scholarly journals Deep Learning Application for Predicting Soil Organic Matter Content by VIS-NIR Spectroscopy

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Zhe Xu ◽  
Xiaomin Zhao ◽  
Xi Guo ◽  
Jiaxin Guo
Keyword(s):  
Organic Matter ◽  
Deep Learning ◽  
Infrared Spectroscopy ◽  
Soil Organic Matter ◽  
Near Infrared Spectroscopy ◽  
Spectral Reflectance ◽  
Near Infrared ◽  
Spectral Variation ◽  
Full Spectrum ◽  
Reflectance Data

Deep learning is characterized by its strong ability of data feature extraction. This method can provide unique advantages when applying it to visible and near-infrared spectroscopy for predicting soil organic matter (SOM) content in those cases where the SOM content is negatively correlated with the spectral reflectance of soil. This study relied on the SOM content data of 248 red soil samples and their spectral reflectance data of 400–2450 nm in Fengxin County, Jiangxi Province (China) to meet three objectives. First, a multilayer perceptron and two convolutional neural networks (LeNet5 and DenseNet10) were used to predict the SOM content based on spectral variation and variable selection, and the outcomes were compared with that from the traditional back-propagation neural network (BPN). Second, the four methods were applied to full-spectrum modeling to test the difference to selected feature variables. Finally, the potential of direct modeling was evaluated using spectral reflectance data without any spectral variation. The results of prediction accuracy showed that deep learning performed better at predicting the SOM content than did the traditional BPN. Based on full-spectrum data, deep learning was able to obtain more feature information, thus achieving better and more stable results (i.e., similar average accuracy and far lower standard deviation) than those obtained through variable selection. DenseNet achieved the best prediction result, with a coefficient of determination (R2) = 0.892 ± 0.004 and a ratio of performance to deviation (RPD) = 3.053 ± 0.056 in validation. Based on DenseNet, the application of spectral reflectance data (without spectral variation) produced robust results for application-level purposes (validation R2 = 0.853 ± 0.007 and validation RPD = 2.639 ± 0.056). In conclusion, deep learning provides an effective approach to predict the SOM content by visible and near-infrared spectroscopy and DenseNet is a promising method for reducing the amount of data preprocessing.

scholarly journals In situ near-infrared spectroscopy for soil organic matter prediction in paddy soil, Pasak watershed, Thailand

2018 ◽  
Vol 64 (No. 2) ◽  
pp. 70-75 ◽  
Author(s):  
Romsonthi Chutipong ◽  
Tawornpruek Saowanuch ◽  
Watana Sumitra
Keyword(s):  
Organic Matter ◽  
Infrared Spectroscopy ◽  
Soil Organic Matter ◽  
Soil Properties ◽  
Soil Quality ◽  
Near Infrared Spectroscopy ◽  
Spectral Reflectance ◽  
Near Infrared ◽  
Partial Least Square

Soil organic matter (SOM) is a major index of soil quality assessment because it is one of the key soil properties controlling nutrient budgets in agricultural production systems. The aim of the in situ near-infrared spectroscopy (NIRS) for SOM prediction in paddy area is evaluation of the potential of SOM and prediction of other soil properties. There are keys for soil fertility and soil quality assessments. A spectral reflectance of 130 soil samples was collected by field spectroradiometer in a region of near-infrared. Spectral reflectance collections were processed by the first derivative transformation with the Savitsky-Golay algorithms. Partial least square regression method was used to develop a calibration model between soil properties and spectral reflectance, which was used for prediction and validation processes. Finally, the results of this study demonstrate that NIRS is an effective method that can be used to predict SOM (R<sup>2</sup> = 0.73, RPD (ratio of performance to deviation) = 1.82) and total nitrogen (R<sup>2</sup> = 0.72, RPD = 1.78). Therefore, NIRS is a potential tool for soil properties predictions. The use of these techniques will facilitate the implementation of soil management with a decreasing cost and time of soil study in a large scale. However, further works are necessary to develop more accurate soil properties prediction and to apply this method to other areas.

Qualitative near infrared spectroscopy, a new tool to recognize past vegetation signature in soil organic matter

2015 ◽  
Vol 82 ◽  
pp. 127-134 ◽  
Author(s):  
Damien Ertlen ◽  
Dominique Schwartz ◽  
Didier Brunet ◽  
Jean-Michel Trendel ◽  
Pierre Adam ◽  
...  
Keyword(s):  
Organic Matter ◽  
Infrared Spectroscopy ◽  
Soil Organic Matter ◽  
Near Infrared Spectroscopy ◽  
Near Infrared

scholarly journals Analysis of soil organic matter in tropical soils with near-infrared spectroscopy (NIRS) and chemometrics

2012 ◽  
Vol 39 (2) ◽  
pp. 387-394
Author(s):  
Aarón Jarquín-Sánchez ◽  
Sergio Salgado-García ◽  
David J Palma-López ◽  
Wilder Camacho-Chiu
Keyword(s):  
Organic Matter ◽  
Infrared Spectroscopy ◽  
Soil Organic Matter ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Tropical Soils

scholarly journals Characterization of soil organic matter by near infrared spectroscopy – determination of glomalin in different soils

2016 ◽  
Author(s):  
Jiří Zbíral ◽  
David Čižmár ◽  
Stanislav Malý ◽  
Elena Obdržálková
Keyword(s):  
Organic Matter ◽  
Infrared Spectroscopy ◽  
Soil Organic Matter ◽  
Near Infrared Spectroscopy ◽  
Forest Soils ◽  
Near Infrared ◽  
Arable Land ◽  
Soil Samples ◽  
Calibration Model ◽  
Calibration Models

Abstract. Determining and characterizing soil organic matter (SOM) cheaply and reliably can help to support decisions concerning sustainable land management and climate policy. Glomalin, a glycoprotein produced by arbuscular mycorrhizal fungi, was recommended as a promising indicator of SOM quality. But extracting glomalin from and determining glomalin in soils using classical chemical methods is too complicated and time consuming and therefore limits the use of this parameter in large scale surveys. Near infrared spectroscopy (NIRS) is a very rapid, non-destructive analytical technique that can be used to determine many constituents of soil organic matter. Representative sets of 84 different soil samples from arable land and grasslands and 75 forest soils were used to develop reliable NIRS calibration models for glomalin. One calibration model was developed for samples with a low content of glomalin (arable land and grasslands), the second for soils with a high content of glomalin (forest soils), and the third calibration model for all combined soil samples. Calibrations were validated and optimized by leave-one-sample-out-cross-validation (LOSOCV) and by the external validation using eight soil samples (arable land and grassland), and six soil samples (forest soils) not included in the calibration models. Two different calibration models were recommended. One model for arable and grassland soils and the second for forest soils. No statistically significant differences were found between the reference and the NIRS method for both calibration models. The parameters of the NIRS calibration model (RMSECV = 0,70 and R = 0,90 for soils from arable land and grasslands and RMSECV = 3,8 and R = 0,94 for forest soils) proved that glomalin can be determined directly in air-dried soils by NIRS with adequate trueness and precision.

scholarly journals Prediction of soil organic matter and clay contents by near-infrared spectroscopy - NIRS

2020 ◽  
Vol 50 (1) ◽  
Author(s):  
Bruno Pedro Lazzaretti ◽  
Leandro Souza da Silva ◽  
Gerson Laerson Drescher ◽  
André Carnieletto Dotto ◽  
Darines Britzke ◽  
...  
Keyword(s):  
Organic Matter ◽  
Infrared Spectroscopy ◽  
Soil Organic Matter ◽  
Near Infrared Spectroscopy ◽  
Calibration Curve ◽  
Near Infrared ◽  
Soil Analysis ◽  
Clay Content ◽  
Soil Samples ◽  
Support Vector

ABSTRACT: Among the soil constituents, special attention is given to soil organic matter (SOM) and clay contents, since, among other aspects, they are key factors to nutrient retention and soil aggregates formation, which directly affect the crop production potential. The methods commonly used for the quantification of these constituents have some disadvantages, such as the use of chemical reactants and waste generation. An alternative to these methods is the near-infrared spectroscopy (NIRS) technique. The aim of this research is to evaluate models for SOM and clay quantification in soil samples using spectral data by NIRS. A set (n = 400) of soil samples previously analyzed by traditional methods were used to generate a NIRS calibration curve. The clay content was determined by the hydrometer method while SOM content was determined by sulfochromic solution. For calibration, we used the original spectra (absorbance) and spectral pretreatment (Savitzky-Golay smoothing derivative) in the following models: multiple linear regression (MLR), partial last squares regression (PLSR), support vector machine (SVM) and Gaussian process regression (GPR). The curve validation was performed with the SVM model (best performance in the calibration based on R² and RMSE) in two ways: with 40 random samples from the calibration set and another set with 200 new unknown samples. The soil clay content affects the predictive ability of the calibration curve to estimate SOM content by NIRS. Validation curves showed poorer performance (lower R² and higher RMSE) when generated from unknown samples, where the model tends to overestimate the lower levels and to underestimate the higher levels of clay and SOM. Despite the potential of NIRS technique to predict these attributes, further calibration studies are still needed to use this technique in soil analysis laboratories.

Sign in / Sign up

Export Citation Format

Share Document