Estimating Soil Arsenic Content with Visible and Near-Infrared Hyperspectral Reflectance

Soil arsenic (AS) contamination has attracted a great deal of attention because of its detrimental effects on environments and humans. AS and inorganic AS compounds have been classified as a class of carcinogens by the World Health Organization. In order to select a high-precision method for predicting the soil AS content using hyperspectral techniques, we collected 90 soil samples from six different land use types to obtain the soil AS content by chemical analysis and hyperspectral data based on an indoor hyperspectral experiment. A partial least squares regression (PLSR), a support vector regression (SVR), and a back propagation neural network (BPNN) were used to establish a relationship between the hyperspectral and the soil AS content to predict the soil AS content. In addition, the feasibility and modeling accuracy of different interval spectral resampling, different spectral pretreatment methods, feature bands, and full-band were compared and discussed to explore the best inversion method for estimating soil AS content by hyperspectral. The results show that 10 nm + second derivative (SD) + BPNN is the optimum method to predict soil AS content estimation; R v 2 is 0.846 and residual predictive deviation (RPD) is 2.536. These results can expand the representativeness and practicability of the model to a certain extent and provide a scientific basis and technical reference for soil pollution monitoring.

Download Full-text

Ensemble Identification of Spectral Bands Related to Soil Organic Carbon Levels over an Agricultural Field in Southern Ontario, Canada

Remote Sensing ◽

10.3390/rs11111298 ◽

2019 ◽

Vol 11 (11) ◽

pp. 1298 ◽

Cited By ~ 3

Author(s):

Ahmed Laamrani ◽

Aaron A. Berg ◽

Paul Voroney ◽

Hannes Feilhauer ◽

Line Blackburn ◽

...

Keyword(s):

Organic Carbon ◽

Soil Organic Carbon ◽

Near Infrared ◽

Hyperspectral Data ◽

Support Vector ◽

Least Squares Regression ◽

Agricultural Field ◽

Southern Ontario ◽

Spectral Bands ◽

Selection Of

The recent use of hyperspectral remote sensing imagery has introduced new opportunities for soil organic carbon (SOC) assessment and monitoring. These data enable monitoring of a wide variety of soil properties but pose important methodological challenges. Highly correlated hyperspectral spectral bands can affect the prediction and accuracy as well as the interpretability of the retrieval model. Therefore, the spectral dimension needs to be reduced through a selection of specific spectral bands or regions that are most helpful to describing SOC. This study evaluates the efficiency of visible near-infrared (VNIR) and shortwave near-infrared (SWIR) hyperspectral data to identify the most informative hyperspectral bands responding to SOC content in agricultural soils. Soil samples (111) were collected over an agricultural field in southern Ontario, Canada and analyzed against two hyperspectral datasets: An airborne Nano-Hyperspec imaging sensor with 270 bands (400–1000 nm) and a laboratory hyperspectral dataset (ASD FieldSpec 3) along the 1000–2500 nm range (NIR-SWIR). In parallel, a multimethod modeling approach consisting of random forest, support vector machine, and partial least squares regression models was used to conduct band selections and to assess the validity of the selected bands. The multimethod model resulted in a selection of optimal band or regions over the VNIR and SWIR sensitive to SOC and potentially for mapping. The bands that achieved the highest respective importance values were 711–715, 727, 986–998, and 433–435 nm regions (VNIR); and 2365–2373, 2481–2500, and 2198–2206 nm (NIR-SWIR). Some of these bands are in agreement with the absorption features of SOC reported in the literature, whereas others have not been reported before. Ultimately, the selection of optimal band and regions is of importance for quantification of agricultural SOC and would provide a new framework for creating optimized SOC-specific sensors.

Download Full-text

Early Detection of Plant Viral Disease Using Hyperspectral Imaging and Deep Learning

Sensors ◽

10.3390/s21030742 ◽

2021 ◽

Vol 21 (3) ◽

pp. 742

Author(s):

Canh Nguyen ◽

Vasit Sagan ◽

Matthew Maimaitiyiming ◽

Maitiniyazi Maimaitijiang ◽

Sourav Bhadra ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Early Detection ◽

Convolutional Neural Network ◽

Near Infrared ◽

Hyperspectral Data ◽

Viral Diseases ◽

Support Vector ◽

Spectral Features ◽

Feature Spaces

Early detection of grapevine viral diseases is critical for early interventions in order to prevent the disease from spreading to the entire vineyard. Hyperspectral remote sensing can potentially detect and quantify viral diseases in a nondestructive manner. This study utilized hyperspectral imagery at the plant level to identify and classify grapevines inoculated with the newly discovered DNA virus grapevine vein-clearing virus (GVCV) at the early asymptomatic stages. An experiment was set up at a test site at South Farm Research Center, Columbia, MO, USA (38.92 N, −92.28 W), with two grapevine groups, namely healthy and GVCV-infected, while other conditions were controlled. Images of each vine were captured by a SPECIM IQ 400–1000 nm hyperspectral sensor (Oulu, Finland). Hyperspectral images were calibrated and preprocessed to retain only grapevine pixels. A statistical approach was employed to discriminate two reflectance spectra patterns between healthy and GVCV vines. Disease-centric vegetation indices (VIs) were established and explored in terms of their importance to the classification power. Pixel-wise (spectral features) classification was performed in parallel with image-wise (joint spatial–spectral features) classification within a framework involving deep learning architectures and traditional machine learning. The results showed that: (1) the discriminative wavelength regions included the 900–940 nm range in the near-infrared (NIR) region in vines 30 days after sowing (DAS) and the entire visual (VIS) region of 400–700 nm in vines 90 DAS; (2) the normalized pheophytization index (NPQI), fluorescence ratio index 1 (FRI1), plant senescence reflectance index (PSRI), anthocyanin index (AntGitelson), and water stress and canopy temperature (WSCT) measures were the most discriminative indices; (3) the support vector machine (SVM) was effective in VI-wise classification with smaller feature spaces, while the RF classifier performed better in pixel-wise and image-wise classification with larger feature spaces; and (4) the automated 3D convolutional neural network (3D-CNN) feature extractor provided promising results over the 2D convolutional neural network (2D-CNN) in learning features from hyperspectral data cubes with a limited number of samples.

Download Full-text

Mapping Soil Alkalinity and Salinity in Northern Songnen Plain, China with the HJ-1 Hyperspectral Imager Data and Partial Least Squares Regression

Sensors ◽

10.3390/s18113855 ◽

2018 ◽

Vol 18 (11) ◽

pp. 3855 ◽

Cited By ~ 9

Author(s):

Lin Bai ◽

Cuizhen Wang ◽

Shuying Zang ◽

Changshan Wu ◽

Jinming Luo ◽

...

Keyword(s):

Least Squares ◽

Partial Least Squares ◽

Soil Ph ◽

Partial Least Squares Regression ◽

Near Infrared ◽

Hyperspectral Data ◽

Validation Dataset ◽

Least Squares Regression ◽

Songnen Plain ◽

Mean Square Errors

In arid and semi-arid regions, identifying and monitoring of soil alkalinity and salinity are in urgently need for preventing land degradation and maintaining ecological balances. In this study, physicochemical, statistical, and spectral analysis revealed that potential of hydrogen (pH) and electrical conductivity (EC) characterized the saline-alkali soils and were sensitive to the visible and near infrared (VIS-NIR) wavelengths. On the basis of soil pH, EC, and spectral data, the partial least squares regression (PLSR) models for estimating soil alkalinity and salinity were constructed. The R2 values for soil pH and EC models were 0.77 and 0.48, and the root mean square errors (RMSEs) were 0.95 and 17.92 dS/m, respectively. The ratios of performance to inter-quartile distance (RPIQ) for the soil pH and EC models were 3.84 and 0.14, respectively, indicating that the soil pH model performed well but the soil EC model was not considerably reliable. With the validation dataset, the RMSEs of the two models were 1.06 and 18.92 dS/m. With the PLSR models applied to hyperspectral data acquired from the hyperspectral imager (HSI) onboard the HJ-1A satellite (launched in 2008 by China), the soil alkalinity and salinity distributions were mapped in the study area, and were validated with RMSEs of 1.09 and 17.30 dS/m, respectively. These findings revealed that the hyperspectral images in the VIS-NIR wavelengths had the potential to map soil alkalinity and salinity in the Songnen Plain, China.

Download Full-text

Mapping Canopy Chlorophyll Content in a Temperate Forest Using Airborne Hyperspectral Data

Remote Sensing ◽

10.3390/rs12213573 ◽

2020 ◽

Vol 12 (21) ◽

pp. 3573

Author(s):

J. Malin Hoeppner ◽

Andrew K. Skidmore ◽

Roshanak Darvishzadeh ◽

Marco Heurich ◽

Hsing-Chung Chang ◽

...

Keyword(s):

Chlorophyll Content ◽

Spectral Resolution ◽

Near Infrared ◽

Deciduous Forest ◽

Mixed Forest ◽

Hyperspectral Data ◽

Least Squares Regression ◽

Area Index ◽

Management Interventions ◽

Shortwave Infrared

Chlorophyll content, as the primary pigment driving photosynthesis, is directly affected by many natural and anthropogenic disturbances and stressors. Accurate and timely estimation of canopy chlorophyll content (CCC) is essential for effective ecosystem monitoring to allow for successful management interventions to occur. Hyperspectral remote sensing offers the possibility to accurately estimate and map canopy chlorophyll content. In the past, research has predominantly focused on the use of hyperspectral data on canopy chlorophyll content retrieval of crops and grassland ecosystems. Therefore, in this study, a temperate mixed forest, the Bavarian Forest National Park in Germany, was chosen as the study site. We compared different statistical models (narrowband vegetation indices (VIs), partial least squares regression (PLSR) and random forest (RF)) in their accuracy to predict CCC using airborne hyperspectral data. The airborne hyperspectral imagery was acquired by the AisaFenix sensor (623 bands; 3.5 nm spectral resolution in the visible near-infrared (VNIR) region, and 12 nm spectral resolution in the shortwave infrared (SWIR) region; 3 m spatial resolution) on July 6, 2017. In situ leaf chlorophyll content and leaf area index measurements were sampled from the upper canopy of coniferous, mixed, and deciduous forest stands in July and August 2017. The study yielded the highest retrieval accuracies with PLSR (root mean square error (RMSE) = 0.25 g/m2, R2 = 0.66). It further indicated specific spectral regions within the visible (390–400 nm and 470–540 nm), red edge (680–780 nm), near-infrared (1050–1100 nm) and shortwave infrared regions (2000–2270 nm) that were important for CCC retrieval. The results showed that forest CCC can be mapped with relatively high accuracies using image spectroscopy.

Download Full-text

Hyperspectral Inversion of Phragmites Communis Carbon, Nitrogen, and Phosphorus Stoichiometry Using Three Models

Remote Sensing ◽

10.3390/rs12121998 ◽

2020 ◽

Vol 12 (12) ◽

pp. 1998

Author(s):

Lijuan Cui ◽

Zhiguo Dou ◽

Zhijun Liu ◽

Xueyan Zuo ◽

Yinru Lei ◽

...

Keyword(s):

Prediction Accuracy ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Model Error ◽

Scientific Basis ◽

Hyperspectral Data ◽

Dynamic Monitoring ◽

Support Vector ◽

Nitrogen And Phosphorus ◽

Accuracy And Stability

Studying the stoichiometric characteristics of plant C, N, and P is an effective way of understanding plant survival and adaptation strategies. In this study, 60 fixed plots and 120 random plots were set up in a reed-swamp wetland, and the canopy spectral data were collected in order to analyze the stoichiometric characteristics of C, N, and P across all four seasons. Three machine models (random forest, RF; support vector machine, SVM; and back propagation neural network, BPNN) were used to study the stoichiometric characteristics of these elements via hyperspectral inversion. The results showed significant differences in these characteristics across seasons. The RF model had the highest prediction accuracy concerning the stoichiometric properties of C, N, and P. The R2 of the four-season models was greater than 0.88, 0.95, 0.97, and 0.92, respectively. According to the root mean square error (RMSE) results, the model error of total C (TC) inversion is the smallest, and that of C/N inversion is the largest. The SVM yielded poor predictive results for the stoichiometric properties of C, N, and P. The R2 of the four-season models was greater than 0.82, 0.81, 0.81, and 0.70, respectively. According to RMSE results, the model error of TC inversion is the smallest, and that of C/P inversion is the largest. The BPNN yielded high stoichiometric prediction accuracy. The R2 of the four-season models was greater than 0.87, 0.96, 0.84, and 0.90, respectively. According to RMSE results, the model error of TC inversion is the smallest, and that of C/P inversion is the largest. The accuracy and stability of the results were verified by comprehensive analysis. The RF model showed the greatest prediction stability, followed by the BPNN and then the SVM models. The results indicate that the accuracy and stability of the RF model were the highest. Hyperspectral data can be used to accurately invert the stoichiometric characteristics of C, N, and P in wetland plants. It provides a scientific basis for the long-term dynamic monitoring of plant stoichiometry through hyperspectral data in the future.

Download Full-text

Nitrogen, phosphorus, and potassium prediction in soils, using infrared spectroscopy

Soil Research ◽

10.1071/sr10098 ◽

2011 ◽

Vol 49 (2) ◽

pp. 166 ◽

Cited By ~ 25

Author(s):

Yongni Shao ◽

Yong He

Keyword(s):

Infrared Spectroscopy ◽

Soil Properties ◽

Least Squares ◽

Near Infrared ◽

Soil Analysis ◽

Support Vector ◽

Least Squares Regression ◽

Available Nitrogen ◽

Phosphorus And Potassium ◽

Destructive Measurement

The aim of this study was to investigate the potential of the infrared spectroscopy technique for non-destructive measurement of soil properties. For the study, 280 soil samples were collected from several regions in Zhejiang, China. Data from near infrared (NIR, 800–2500 nm), mid infrared (MIR, 4000–400 cm–1), and the combined NIR–MIR regions were compared to determine which produced the best prediction of soil properties. Least-squares support vector machines (LS-SVM) were applied to construct calibration models for soil properties such as available nitrogen (N), phosphorus (P), and potassium (K). The results showed that both spectral regions contained substantial information on N, P, and K in the soils studied, and the combined NIR–MIR region did a little worse than either the NIR or MIR region. Optimal results were obtained through LS-SVM compared with the standard partial least-squares regression method, and the correlation coefficient of prediction (rp), root mean square error for prediction, and bias were, respectively, 0.90, 16.28 mg/kg, and 0.96 mg/kg for the prediction results of N in the NIR region; and 0.88, 41.62 mg/kg, and –2.28 mg/kg for the prediction results of P, and 0.89, 33.47 mg/kg, and 2.96 mg/kg for the prediction results of K, both in the MIR region. This work demonstrated the potential of LS-SVM coupled to infrared reflectance spectroscopy for more efficient soil analysis and the acquisition of soil information.

Download Full-text

Discrimination of Transgenic Canola (Brassica napus L.) and their Hybrids with B. rapa using Vis-NIR Spectroscopy and Machine Learning Methods

International Journal of Molecular Sciences ◽

10.3390/ijms23010220 ◽

2021 ◽

Vol 23 (1) ◽

pp. 220

Author(s):

Soo-In Sohn ◽

Subramani Pandian ◽

John-Lewis Zinia Zaukuu ◽

Young-Ju Oh ◽

Soo-Yun Park ◽

...

Keyword(s):

Brassica Napus ◽

Near Infrared ◽

Rapid Development ◽

Nir Spectroscopy ◽

Gm Crops ◽

F1 Hybrids ◽

Support Vector ◽

Composition Analysis ◽

Least Squares Regression ◽

Brassica Napus L

In recent years, the rapid development of genetically modified (GM) technology has raised concerns about the safety of GM crops and foods for human health and the ecological environment. Gene flow from GM crops to other crops, especially in the Brassicaceae family, might pose a threat to the environment due to their weediness. Hence, finding reliable, quick, and low-cost methods to detect and monitor the presence of GM crops and crop products is important. In this study, we used visible near-infrared (Vis-NIR) spectroscopy for the effective discrimination of GM and non-GM Brassica napus, B. rapa, and F1 hybrids (B. rapa X GM B. napus). Initially, Vis-NIR spectra were collected from the plants, and the spectra were preprocessed. A combination of different preprocessing methods (four methods) and various modeling approaches (eight methods) was used for effective discrimination. Among the different combinations, the Savitzky-Golay and Support Vector Machine combination was found to be an optimal model in the discrimination of GM, non-GM, and hybrid plants with the highest accuracy rate (100%). The use of a Convolutional Neural Network with Normalization resulted in 98.9%. The same higher accuracy was found in the use of Gradient Boosted Trees and Fast Large Margin approaches. Later, phenolic acid concentration among the different plants was assessed using GC-MS analysis. Partial least squares regression analysis of Vis-NIR spectra and biochemical characteristics showed significant correlations in their respective changes. The results showed that handheld Vis-NIR spectroscopy combined with chemometric analyses could be used for the effective discrimination of GM and non-GM B. napus, B. rapa, and F1 hybrids. Biochemical composition analysis can also be combined with the Vis-NIR spectra for efficient discrimination.

Download Full-text

Quantitatively estimating main soil water-soluble salt ions content based on Visible-near infrared wavelength selected using GC, SR and VIP

PeerJ ◽

10.7717/peerj.6310 ◽

2019 ◽

Vol 7 ◽

pp. e6310 ◽

Cited By ~ 4

Author(s):

Haifeng Wang ◽

Yinwen Chen ◽

Zhitao Zhang ◽

Haorui Chen ◽

Xianwen Li ◽

...

Keyword(s):

Spectral Data ◽

Near Infrared ◽

Soil Salinization ◽

Water Soluble ◽

Soluble Salt ◽

Support Vector ◽

Least Squares Regression ◽

Model Accuracy ◽

Salt Ions ◽

Spectral Models

Soil salinization is the primary obstacle to the sustainable development of agriculture and eco-environment in arid regions. The accurate inversion of the major water-soluble salt ions in the soil using visible-near infrared (VIS-NIR) spectroscopy technique can enhance the effectiveness of saline soil management. However, the accuracy of spectral models of soil salt ions turns out to be affected by high dimensionality and noise information of spectral data. This study aims to improve the model accuracy by optimizing the spectral models based on the exploration of the sensitive spectral intervals of different salt ions. To this end, 120 soil samples were collected from Shahaoqu Irrigation Area in Inner Mongolia, China. After determining the raw reflectance spectrum and content of salt ions in the lab, the spectral data were pre-treated by standard normal variable (SNV). Subsequently the sensitive spectral intervals of each ion were selected using methods of gray correlation (GC), stepwise regression (SR) and variable importance in projection (VIP). Finally, the performance of both models of partial least squares regression (PLSR) and support vector regression (SVR) was investigated on the basis of the sensitive spectral intervals. The results indicated that the model accuracy based on the sensitive spectral intervals selected using different analytical methods turned out to be different: VIP was the highest, SR came next and GC was the lowest. The optimal inversion models of different ions were different. In general, both PLSR and SVR had achieved satisfactory model accuracy, but PLSR outperformed SVR in the forecasting effects. Great difference existed among the optimal inversion accuracy of different ions: the predicative accuracy of Ca2+, Na+, Cl−, Mg2+ and SO42− was very high, that of CO32− was high and K+ was relatively lower, but HCO3− failed to have any predicative power. These findings provide a new approach for the optimization of the spectral model of water-soluble salt ions and improvement of its predicative precision.

Download Full-text

Estimating growth and photosynthetic properties of wheat grown in simulated saline field conditions using hyperspectral reflectance sensing and multivariate analysis

Scientific Reports ◽

10.1038/s41598-019-52802-5 ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 4

Author(s):

Salah El-Hendawy ◽

Nasser Al-Suhaibani ◽

Majed Alotaibi ◽

Wael Hassan ◽

Salah Elsayed ◽

...

Keyword(s):

Near Infrared ◽

Agricultural Sector ◽

Hyperspectral Data ◽

Field Conditions ◽

Least Squares Regression ◽

Hyperspectral Reflectance ◽

Full Spectrum ◽

Salinity Levels ◽

Shortwave Infrared ◽

Related Trait

Abstract The timely estimation of growth and photosynthetic-related traits in an easy and nondestructive manner using hyperspectral data will become imperative for addressing the challenges of environmental stresses inherent to the agricultural sector in arid conditions. However, the handling and analysis of these data by exploiting the full spectrum remains the determining factor for refining the estimation of crop variables. The main objective of this study was to estimate growth and traits underpinning photosynthetic efficiency of two wheat cultivars grown under simulated saline field conditions and exposed to three salinity levels using hyperspectral reflectance information from 350–2500 nm obtained at two years. Partial least squares regression (PLSR) based on the full spectrum was applied to develop predictive models for estimating the measured parameters in different conditions (salinity levels, cultivars, and years). Variable importance in projection (VIP) of PLSR in combination with multiple linear regression (MLR) was implemented to identify important waveband regions and influential wavelengths related to the measured parameters. The results showed that the PLSR models exhibited moderate to high coefficients of determination (R2) in both the calibration and validation datasets (0.30–0.95), but that this range of R2 values depended on parameters and conditions. The PLSR models based on the full spectrum accurately and robustly predicted three of four parameters across all conditions. Based on the combination of PLSR-VIP and MLR analysis, the wavelengths selected within the visible (VIS), red-edge, and middle near-infrared (NIR) wavebands were the most sensitive to all parameters in all conditions, whereas those selected within the shortwave infrared (SWIR) waveband were effective for some parameters in particular conditions. Overall, these results indicated that the PLSR analysis and band selection techniques can offer a rapid and nondestructive alternative approach to accurately estimate growth- and photosynthetic-related trait responses to salinity stress.

Download Full-text

Application of VIS/NIR Spectroscopy and SDAE-NN Algorithm for Predicting the Cold Storage Time of Salmon

Journal of Spectroscopy ◽

10.1155/2018/7450695 ◽

2018 ◽

Vol 2018 ◽

pp. 1-9 ◽

Cited By ~ 4

Author(s):

Ting Wu ◽

Nan Zhong ◽

Ling Yang

Keyword(s):

Neural Network ◽

Cold Storage ◽

Storage Time ◽

Near Infrared ◽

High Efficiency ◽

Back Propagation ◽

Nir Spectroscopy ◽

Back Propagation Neural Network ◽

Least Squares Regression ◽

Test Sets

The cold storage time of salmon has a significant impact on its freshness, which is an important factor for consumers to evaluate the quality of salmon. The efficient, accurate, and convenient protocol is urgent to appraise the freshness for quality checking. In this paper, the ability of visible/near-infrared (VIS/NIR) spectroscopy was evaluated to predict the cold storage time of salmon meat and skin, which were stored at low-temperature box for 0~12 days. Meanwhile, a double-layer stacked denoising autoencoder neural network (SDAE-NN) algorithm was introduced to establish the prediction model without spectral pre-preprocessing. The results showed that, compared with the common methods such as partial least squares regression (PLSR) and back propagation neural network (BP-NN), the SDAE-NN method had a better performance due to its high efficiency in decreasing noise and optimizing the initial weights. The determination coefficient of test sets (R2test) and root mean square error of test sets (RMSEP) have been calculated based on SDAE-NN, for the salmon meat (skin), the R2test can reach 0.98 (0.92), and the RMSEP can reach 0.93 (1.75), respectively. It is highlighted that the algorithm is efficient and accurate and that the salmon meat would be more suitable for predicting freshness than the salmon skin. VIS/NIR spectroscopy combined with the SDAE-NN algorithm can be widely used to predict the freshness of various agricultural products.

Download Full-text