scholarly journals Prediction of soil properties with machine learning models based on the spectral response of soil samples in the near infrared range

2019 ◽  
Vol 70 (4) ◽  
pp. 298-313 ◽  
Author(s):  
Stanisław Gruszczyński
Keyword(s):  
Soil Properties ◽  
Near Infrared ◽  
Soil Analysis ◽  
Spectral Response ◽  
Research Centre ◽  
Infrared Range ◽  
Soil Maps ◽  
Soil Features ◽  
The Impact ◽  
The Relationship

Abstract One of the basic methods for soil analysis time and cost reduction is using soil sample spectral response in laboratory conditions. The problem with this method lies in determining the relationship between the shape of the soil spectral response and soil physical or chemical properties. The LUCAS soil database collected by the EU’s ESDAC research centre is good material to analyse the relationship between the soil properties and the near infrared (NIR) spectral response. The modelling described in the paper is based on these data. The analysis of the impact of soil properties configuration on absorbance levels in various NIR spectrum ranges was conducted using the stepwise regression models with the properties, properties squared and products of properties being explanatory variables. The analysis of partial correlation of soil properties values with absorbance values and absorbance derivative in the entire spectral range was conducted in order to evaluate the impact of the absorbance transformation (the first derivative of absorbance vector) on the change of significance of relationship with properties values. The Multi Layer Perceptron (MLP) models were used to estimate the absorbance relationship with single soil features. Soil property modelling based on the selection and transformation algorithm of raw values and first and second absorbance derivatives was also conducted along with the suitability evaluation of such models in building digital soil maps. The absorbance is affected by a limited number of tested soil features like pH, texture, content of carbonates, SOC, N, and CEC; P and K contents have, in case of this research, a negligible impact. The NIR methodology can be suitable in conditions of limited soil variation and particularly in development of thematic soil maps.

scholarly journals Spectral Irradiance Influence on Solar Cells Efficiency

Energies ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 5017
Author(s):  
David Leitão ◽  
João Paulo N. Torres ◽  
João F. P. Fernandes
Keyword(s):  
Near Infrared ◽  
Spectral Response ◽  
Experimental Tests ◽  
Optical Filters ◽  
Spectral Irradiance ◽  
Copper Indium ◽  
Input Variables ◽  
Relative Errors ◽  
The Impact ◽  
High Pass

This paper investigates the influence of the spectral irradiance variation and the spectral response (SR) on the production of energy by photovoltaic cells. To determine the impact of SR and spectral irradiance on m-Si and perovskite cells, experimental tests were conducted outdoors, used optical filters to select different zones of the spectrum. For the computational simulations of the different photovoltaic modules, when subjected to a certain spectral irradiance, a model with spectral factor (SF) was implemented. The SF model accurately simulated the experiments performed for the high-pass filters. The highest relative errors for certain irradiation bands occurred due to the input variables used in the model, which did not fully describe the reality of the experiments performed. The effect of the SR and the spectral irradiance for each of them were observed through the simulations for the m-Si, a-Si, CdTe, and copper indium selenide (CIS) modules. The CIS technology presented a better overall result in the near infrared zone, producing about half of the energy produced by the CdTe technology in the visible zone. The SF, spectral incompatibility factor (MM), and spectral effective responsivity (SEF) parameters were verified to be important for studying the photovoltaic energy production.

scholarly journals Estimation of Secondary Soil Properties by Fusion of Laboratory and On-Line Measured Vis–NIR Spectra

2019 ◽  
Vol 11 (23) ◽  
pp. 2819 ◽  
Author(s):  
Muhammad Abdul Munnaf ◽  
Said Nawar ◽  
Abdul Mounem Mouazen
Keyword(s):  
Soil Properties ◽  
Real Time ◽  
Measurement Accuracy ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Spectral Response ◽  
Nir Spectroscopy ◽  
Accurate Estimation ◽  
Line Measurement ◽  
On Line

Visible and near infrared (vis–NIR) diffuse reflectance spectroscopy has made invaluable contributions to the accurate estimation of soil properties having direct and indirect spectral responses in NIR spectroscopy with measurements made in laboratory, in situ or using on-line (while the sensor is moving) platforms. Measurement accuracies vary with measurement type, for example, accuracy is higher for laboratory than on-line modes. On-line measurement accuracy deteriorates further for secondary (having indirect spectral response) soil properties. Therefore, the aim of this study is to improve on-line measurement accuracy of secondary properties by fusion of laboratory and on-line scanned spectra. Six arable fields were scanned using an on-line sensing platform coupled with a vis–NIR spectrophotometer (CompactSpec by Tec5 Technology for spectroscopy, Germany), with a spectral range of 305–1700 nm. A total of 138 soil samples were collected and used to develop five calibration models: (i) standard, using 100 laboratory scanned samples; (ii) hybrid-1, using 75 laboratory and 25 on-line samples; (iii) hybrid-2, using 50 laboratory and 50 on-line samples; (iv) hybrid-3, using 25 laboratory and 75 on-line samples, and (v) real-time using 100 on-line samples. Partial least squares regression (PLSR) models were developed for soil pH, available potassium (K), magnesium (Mg), calcium (Ca), and sodium (Na) and quality of models were validated using an independent prediction dataset (38 samples). Validation results showed that the standard models with laboratory scanned spectra provided poor to moderate accuracy for on-line prediction, and the hybrid-3 and real-time models provided the best prediction results, although hybrid-2 model with 50% on-line spectra provided equally good results for all properties except for pH and Na. These results suggest that either the real-time model with exclusively on-line spectra or the hybrid model with fusion up to 50% (except for pH and Na) and 75% on-line scanned spectra allows significant improvement of on-line prediction accuracy for secondary soil properties using vis–NIR spectroscopy.

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

Soil Research ◽  
2011 ◽  
Vol 49 (2) ◽  
pp. 166 ◽  
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.

scholarly journals Mobile Proximal Sensing with Visible and Near Infrared Spectroscopy for Digital Soil Mapping

Soil Systems ◽  
2020 ◽  
Vol 4 (3) ◽  
pp. 40
Author(s):  
Masakazu Kodaira ◽  
Sakae Shibusawa
Keyword(s):  
Soil Properties ◽  
Regression Models ◽  
Near Infrared ◽  
Soil Property ◽  
Coefficient Of Determination ◽  
Clay Loam ◽  
Soil Maps ◽  
Local Regression ◽  
Predicted Values ◽  
Digital Soil Maps

The objective of this study was to estimate multiple soil property local regression models, confirm the accuracy of the predicted values using visible near-infrared subsurface diffuse reflectance spectra collected by a mobile proximal soil sensor, and show that digital soil maps predicted by multiple soil property local regression models are able to visualize empirical knowledge of the grower. The parent materials in the experimental fields were light clay, clay loam, and sandy clay loam. The study was conducted in Saitama Prefecture, Japan. To develop local regression models for the 30 chemical and 4 physical properties, a total of 231 samples were collected; to evaluate accuracy of prediction, 65 samples were collected. The local regression models were developed using 2nd derivative pretreatment by the Savitzky–Golay algorithm and partial least squares regression. The local regression models were evaluated using the coefficient of determination (R2), residual prediction deviation (RPD), range error ratio (RER), and the ratio of prediction error to interquartile range (RPIQ). The R2 accuracy of the 34 local regression models was 0.81 or higher. In the predicted values for 65 unknown samples, the local regression models could ‘distinguish between high and low’ for 3 of the 34 soil properties, but were ‘not useful’ as absolute quantitative values for the other 31 soil properties. However, it was confirmed that the predicted values followed the transition in measured values, and thus that the developed 34 regression models could be used for generating digital soil maps based on relative quantitative values. The grower changed the ridge direction in the field from east–west to north–south just looking at the digital soil maps.

Impact of temperature and relative humidity on the near infrared spectroscopy measurements of cotton fiber micronaire

2017 ◽  
Vol 88 (20) ◽  
pp. 2279-2291 ◽  
Author(s):  
Jimmy Zumba ◽  
James Rodgers ◽  
Matthew Indest
Keyword(s):  
Relative Humidity ◽  
Environmental Conditions ◽  
Cotton Fiber ◽  
Near Infrared ◽  
Spectral Response ◽  
Wavelength Region ◽  
Predictive Capability ◽  
Textile Processing ◽  
Processing Efficiency ◽  
The Impact

A key cotton fiber property is micronaire. Micronaire can impact the fiber’s quality, textile processing efficiency, and fabric dye consistency. Fiber micronaire is normally measured in a laboratory under tight standard temperature and relative humidity (RH) environmental conditions (21 ± 1℃, 65 ± 2% RH). Near infrared (NIR) measurements have been performed both inside and outside of the laboratory, but measurements outside the laboratory have at times demonstrated reduced predictive capability, possibly due to the lack of standard environmental conditions. A program was implemented to determine the impact of non-standard conditions of temperature T and relative humidity RH on NIR micronaire results for bench-top and portable NIR instruments. Non-standard T and RH resulted in varying fiber moisture, which impacted the NIR spectral response. The NIR micronaire results were impacted by the non-standard conditioning for all instruments, with the lower wavelength region (∼910–1680 nm) portable instrument impacted the most. The impacts and deviations were greater at high temperature/RH compared to low temperature/RH conditioning. These results provide a rationale for the deviations observed previously in NIR micronaire results for outside the laboratory micronaire measurements with portable NIR units.

scholarly journals Hyperspectral system trade-offs for illumination, hardware and analysis methods: a case study of seed mix ingredient discrimination

2020 ◽  
Author(s):  
Carolina Blanch-Pérez del Notario ◽  
Carlos López-Molina ◽  
Andy Lambrechts ◽  
Wouter Saeys
Keyword(s):  
Hyperspectral Imaging ◽  
Spectral Resolution ◽  
Food Industry ◽  
Near Infrared ◽  
Imaging System ◽  
Infrared Range ◽  
Analysis Methods ◽  
Trade Offs ◽  
The Impact

The discrimination power of a hyperspectral imaging system for image segmentation or object detection is determined by the illumination, the camera spatial–spectral resolution, and both the pre-processing and analysis methods used for image processing. In this study, we methodically reviewed the alternatives for each of those factors for a case study from the food industry to provide guidance in the construction and configuration of hyperspectral imaging systems in the visible near infrared range for food quality inspection. We investigated both halogen- and LED-based illuminations and considered cameras with different spatial–spectral resolution trade-offs. At the level of the data analysis, we evaluated the impact of binning, median filtering and bilateral filtering as pre- or post-processing and compared pixel-based classifiers with convolutional neural networks for a challenging application in the food industry, namely ingredient identification in a flour–seed mix. Starting from a basic configuration and by modifying the combination of system aspects we were able to increase the mean accuracy by at least 25 %. In addition, different trade-offs in performance-complexity were identified for different combinations of system parameters, allowing adaptation to diverse application requirements.

scholarly journals Graphene oxide and its derivatives as promising In-vitro bio-imaging platforms

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Yasaman Esmaeili ◽  
Elham Bidram ◽  
Ali Zarrabi ◽  
Abbas Amini ◽  
Chun Cheng
Keyword(s):  
Graphene Oxide ◽  
Optical Sensors ◽  
Near Infrared ◽  
Fluorescent Microscopy ◽  
Photoluminescence Property ◽  
Infrared Range ◽  
Chemical Structures ◽  
Bio Imaging ◽  
The Impact

Abstract Intrinsic fluorescence and versatile optical properties of Graphene Oxide (GO) in visible and near-infrared range introduce this nanomaterial as a promising candidate for numerous clinical applications for early-diagnose of diseases. Despite recent progresses in the impact of major features of GO on the photoluminescence properties of GO, their modifications have not yet systematically understood. Here, to study the modification effects on the fluorescence behavior, poly ethylene glycol (PEG) polymer, metal nanoparticles (Au and Fe3O4) and folic acid (FA) molecules were used to functionalize the GO surface. The fluorescence performances in different environments (water, DMEM cell media and phosphate buffer with two different pH values) were assessed through fluorescence spectroscopy and fluorescent microscopy, while Fourier-transform infrared spectroscopy (FTIR) and X-ray diffraction (XRD) and Scanning electron microscopy (SEM) were utilized to evaluate the modifications of chemical structures. The modification of GO with desired molecules improved the photoluminescence property. The synthesized platforms of GO-PEG, GO-PEG-Au, GO-PEG-Fe3O4 and GO-PEG-FA illustrated emissions in three main fluorescence regions (blue, green and red), suitable for tracing and bio-imaging purposes. Considering MTT results, these platforms potentially positioned themselves as non-invasive optical sensors for the diagnosis alternatives of traditional imaging agents.

scholarly journals ANALYSIS OF MODELS AND ALGORITHMS FOR MEASURING THE AREA OF VINE LEAVES

2018 ◽  
Vol 6 (3) ◽  
pp. 213-224
Author(s):  
Krasimira Georgieva ◽  
Miglena Kazakova ◽  
Zlatin Zlatev
Keyword(s):  
Near Infrared ◽  
Autonomous Robots ◽  
Infrared Range ◽  
Important Indicator ◽  
Video Cameras ◽  
Small Height ◽  
Low Energy Consumption ◽  
The Relationship ◽  
Near Infrared Range ◽  
Sufficient Precision

The area of the vine leaves is an important indicator for determining the quantity of leaf mass, making connections with the influence of the environment, improving the methods of growing the vineyards. Satellite and aviation measurements for now have the drawback that the images obtained are of low resolution and do not allow the measurement of the area of individual leaf. A solution to this problem is the use of unmanned aerial vehicles, which provide digital images of a small height (1-3 m) and autonomous robots to navigate in the vineyards. These systems use video cameras operating in the visible, near infrared range and thermo cameras. The measurement of individual leaves and the search for links to the foliage and plant indicators is due to the fact that in order to do this when crawling the array, it is necessary to use low energy consumption devices. These devices also have poor computing resources. In this report a comparative analysis of 16 models describing the relationship between the area and the main dimensions of the leaf - long and short axis is made. Three of these models have been selected to describe this relationship with sufficient precision. They are compared with the 4 algorithm for measuring the area of the vine leaves. The results obtained show that the measurement error, the data processing time between the algorithms used and the models are comparable. The analyzes made suggest that the choice of a method for measuring the area of vine leaves depends on the desired accuracy, the time of receipt, the processing and the analysis of the results of what equipment the user has access to.

scholarly journals Impact of Headworks of River Chenab on Surrounding Vegetation and Phytodiversity Analysis

2021 ◽  
Vol 12 (1) ◽  
pp. 16
Author(s):  
Muhammad Azhar Ali ◽  
Muhammad Sajjad Iqbal
Keyword(s):  
Environmental Gradients ◽  
Soil Analysis ◽  
Anthropogenic Activities ◽  
Chemical Properties ◽  
Detrended Correspondence Analysis ◽  
Environmental Data ◽  
Heat Map ◽  
Physical And Chemical ◽  
The Impact ◽  
The Relationship

This study focused on the impact assessment of the wild flora and environmental gradients encompassed by the River Chenab headworks using quantitative ecological indices. Quadrats of 1 × 1, 5 × 5 and 10 × 10 m2 sizes were used for vegetation. Considering environmental data, grazing and anthropogenic effects, soil analysis based on different physical and chemical properties was studied. The relationship between different sites and their surroundings was analyzed by Canonical and Detrended Correspondence Analysis. Similarity indices were revealed through the use of a heat map and dendrogram. As many as 130 plant species, 60 families, comprising 104 species of dicots, 17 monocots, 7 pteridophytes and 2 species of bryophytes were recorded. Different soil properties including organic matter, soil moisture and soil pH affect the vegetation on different sites. Anthropogenic activities such as construction, fishing and animal grazing were the main threats for vegetation that need to be restricted strategically to conserve surrounding vegetation.

Sign in / Sign up

Export Citation Format

Share Document