Content Estimation Model Research Articles

Combining Remote Sensing and Meteorological Data for Improved Rice Plant Potassium Content Estimation

Potassium (K) plays a significant role in the formation of crop quality and yield. Accurate estimation of plant potassium content using remote sensing (RS) techniques is therefore of great interest to better manage crop K nutrition. To improve RS of crop K, meteorological information might prove useful, as it is well established that weather conditions affect crop K uptake. We aimed to determine whether including meteorological data into RS-based models can improve K estimation accuracy in rice (Oryza sativa L.). We conducted field experiments throughout three growing seasons (2017–2019). During each year, different treatments (i.e., nitrogen, potassium levels and plant varieties) were applied and spectra were taken at different growth stages throughout the growing season. Firstly, we conducted a correlation analysis between rice plant potassium content and transformed spectra (reflectance spectra (R), first derivative spectra (FD) and reciprocal logarithm-transformed spectra (log [1/R])) to select correlation bands. Then, we performed the genetic algorithms partial least-squares and linear mixed effects model to select important bands (IBs) and important meteorological factors (IFs) from correlation bands and meteorological data (daily average temperature, humidity, etc.), respectively. Finally, we used the spectral index and machine learning methods (partial least-squares regression (PLSR) and random forest (RF)) to construct rice plant potassium content estimation models based on transformed spectra, transformed spectra + IFs and IBs, and IBs + IFs, respectively. Results showed that normalized difference spectral index (NDSI (R1210, R1105)) had a moderate estimation accuracy for rice plant potassium content (R2 = 0.51; RMSE = 0.49%) and PLSR (FD-IBs) (R2 = 0.69; RMSE = 0.37%) and RF (FD-IBs) (R2 = 0.71; RMSE = 0.40%) models based on FD could improve the prediction accuracy. Among the meteorological factors, daily average temperature contributed the most to estimating rice plant potassium content, followed by daily average humidity. The estimation accuracy of the optimal rice plant potassium content models was improved by adding meteorological factors into the three RS models, with model R2 increasing to 0.65, 0.74, and 0.76, and RMSEs decreasing to 0.42%, 0.35%, and 0.37%, respectively, suggesting that including meteorological data can improve our ability to remotely sense plant potassium content in rice.

Application of hyperspectral analysis of chlorophyll a concentration inversion in Nansi Lake

Chlorophyll-a (Chl-a) is an important water quality safety evaluation index, and accurate Chl-a concentration monitoring is important for the development of aquaculture, aquatic ecosystem balance, and drinking water safety. Rapid and accurate Chl-a concentration determination in water using hyperspectral remote sensing is an important subject in water ecological environment monitoring. In this study, the spectral reflectance and Chl-a concentration of Nansi Lake were measured, and the time-frequency method of empirical mode decomposition (EMD) analysis was used for the noise reduction and reconstruction of the first-order differential of the spectrum to extract sensitive spectral features. The eXtreme Gradient Boosting (XGBoost) machine learning algorithm was used to establish a Chl-a concentration estimation model, and the best parameters and model combinations for the inversion of the Chl-a concentration in the water column of Nansi Lake were determined. The results show that the combined three-band algorithm combination parameters obtained from the EMD noise-reduced reconstruction of spectral first-order differential (OFODSR-D) data fit the measured Chl-a concentrations better than the original spectral (OSR) and OFODSR data, with a maximum correlation coefficient of 0.8588. Second, the models based on OFODSR-D achieved more satisfactory prediction results, with XGBoost having the highest estimation accuracy (R2 of 0.9024 and root-mean-square error (RMSE) of 1.1312 μg·L−1 for the inverse model), followed by the partial least squares regression (PLSR) model and the linear model (R2 of 0.8474 and 0.8326, and RMSE of 13.3031 and 7.6987 μg·L−1, respectively). This study innovatively introduces the EMD method to the spectral processing of water bodies, obtains optimal parameters for the inversion of the Chl-a concentration, and achieves better results. This study provides a new approach to obtaining optimal inversion parameters for Chl-a monitoring in inland lake water bodies using remote-sensing methods.

Research on estimation models of the spectral characteristics of soil organic matter based on the soil particle size

Soil organic matter (SOM) is an important part of soil fertility and the main nutrient source for crop growth. The establishment of an effective SOM content estimation model can provide technical support for the improvement of saline soil and the implementation of precision agriculture. In this paper, a laboratory spectrometer was used to measure the spectral reflectance of saline soils with particle sizes of 1 mm, 0.50 mm, 0.25 mm and 0.15 mm collected from Kenli County. After spectral preprocessing and spectral transformation, the characteristic bands of the SOM spectrum were extracted by the successive projections algorithm (SPA). Finally, stepwise multiple linear regression (SMLR), principal component regression (PCR) and partial least squares regression (PLSR) were used to establish SOM content estimation models based on soil particle size. The results showed the following. (i) Soil particle size had a significant impact on soil spectral reflectance. The smaller the soil particle size was, the greater the soil spectral reflectance. (ii) The sensitive bands for SOM were mainly concentrated in the visible light region (400–760 nm). First derivative (FD) transformation can effectively improve the characteristic spectral information obtained from SOM. (iii) Among the three models established with the characteristic bands, the estimation ability of the PLSR model was better than that of the PCR and SMLR models. (iv) The FD of the original spectral reflectance of the 0.25 mm particles combined with the PLSR model gave the best estimation of the SOM content. When the soil particle size was less than 0.25 mm, the estimation results of the model were not improved. These results provide a basis for effective estimation of the SOM content and improvement of saline-alkali soil in Kenli County in the Yellow River Delta.

Comparison of new hyperspectral index and machine learning models for prediction of winter wheat leaf water content

BackgroundThe leaf water content estimation model is established by hyperspectral technology, which is crucial and provides technical reference for precision irrigation.MethodsIn this study, two consecutive years of field experiments (different irrigation times and seven wheat varieties) in 2018–2020 were performed to obtain the canopy spectra reflectance and leaf water content (LWC) data. The characteristic bands related to LWC were extracted from correlation coefficient method (CA) and x-Loading weight method (x-Lw). Five modeling methods, spectral index and four other methods (Partial Least-Squares Regression (PLSR), Random Forest Regression (RFR), Extreme Random Trees (ERT), and K-Nearest Neighbor (KNN)) based characteristic bands, were employed to construct LWC estimation models.ResultsThe results showed that the canopy spectral reflectance increased with the increase of irrigation times, especially in the near-infrared band (750–1350 nm). The prediction accuracy of the newly developed differential spectral index DVI (R1185, R1307) was higher than that of the existing spectral index, with R2 of 0.85 and R2 of 0.78 for the calibration and validation, respectively. Due to a large amount of hyperspectral data, the correlation coefficient method (CA) and x-Loading weight (x-Lw) were used to select the water characteristic bands (100 and 28 characteristic bands, respectively) from the full spectrum. We found that the accuracy of the model based on the characteristic bands was not significantly lower than that of the full spectrum-based models. Among these models, the ERT- x-Lw model performed the best (R2 and RMSE of 0.88 and 1.46; 0.84 and 1.62 for the calibration and validation, respectively). In addition, the accuracy of the LWC estimation model constructed by ERT-x-Lw was higher than that of DVI (R1185, R1307).ConclusionThe two models based on ERT-x-Lw and DVI (R1185, R1307) can effectively predict wheat leaf water content. The results provide a technical reference and a basis for crop water monitoring and diagnosis under similar production conditions.

DUAL-WAVELENGTH TERRESTRIAL LASER SCANNING AS A CALIBRATION TOOL FOR SATELLITE ESTIMATION OF FOREST CANOPY MOISTURE CONTENT

Abstract. Satellites can estimate forest canopy moisture content at the landscape level, and thus have been widely utilized in forest health monitoring. However, the calibration and validation of the estimation models can be challenging. Collecting a sufficient number of leaf samples from the canopy top layers in sampling plots that match the pixel size of the sensor is needed, which is a cost, time and effort consuming process. Dual-wavelength Terrestrial Laser Scanning (TLS) has been successfully used in estimating canopy moisture content of individual trees in three dimensions (3D) in several recent studies. Such 3D estimates, if produced at the plot level, can be used in the calibration and validation of satellite forest canopy moisture content estimation models. In this study, forest canopy moisture content, quantified as the leaf Equivalent Water Thickness (EWT), was estimated in 3D at the plot level in a mixed-species deciduous broadleaf forest plot using dual-wavelength TLS intensity data (808 nm near infrared and 1550 nm shortwave infrared wavelengths). The relative error in the EWT estimation was 6%, and the EWT point cloud revealed vertical heterogeneity in the EWT distribution. EWT was 37% higher in the canopy top layers than in the canopy bottom layers. The results obtained in this study showed that dual-wavelength TLS has the potential to be used in operational landscape-scale EWT estimation, and can be a useful tool for the calibration and validation of satellite EWT estimation models.

RETRACTED ARTICLE: Monitoring soil salinization in Manas River Basin, Northwestern China based on multi-spectral index group

ABSTRACT Large-scale and accurate monitoring soil salinization is essential for controlling soil degradation and sustainable agricultural development. The agricultural irrigation area of the Manas River Basin in the arid area of Northwest China was selected as the test area. The soil salinization monitoring model based on spectral index group was constructed by comparing the accuracy of PCR, PLSR and MLR models using the transformation of multi-spectral index group and index screening. The results showed that there was a certain correlation between the 28 spectral index groups, with a maximum correlation coefficient -0.3689 between the original spectral group and the soil salt content was B10 band. After the transformation of original data for the logarithm Ln(R), exponential eR and square root R1/2 respectively, the correlation between each index and soil salinity was significantly improved, with the maximum correlation coefficient was up to -0.7564 of R1/2. The salt content estimation models were constructed by different data transformation using PLSR, PCR and MLR methods, respectively. This study provides a fast and accurate method for monitoring regional soil salinity content and the results can provide a reference for soil salinity grading management in arid and semi-arid areas.

Hyperspectral Estimation of Soil Organic Matter Content using Different Spectral Preprocessing Techniques and PLSR Method

Soil organic matter (SOM) is the main source of soil nutrients, which are essential for the growth and development of agricultural crops. Hyperspectral remote sensing is one of the most efficient ways of estimating the SOM content. Visible, near infrared, and mid-infrared reflectance spectroscopy, combined with the partial least squares regression (PLSR) method is considered to be an effective way of determining soil properties. In this study, we used 54 different spectral pretreatments to preprocess soil spectral data. These spectral pretreatments were composed of three denoising methods, six data transformations, and three dimensionality reduction methods. The three denoising methods included no denoising (ND), Savitzky–Golay denoising (SGD), and wavelet packet denoising (WPD). The six data transformations included original spectral data, R; reciprocal, 1/R; logarithmic, log(R); reciprocal logarithmic, log(1/R); first derivative, R’; and first derivative of reciprocal, (1/R)’. The three dimensionality reduction methods included no dimensionality reduction (NDR), sensitive waveband dimensionality reduction (SWDR), and principal component analysis (PCA) dimensionality reduction (PCADR). The processed spectra were then employed to construct PLSR models for predicting the SOM content. The main results were as follows—(1) the wavelet packet denoising (WPD)-R’ and WPD-(1/R)’ data showed stronger correlations with the SOM content. Furthermore, these methods could effectively limit the correlation between the adjacent bands and, thus, prevent “overfitting”. (2) Of the 54 pretreatments investigated, WPD-(1/R)’-PCADR yielded the model with the highest accuracy and stability. (3) For the same denoising method and spectral transformation data, the accuracy of the SOM content estimation model based on SWDR was higher than that of the model based on NDR. Furthermore, the accuracy in the case of PCADR was higher than that for SWDR. (4) Dimensionality reduction was effective in preventing data overfitting. (5) The quality of the spectral data could be improved and the accuracy of the SOM content estimation model could be enhanced effectively, by using some appropriate preprocessing methods (one combining WPD and PCADR in this study).

Estimation of total nitrogen content in sugarbeet leaves under drip irrigation based on hyperspectral characteristic parameters and vegetation index

The purpose of this paper is to clarify the quantitative relationship between total nitrogen content of sugar beet and high-resolution vegetation remote sensing, to explore the establishment of an optimal estimation model for total nitrogen content of sugar beet, and to monitor the growth of sugar beet. Xinjiang drip-irrigated sugar beet (Beta356) was selected to collect the reflectance spectra of leaf cluster during the leaves rapid growth period, root expansion period and sugar accumulation period by the ASD field hyperspectral apparatus. The total nitrogen content was also measured and the relationship between original spectral reflectance and total nitrogen content was analyzed. According to the correlation between the first-order differential spectral reflectance and total nitrogen content, a total nitrogen content estimation model was established. The model with spectral characteristic parameter Dr762 power function had a good ability to estimate total nitrogen content in leaves of beet, with the determination coefficient, relative error, and root mean square error of 0.747, 21.635, and 4.914, respectively. Various function estimation models were established based on vegetation index and leaf total nitrogen content. The linear function under vegetation index Dr762–Dr496 had better ability to estimate leaf total nitrogen content. Its determinant coefficient, relative error, and root mean square error were 0.794, 23.008, and 5.372, respectively.

Evaluating Different Non-Destructive Estimation Methods for Winter Wheat (Triticum aestivum L.) Nitrogen Status Based on Canopy Spectrum

Compared to conventional laboratory testing methods, crop nitrogen estimation methods based on canopy spectral characteristics have advantages in terms of timeliness, cost, and practicality. A variety of rapid and non-destructive estimation methods based on the canopy spectrum have been developed on the scale of space, sky, and ground. In order to understand the differences in estimation accuracy and applicability of these methods, as well as for the convenience of users to select the suitable technology, models for estimation of nitrogen status of winter wheat were developed and compared for three methods: drone equipped with a multispectral camera, soil plant analysis development (SPAD) chlorophyll meter, and smartphone photography. Based on the correlations between observed nitrogen status in winter wheat and related vegetation indices, green normalized difference vegetation index (GNDVI) and visible atmospherically resistant index (VARI) were selected as the sensitive vegetation indices for the drone equipped with a multispectral camera and smartphone photography methods, respectively. The correlation coefficients between GNDVI, SPAD, and VARI were 0.92 ** and 0.89 **, and that between SPAD and VARI was 0.90 **, which indicated that three vegetation indices for these three estimation methods were significantly related to each other. The determination coefficients of the 0–90 cm soil nitrate nitrogen content estimation models for the drone equipped with a multispectral camera, SPAD, and smartphone photography methods were 0.63, 0.54, and 0.81, respectively. In the estimation accuracy evaluation, the method of smartphone photography had the smallest root mean square error (RMSE = 9.80 mg/kg). The accuracy of the smartphone photography method was slightly higher than the other two methods. Due to the limitations of these models, it was found that the crop nitrogen estimation methods based on canopy spectrum were not suitable for the crops under severe phosphate deficiency. In addition, in estimation of soil nitrate nitrogen content, there were saturation responses in the estimation indicators of the three methods. In order to introduce these three methods in the precise management of nitrogen fertilizer, it is necessary to further improve their estimation models.

Hyperspectral estimation model of soil Pb content and its applicability in different soil types

In order to obtain Pb content in soil quickly and efficiently, a multivariate linear regression (MLR) and a principal component regression (PCR) Pb content estimation model were established on the basis of hyperspectral techniques, and their applicability in different soil types was evaluated. Results indicated that Pb exhibited strong spatial heterogeneity in the study area, and more than 82% of the samples exceeded the background value. In addition, the pollution range was large. Pb was sensitive in the near-infrared band, and the correlation of absorbance (AB) was most significant of all the transformed forms. Both models achieved optimal stability and reliability when AB was used as an independent variable. Compared with the PCR model, the stability, fitting accuracy, and predictive power of the MLR model were superior with a coefficient of determination, root mean square error, and mean relative error of 0.724%, 24.92%, and 28.22%, respectively. Both models could be applied to different soil types; however, MLR had better applicability compared with PCR. The PCR model that distinguished different soil types had better reliability than one that did not. Thus, the model established via hyperspectral techniques can achieve large-area, rapid, and efficient soil Pb content monitoring, which can provide technical support for the treatment of heavy metal pollution in soil.

Development of a predictive model for stromal content in prostate cancer samples to improve signature performance.

Prostate cancer is heterogeneous in both cellular composition and patient outcome, and development of biomarker signatures to distinguish indolent from aggressive tumours is a high priority. Stroma plays an important role during prostate cancer progression and undergoes histological and transcriptional changes associated with disease. However, identification and validation of stromal markers is limited by a lack of datasets with defined stromal/tumour ratio. We have developed a prostate‐selective signature to estimate the stromal content in cancer samples of mixed cellular composition. We identified stromal‐specific markers from transcriptomic datasets of developmental prostate mesenchyme and prostate cancer stroma. These were experimentally validated in cell lines, datasets of known stromal content, and by immunohistochemistry in tissue samples to verify stromal‐specific expression. Linear models based upon six transcripts were able to infer the stromal content and estimate stromal composition in mixed tissues. The best model had a coefficient of determination R 2 of 0.67. Application of our stromal content estimation model in various prostate cancer datasets led to improved performance of stromal predictive signatures for disease progression and metastasis. The stromal content of prostate tumours varies considerably; consequently, deconvolution of stromal proportion may yield better results than tumour cell deconvolution. We suggest that adjusting expression data for cell composition will improve stromal signature performance and lead to better prognosis and stratification of men with prostate cancer. © 2019 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

A multi-region combined model for non-destructive prediction of soluble solids content in apple, based on brightness grade segmentation of hyperspectral imaging

On-line estimation of fruit internal attributes based on visible-near infrared spectrum is an effective approach for improving fruit value and farmer income. Brightness correction of the hyperspectral image can significantly affect the accuracy of quality estimation in fruits with spherical geometric structure, while pixel by pixel correction method is time-consuming and impractical in on-line rapid detection. To improve the flexibility and speed of the soluble solids content (SSC) estimation model of intact apple, the spectra of core region, middle region and outer region were extracted from hyperspectral reflectance imaging over the region of 400–1000 nm with a brightness grade segmentation method, and then a multi-region combined partial least square (MCPLS) prediction model was built. Results showed that MCPLS method achieved better results than traditional PLS and multi-region average PLS methods. To further improve the applicability of the prediction model in practice, 21 wavelengths effective for SSC estimation were selected by successive projection algorithm and used to rebuild the prediction model using MCPLS method; the correlation coefficient, root mean square error of prediction set and residual predictive deviation were 0.9132, 0.3929 and 2.1652 respectively. Additionally, multi-region combined method just needs to compute the average spectra of each region, which significantly improved the detection speed by comparison with previous pixel by pixel brightness correction method. Hence the multi-region combined prediction model of SSC was developed based on the spectral contribution of each region to SSC prediction and the method of brightness grade segmentation.

Estimation of HIV‐1 viral load in plasma of HIV‐1‐infected people based on the associated Raman spectroscopic peaks

AbstractMost HIV viral load determination techniques available commercially are anchored on direct measurements of either HIV ribonucleic acid (RNA), provirus DNA, or viral antigen. Such techniques often require expensive reagents which makes the process expensive. This study reported the feasibility of label‐free determination of HIV‐1 viral load in plasma based on the consequence of the virus in the components of plasma. The study aimed to provide a relatively cheap and faster HIV‐1 detection and further estimate the concentration of the virus without using any reagent. We subjected 22 HIV‐1‐infected human plasma samples to Raman peak height evaluation to develop a detection and concentration estimation model for HIV‐1. Simultaneously, all the samples were examined for HIV‐1 infection using qualitative polymerase chain reaction (PCR) test. The positive samples were further subjected to quantitative PCR to determine their corresponding viral load. Principal component analysis (PCA) and artificial neural network (ANN) were employed in Raman spectral analysis to enhance label‐free detection of the HIV‐1 in plasma. The quantification model results for HIV‐1 yielded a good correlation with those obtained by the reference quantitative PCR method. HIV‐1 viral load estimation based on the associated Raman spectral peaks centered at 1,270 and 1,446 cm−1 achieved a clinically accepted coefficient of determination (R2 > 0.9). The viral detection sensitivity from the two associated peaks were 95 and 100 copies of the virus per milliliter of plasma, respectively, hence showing that the Raman‐based model can be a potential HIV‐1 diagnostic and viral load estimation tool.

Visualization of Chlorophyll Content Distribution in Apple Leaves Based on Hyperspectral Imaging Technology

We took distribution visualization of chlorophyll content in apple leaves to estimate the nutrient content and growth levels of apple leaves. 130 mature and non-destructive apple leaves were collected, and imaging spectroscopy data were collected by SOC710VP hyperspectral imager. The chlorophyll content of the leaves was determined on the spectral information of the leaves. After pre-processing, we took linear wavelength stepwise regression method to choose the sensitive wavelength of chlorophyll content. And then we established partial least squares, principal component analysis and stepwise regression model. Finally, the chlorophyll content distribution visualization was realized. The results showed that the sensitive wavelengths of the chlorophyll content were 712.50 nm, 509.95 nm, 561.22 nm, 840.62 nm, 696.67 nm and 987.91 nm. The R2, RMSE, RE of the optical chlorophyll content estimation model, and the principal component analysis regression model, were 0.800, 0.319 and 26.4%. The chlorophyll content of each pixel on the hyperspectral image of apple leaves was calculated by the best estimation model and we completed the visualization distribution of chlorophyll content, which provided a technical support for the rapid detection of nutrient distribution.

Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method

In order to estimate the chlorophyll content of maize plant non-destructively and rapidly, the research was conducted on maize at the heading stage using spectroscopy technology. The spectral reflectance of maize canopy was measured and processed following wavelet denoising and multivariate scatter correction (MSC) to reduce the noise influence. Firstly, the signal to noise ratio (SNR) and curve smoothness (CS) were used to evaluate the denoising effect of different wavelet functions and decomposition levels. As a result, the Sym6 wavelet basis function and the 5th level decomposition were determined to denoise the original signal. The MSC method was used to eliminate the scattering effect after denoising. Then three spectral ranges were extracted by interval partial least squares (IPLS) including the 525-549 nm, 675-749 nm and 850-874 nm. Finally, the chlorophyll content estimation model was developed by using support vector regression (SVR) method. The calibration Rc2 of the SVR model was 0.831, the RMSEC was 1.3852 mg/L; the validation Rv2 was 0.809, the RMSEP was 0.8664 mg/L. The results show that the SNR and CS indicators can be used to select the parameters for wavelet denoising and model can be used to estimate the chlorophyll content of maize canopy in the field. Keywords: maize canopy, spectral reflectance, wavelet denoising, SVR model, chlorophyll content DOI: 10.25165/j.ijabe.20181106.3072 Citation: Liu H J, Li M Z, Zhang J Y, Gao D H, Sun H, Yang L W. Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method. Int J Agric & Biol Eng, 2018; 11(6): 132–137.

Drug delivery to the eye anterior chamber by intraocular lenses: An in vivo concentration estimation model

Drug loaded intraocular lenses have been proposed as an alternative to the conventional post-cataract removal prophylaxis through topical drug administration, since the drug or combination of drugs released from the lenses are delivered directly to the target site. In this work, a mathematical model to estimate the concentration of drug released from such lenses in the eye aqueous humor was developed. To attain these estimated concentration profiles, partition and effective diffusivity coefficients for the specific lens material were obtained from standard in vitro release experiments. The model was validated by comparing the predicted aqueous humor concentrations with those obtained in in vivo studies where hydrophilic acrylic intraocular lens loaded with an antibiotic (moxifloxacin) were implanted in rabbits. Subsequently, other partition and effective diffusivity values were determined for levofloxacin, diclofenac and ketorolac in the same hydrophilic acrylic and in a second material, a silicone hydrogel. Predicted drug concentrations in the aqueous humor allowed an initial screening and evaluation of the most promising system for post-cataract removal prophylaxis, with the hydrophilic acrylic material presenting promising results, especially for moxifloxacin and diclofenac controlled release.

Simple, fast, and low-cost camera-based water content measurement with colorimetric fluorescent indicator

Recently, a simple, sensitive, and low-cost fluorescent indicator has been proposed to determine water contents in organic solvents, drugs, and foodstuffs. The change of water content leads to the change of the indicator’s fluorescence color under the ultra-violet (UV) light. Whereas the water content values could be estimated from the spectrum obtained by a bulky and expensive spectrometer in the previous research, this paper demonstrates a simple and low-cost camera-based water content measurement scheme with the same fluorescent water indicator. Water content is calculated over the range of 0–30% by quadratic polynomial regression models with color information extracted from the captured images of samples. Especially, several color spaces such as RGB, xyY, L∗a∗b∗, u′v′, HSV, and YCBCR have been investigated to establish the optimal color information features over both linear and nonlinear RGB data given by a camera before and after gamma correction. In the end, a 2nd order polynomial regression model along with HSV in a linear domain achieves the minimum mean square error of 1.06% for a 3-fold cross validation method. Additionally, the resultant water content estimation model is implemented and evaluated in an off-the-shelf Android-based smartphone.

Estimation of rice protein content before harvest using ground-based hyperspectral imaging and region of interest analysis

Protein content, which represents rice taste quality, must be estimated in order to create a harvesting plan as well as next year’s basal dressing fertilizer application plan. Ground-based hyperspectral imaging with high resolution (1 × 1 mm per pixel) was used for estimating the protein content of brown rice before harvest. This paper compares the estimation accuracy of rice protein content estimation models generated from the mean reflectances of five regions of interest (ROIs): the overall target area, dark area (less illuminated parts of the rice plants), canopy area (leaves, yellow leaves, and ears), leaf area, and ear and yellow leaf area. The size of the target sampling area was 0.85 × 0.85 m. An R + G + B histogram and a GNDVI–NDVI image were used to separate the target area into the individual ROIs. The values of the coefficient of determination R 2 and the root mean square error of prediction (RMSE) were similar for each model: R 2 ranged from 0.83 to 0.86 and RMSE ranged from 0.27 to 0.30% for all models except for the dark area model, where R 2 = 0.76 and RMSE = 0.35%. There were no significant differences in the magnitude of the estimation error among all models. This result indicates that it is not necessary to obtain an image with a ground resolution that is greater than 0.85 × 0.85 m per pixel to estimate rice protein content before harvest. This result should provide useful information when deciding the altitude of platforms for imaging rice fields.

Estimation of ice formation in mortar saturated with sodium chloride solutions

Frost damage of concrete is usually caused by ice expansion, therefore, the ice formation of NaCl solutions is of significant importance for predicting the mechanical degradation of concrete under the combined frost action and NaCl attack. In this study, the ice formation in cementitious materials saturated with different concentrations of NaCl solution is theoretically investigated first. Then the ice formation in mortar is further studied experimentally by electrical measurements. To estimate the ice amount based on the electrical measurements, the relationship between temperature, saturation degree, solution concentration and the electrical conductivity of mortar specimen is clarified. With regard to ice formation and salt crystallization during freeze-thaw, the ice content estimation model is proposed for mortar specimens. In addition, electrical response of meso-scale mortar specimens saturated with NaCl solutions with freeze-thaw cycles (FTCs) is measured. The electrical test results are interpreted with the proposed model and the ice formation is estimated with FTCs. The results from electrical measurements are compared with the theoretical calculations, and acceptable agreement is observed.

Remote sensing models of structure-related biochemicals and pigments for classification of trees

Abstract Global vegetation distribution is the result of environmental conditions and the genetic make-up of plants. In view of the intensive discussions on climate change and its effect on living organisms on earth, it has become necessary to develop new methods and strategies to monitor and follow the changes in global plant distribution. In this research, we focused on a vegetation analysis using spectral reflectance profiles linked to biochemical concentrations. We performed the spectroscopic measurements of Pistacia species at canopy and leaf levels. Concomitant chemical analyses of leaf and bark materials enabled the development of remote sensing (RS) indices of structure-related biochemicals and pigments. We developed RS indices for cellulose, lignin, chlorophyll, carotenoid, anthocyanin and wax. Since the wax was the least studied in this context and due to the fact that it is the first layer of the plant surface that interacts with the incident light, it deserved special attention and was assumed to affect the spectral reflectance and, in combination with the other biochemicals, to contribute to better species identification. In the modeling process, we showed that apart from the major energy absorption spectral bands related to a given biochemical, there were supplementary bands that had a significant effect on the accuracy of the biochemical content estimation. Another factor affecting the accuracy of the biochemical estimation was the season. Thus, we divided the biochemical content estimation models into seasonal groups of spring, summer and fall. The RS indices developed in this work, together with literature-reported RS indices, were used for Pistacia classification. The accuracy (69%) of species classification was significantly higher in spring at an early vegetation stage than in summer (50%), and fall (37%). As a proof of concept, the same sets of RS indices were also used for classifying the genera and families of various plants in the Mediterranean forest using EO1 Hyperion images. The accuracy of the classification maps was 79%, when the full set of RS indices developed in this work was used.