of Typical Farmland Soils in China

Fast and Simultaneous Determination of Soil Properties Using Laser-Induced Breakdown Spectroscopy (LIBS): A Case Study of Typical Farmland Soils in China

Combining Fractional Order Derivative and Spectral Variable Selection for Organic Matter Estimation of Homogeneous Soil Samples by VIS–NIR Spectroscopy

Sensoriamento proximal de solo para a quantificação de atributos químicos e físicos

Contact Info

Product

Resources

About