Partial Least Squares Regression Method Research Articles

Fourier transform infrared spectroscopy of milk samples as a tool to estimate energy balance, energy- and dry matter intake in lactating dairy cows.

The objective of the study was to evaluate the potential of Fourier transform infrared spectroscopy (FTIR) analysis of milk samples to predict body energy status and related traits (energy balance (EB), dry matter intake (DMI) and efficient energy intake (EEI)) in lactating dairy cows. The data included 2371 milk samples from 63 Norwegian Red dairy cows collected during the first 105 days in milk (DIM). To predict the body energy status traits, calibration models were developed using Partial Least Squares Regression (PLSR). Calibration models were established using split-sample (leave-one cow-out) cross-validation approach and validated using an external test set. The PLSR method was implemented using just the FTIR spectra or using the FTIR together with milk yield (MY) or concentrate intake (CONCTR) as predictors of traits. Analyses were conducted for the entire first 105 DIM and separately for the two lactation periods: 5 ≤ DIM ≤ 55 and 55 < DIM ≤ 105. To test the models, an external validation using an independent test set was performed. Predictions depending on the parity (1st, 2nd and 3rd-to 6th parities) in early lactation were also investigated. Accuracy of prediction (r) for both cross-validation and external test set was defined as the correlation between the predicted and observed values for body energy status traits. Analyzing FTIR in combination with MY by PLSR, resulted in relatively high r-values to estimate EB (r = 0.63), DMI (r = 0.83), EEI (r = 0.84) using an external validation. Only moderate correlations between FTIR spectra and traits like EB, EEI and dry matter intake (DMI) have so far been published. Our hypothesis was that improvements in the FTIR predictions of EB, EEI and DMI can be obtained by (1) stratification into different stages of lactations and different parities, or (2) by adding additional information on milking and feeding traits. Stratification of the lactation stages improved predictions compared with the analyses including all data 5 ≤ DIM ≤105. The accuracy was improved if additional data (MY or CONCTR) were included in the prediction model. Furthermore, stratification into parity groups, improved the predictions of body energy status. Our results show that FTIR spectral data combined with MY or CONCTR can be used to obtain improved estimation of body energy status compared to only using the FTIR spectra in Norwegian Red dairy cattle. The best prediction results were achieved using FTIR spectra together with MY for early lactation. The results obtained in the study suggest that the modeling approach used in this paper can be considered as a viable method for predicting an individual cow's energy status.

Exploring multivariate linear regression methods for the prediction of total phenolic content in standard American lager beers using synchronous fluorescence spectroscopy fused data

This work aims to explore chemometric methods for determining the total phenolic content in Brazilian standard American lager beers using synchronous fluorescence spectroscopy fused data. Two hundred and sixteen (216) beer samples were diluted at a ratio of 1:5 (v/v), sonicated for 15 ​min in a water bath, and buffered using an acetic acid/acetate buffer of pH 4.5. The synchronous fluorescence spectra were obtained from 200 to 600 ​nm with a resolution of 1 ​nm. However, different offsets were tested for synchronous fluorescence (Δλ ​= ​20, 50, and 80). All measurements were carried out in triplicate, and the Folin-Ciocalteu method was used as the reference method for the total phenolic content. All chemometric methods were explored using R software and its graphic interface, RStudio. First, the spectral data with different offsets were normalized and fused. After this, the fused data were smoothed with the Savitzky-Golay algorithm with a window of length 11 and a quadratic polynomial, followed by data mean centering. Robust principal component analysis (ROBPCA) was used to identify anomalous data. The Kennard-Stone algorithm was used to split the dataset into 75% for the training set and 25% for the test set. The prediction models used were partial least squares (PLS), orthogonal partial least squares (O-PLS), and elastic net regressions with cross-validation (CV). Ensemble PLS and ensemble sparse PLS with bootstrap resampling were also used. Other PLS regression methods based on the selection of variables were tested, such as significance multivariate regression (sMC – PLS), uninformative variable elimination (UVE – PLS), and interval PLS (iPLS) global and optimized models with cross-validation. All the regression models were built with the training set. The validation was carried out with the application of the regression models to the test set. Within this context, two multivariate regression were highlighted, the CV elastic net and iPLS optimized models, with the root mean square error of prediction (RMSEP) equaling 1.0 and 1.1 ​mg GAE L−1, respectively.

Non-destructive Estimation of Chlorophyll a Content in Red Delicious Apple Cultivar Based on Spectral and Color Data

Non-destructive estimation of the chemical properties of fruit is an important goal of researchers in the food industry, since online operations, such as fruit packaging based on the amount of different chemical properties and determining different stages of handling, are done based on these estimations. In this study, chlorophyll a content in Red Delicious apple cultivar is predicted as a chemical property that is altered by apple ripening stage, using non-destructive spectral and color methods combined. Two artificial intelligence methods based on hybrid Multilayer Perceptron Neural Network - Artificial Bee Colony Algorithm (ANN-ABC) and Partial least squares regression (PLSR) were used in order to obtain a non-destructive estimation of chlorophyll a content. In application of the PLSR method, various pre-processing algorithms were used. In order to statistically properly validate the hybrid ANN-ABC predictive method, 20 runs were performed. Results showed that the best regression coefficient of the PLSR method in predicting chlorophyll a content using spectral data alone was 0.918. At the same time, the average determination coefficient over 20 repetitions in hybrid ANN-ABC in the estimation of chlorophyll a content, using spectral data and color features were higher than 0.92±0.040 and 0.89±0.045, respectively, which to our knowledge is a remarkable non-intrusive estimation result.

Robust Wavelength Selection Using Filter-Wrapper Method and Input Scaling on Near Infrared Spectral Data.

The extraction of relevant wavelengths from a large dataset of Near Infrared Spectroscopy (NIRS) is a significant challenge in vibrational spectroscopy research. Nonetheless, this process allows the improvement in the chemical interpretability by emphasizing the chemical entities related to the chemical parameters of samples. With the complexity in the dataset, it may be possible that irrelevant wavelengths are still included in the multivariate calibration. This yields the computational process to become unnecessary complex and decreases the accuracy and robustness of the model. In multivariate analysis, Partial Least Square Regression (PLSR) is a method commonly used to build a predictive model from NIR spectral data. However, in the PLSR method and common commercial chemometrics software, there is no standard wavelength selection procedure applied to screen the irrelevant wavelengths. In this study, a new robust wavelength selection procedure called the modified VIP-MCUVE (mod-VIP-MCUVE) using Filter-Wrapper method and input scaling strategy is introduced. The proposed method combines the modified Variable Importance in Projection (VIP) and modified Monte Carlo Uninformative Variable Elimination (MCUVE) to calculate the scale matrix of the input variable. The modified VIP uses the orthogonal components of Partial Least Square (PLS) in investigating the informative variable in the model by applying the amount of variation both in and , simultaneously. The modified MCUVE uses a robust reliability coefficient and a robust tolerance interval in the selection procedure. To evaluate the superiority of the proposed method, the classical VIP, MCUVE, and autoscaling procedure in classical PLSR were also included in the evaluation. Using artificial data with Monte Carlo simulation and NIR spectral data of oil palm (Elaeis guineensis Jacq.) fruit mesocarp, the study shows that the proposed method offers advantages to improve model interpretability, to be computationally extensive, and to produce better model accuracy.

Estimating purple-soil moisture content using Vis-NIR spectroscopy

Soil moisture is essential for plant growth in terrestrial ecosystems. This study investigated the visible-near infrared (Vis-NIR) spectra of three subgroups of purple soils (calcareous, neutral, and acidic) from western Chongqing, China, containing different water contents. The relationship between soil moisture and spectral reflectivity (R) was analyzed using four spectral transformations, and estimation models were established for estimating the soil moisture content (SMC) of purple soil based on stepwise multiple linear regression (SMLR) and partial least squares regression (PLSR). We found that soil spectra were similar for different moisture contents, with reflectivity decreasing with increasing moisture content and following the order neutral > calcareous > acidic purple soil (at constant moisture content). Three of the four spectral transformations can highlight spectral sensitivity to SMC and significantly improve the correlation between the reflectance spectra and SMC. SMLR and PLSR methods provide similar prediction accuracy. The PLSR-based model using a first-order reflectivity differential (R’) is more effective for estimating the SMC, and gave coefficient of determination root mean square errors of validation (RMSEV), and ratio of performance to inter-quartile distance (RPIQ) values of 0.946, 1.347, and 6.328, respectively, for the calcareous purple soil, and 0.944, 1.818, and 6.569, respectively, for the acidic purple soil. For neutral purple soil, the best prediction was obtained using the SMLR method with R’ transformation, yielding R2v, RMSEV and RPIQ values of 0.973, 0.888 and 8.791, respectively. In general, PLSR is more suitable than SMLR for estimating the SMC of purple soil.

Water-based measured-value fuzzification improves the estimation accuracy of soil organic matter by visible and near-infrared spectroscopy

Visible and near-infrared (Vis-NIR) reflectance spectroscopy continues to emerge as a rapid and effective approach for estimating several soil physical and chemical properties including soil organic matter (SOM), but its accuracy is restricted by many factors including soil water. This study proposed the water-based measured-value fuzzification (WMF) method to decrease the influence of soil water, and combined with the partial least squares regression (PLSR) to develop SOM models. Vis-NIR spectral data was measured by an ASD FieldSpec 3 spectrometer. After WMF analysis, the PLSR method was used to develop SOM models. By comparison with the PLSR model, the WMF-PLSR model produced markedly better results (root mean square error of validation [RMSEV] = 2.776 g/kg, mean relative error of validation [MREV] = 8.111%, and ratio of performance to interquartile range [RPIQv] = 4.729). With these, the WMF method combined with PLSR shows the potential for estimating SOM content and expands the range of observation methods.

A Comparative Study of PLSR and SVM-R with Various Preprocessing Techniques for the Quantitative Determination of Soluble Solids Content of Hardy Kiwi Fruit by a Portable Vis/NIR Spectrometer.

Linear partial least square and non-linear support vector machine regression analysis with various preprocessing techniques and their combinations were used to determine the soluble solids content of hardy kiwi fruits by a handheld, portable near-infrared spectroscopy. Fruits of four species, namely Autumn sense (A), Chungsan (C), Daesung (D), and Green ball (Gb) were collected from five different areas of Gwangyang (G), Muju (M), Suwon (S), Wonju (Q), and Yeongwol (Y) in South Korea. The dataset for calibration and prediction was prepared based on each area, species, and in combination. Half of the dataset of each area, species, and combined dataset was used as calibrated data and the rest was used for model validation. The best prediction correlation coefficient ranges between 0.67 and 0.75, 0.61 and 0.77, and 0.68 for the area, species, combined dataset, respectively using partial least square regression (PLSR) method with different preprocessing techniques. On the other hand, the best correlation coefficient of predictions using the support vector machine regression (SVM-R) algorithm was 0.68 and 0.80, 0.62 and 0.79, and 0.74 for the area, species, and combined dataset, respectively. In most cases, the SVM-R algorithm produced better results with Autoscale preprocessing except G area and species Gb, whereas the PLS algorithm shows a significant difference in calibration and prediction models for different preprocessing techniques. Therefore, the SVM-R method was superior to the PLSR method in predicting soluble solids content of hardy kiwi fruits and non-linear models may be a better alternative to monitor soluble solids content of fruits. The finding of this research can be used as a reference for the prediction of hardy kiwi fruits soluble solids content as well as harvesting time with better prediction models.

Rapid detection of Aspergillus spp. infection levels on milled rice by headspace-gas chromatography ion-mobility spectrometry (HS-GC-IMS) and E-nose

This study described the rapid detection of milled rice infected with Aspergillus spp. species based on headspace-gas chromatography ion-mobility spectrometry (HS-GC-IMS) and electronic nose (E-nose) combined with chemometrics, namely principal component analysis (PCA), k-nearest neighbor (kNN) and partial least squares regression (PLSR). 3D HS-GC-IMS imaging and their response differences enabled the discrimination among fungal species. kNN was used to differentiate rice samples with cdifferent levels of fungal infection and achieved correct classified rate of 94.44% and 91.67% by HS-GC-IMS and E-nose, respectively. PLSR method was used for quantitative regression of fungal colony counts in rice samples and good prediction performances were achieved by HS-GC-IMS (Rp2 = 0.909, RMSEP = 0.202) and E-nose (Rp2 = 0.864, RMSEP = 0.235). The results indicated that both HS-GC-IMS and E-nose approaches can potentially be implemented for the detection of fungal contamination levels in milled rice, and HS-GC-IMS fingerprinting coupled with chemometrics might be used as an alternative tool for a highly sensitive method. This research might provide scientific information on the rapid, non-destructive, and effective fungal detection system for rice grains.

Hilbert Huang Transformation with filtering as a pre-treatment method for the quantitative study of glucose in near infrared spectra.

In this paper, a novel pre-treatment technique Hilbert Huang Transformation with filtering (HHTF) that is coupling of the Hilbert Huang Transformation and the digital filtering is proposed for the measurement of glucose from near infrared spectroscopy. HHTF comprises of the Empirical Mode Decomposition (EMD) and the Hilbert Spectral Analysis. In Hilbert spectral analysis, Butterworth filtering was used to eliminate the noise present in the Intrinsic Mode Functions (IMFs). The traditional Partial Least squares Regression (PLSR) has been used as the regression method. The proposed HHTF with the PLSR method has been assessed to determine the concentration of glucose from near infrared spectra of two distinct compositions that are prepared by mixing triacetin, urea and glucose in a phosphate buffer solution (PBS) and another composition of glucose and human serum albumin in a PBS. The efficiency of the proposed method has been compared with the standard normal variate and the 1st derivative preprocessing methods and is shown to outperform both.

Application of FT-NIR spectroscopy and NIR hyperspectral imaging to predict nitrogen and organic carbon contents in mine soils

Abstract The aim of this study was to compare the performance of FT-NIR spectroscopy and near-infrared hyperspectral imaging (NIR-HSI) in predicting the Corg and Nt contents in mine soils. The mine soil samples were measured for the Corg and Nt contents and their NIR spectra were recorded (1000–2500 nm). Predictive models were developed using 126 samples with partial least square regression (PLSR) or artificial neural networks (ANN) and validated with 58 independent samples. The NIR-HSI based models had distinctly higher accuracy of Corg content prediction than those based on FT-NIR data in both PLSR and ANN methods, as indicated by lower of standard errors of prediction. The prediction accuracy for the Nt content was similar for the two spectral methods and both chemometric approaches tested. The study showed that despite lower spectral resolution the NIR-HSI spectra retained all the information needed for accurate prediction of Corg and Nt contents.

An integrated strategy for discovering effective components of Shaoyao Gancao decoction for treating neuropathic pain by the combination of partial least-squares regression and multi-index comprehensive method

Ethnopharmacological relevanceNeuropathic pain, the incidence of which ranges from 5 to 8% in the general population, remains challenge in the treatment. Shaoyao Gancao decoction (SGD) is a Chinese classical formula used to relieve pain for thousands of years and has been applied for neuropathic pain nowadays. However, the effective components of SGD for the treatment of neuropathic pain remains unclear. Aims of studyTo investigate the effect and potential mechanism of SGD against neuropathic pain and further reveal the effective components of SGD in the treatment of neuropathic pain. Materials and methodsSpared nerve injury (SNI) model rats of neuropathic pain were orally given SGD to intervene, the components in vivo after SGD administration were determined, behavior indicators, biochemical parameters, and metabolomics were applied for assessing the efficacy. Then correlation between components and biomarkers was analyzed by pearson correlation method. To further measure the contribution of components to efficacy, the combination of partial least-squares regression (PLSR) and multi-index comprehensive method was carried out, according to the corresponding contribution degree of the results, the components with large contribution degree were considered as the effective components. ResultsSGD exhibited a significant regulatory effect on neuropathic pain, which could increase the pain threshold and decrease the levels of SP, β-EP, PGE2 and NO. With the high resolution of UPLC-Q-TOF/MS technology, a total of 128 compounds from SGD were identified and 44 of them were absorbed in blood. Besides, 40 serum biomarkers were identified after intervention of SGD and the metabolic pathways were constructed. The key metabolic pathways including Glycerophospholipid metabolism, Linoleic acid metabolism, Alpha-linolenic acid metabolism, Glycosylphosphatidylinositol-anchor biosynthesis and Arachidonic acid metabolism may be related to the regulation of neuropathic pain. Metabolomics combined with PLSR and multi-index comprehensive method was utilized to discover 5 components including paeonol, DL-Arabinose, benzoic acid, hispaglabridin A and paeonilactone C as effective components of SGD in the treatment of neuropathic pain. This strategy was used to explore the effective components of SGD and elucidate its possible analgesic mechanism. ConclusionThis study demonstrate that SGD significantly relieved neuropathic pain and elucidated the effective components of SGD for treating neuropathic pain, the strategy as an illustrative case study can be applied to other classical formula and is beneficial to improve the quality and efficacy.

Effect of ambiance on the coal characterization using laser-induced breakdown spectroscopy (LIBS)

The influence of surrounding gases, such as He, N2, atmospheric air, and Ar, and gas flow rate on the laser-induced breakdown spectroscopy (LIBS) characterization of coals in free space is studied. The atomic and molecular carbon (C2 and CN) emission intensities are observed to be higher in Ar and N2 ambiance. Quantitative analysis of carbon and ash content in different coal samples is carried out using the carbon bound atomic and molecular emission signals and the ash forming elements (Si, Fe, Mg, Al, Ca, Na, and K) signals. The sum of the LIBS emission of the all and major ash forming elements increased linearly with an increase in the ash content. Similarly, the ratio between the carbon signals (C I, CN, and C2) and the sum of major ash forming elements (Si, Al, Fe, and Ca) also showed a linear increase with the increase in carbon content in coal samples. The linear coefficient of regression, R2, was estimated to be 0.67, 0.58, and 0.85, and the root mean square of calibration samples was estimated to be 5.71, 5.82, and 5.57 wt% using the partial least square regression (PLSR) method for air (no flow), N2, and Ar atmosphere, respectively. The precision and accuracy of the carbon measurement in coal samples by the LIBS technique using the PLSR method were higher in the presence of Ar than air or N2 atmosphere due to the plasma shielding effect.

Application of Postprocessing to Watershed-Scale Subseasonal Climate Forecasts over the Contiguous United States

AbstractSubseasonal to seasonal (S2S) climate forecasting has become a central component of climate services aimed at improving water management. In some cases, operational S2S climate predictions are translated into inputs for follow-on analyses or models, whereas the S2S predictions on their own may provide for qualitative situational awareness. At the spatial scales of water management, however, S2S climate forecasts often suffer from systematic biases, and low skill and reliability. This study assesses the potential to improve S2S forecast skill and salience for watershed applications through the use of postprocessing to harness skills in large-scale fields from the global climate model forecast outputs. To this end, the components-based technique—partial least squares regression (PLSR)—is used to improve the skill of biweekly temperature and precipitation forecasts from the Climate Forecast System version 2 (CFSv2). The PLSR method forms predictor components based on a cross-validated analysis of hindcasts from CFSv2 climate and land surface fields, and the results are benchmarked against raw CFSv2 forecasts, remapped to intermediate-scale watershed areas. We find that postprocessing affords marginal to moderate gains in skill in many watersheds, raising climate forecast skill above a usability threshold over the four seasons analyzed. In other locations, however, postprocessing fails to improve skill, particularly for extreme events, and can lead to unreliably narrow forecast ranges. This work presents evidence that the statistical postprocessing of climate forecast system outputs has potential to improve forecast skill, but that more thorough study of alternative approaches and predictors may be needed to achieve comprehensively positive outcomes.

Estimation of cotton Car/Chla ratio by hyperspectral vegetation indices and partial least square regression

<p indent=0mm>Estimating the ratio between carotenoid to chlorophyll <italic>a</italic> (Car/Chla) provides an additional avenue for the assessment of physiology and phenology of plant growth and development. With the aim of assessing cotton Car/Chla ratio from hyperspectral reflectance, a wide range of carotenoid (Car) and chlorophyll <italic>a</italic> concentrations, and leaf and canopy reflectance at cotton different growth stages were measured. The performance of a variety of Car/Chla ratio related vegetation indices and partial least square regression (PLSR) for Car/Chla ratio and Car estimation were tested. Among all tested vegetation indices, PRI (Photochemical Reflectance Index) and linear PRI models had the most significant correlations with Car/Chla ratio and Car, and could accurately estimate, Car/Chla ratio (<italic>R</italic>²_{leaf level} = 0.69 and <italic>R</italic>²_{canopy level} = 0.67) and Car concentration (<italic>R</italic>²_{leaf level} = 0.44 and<italic> R</italic>²_{canopy level} = 0.36). The best estimation of the Car/Chla ratio and Car was provided by PLSR models with <italic>R</italic>² > 0.80 between the estimated and measured value for Car/Chla ratio and <italic>R</italic>² <italic>= </italic>0.74 for Car. Both reflectance indices and PLSR method were more successful for the estimation of Car/Chla ratio than for that of Car concentration, indicating the promising potential of Car/Chla ratio as a powerful indicator using for plant status monitoring by remote sensing. Besides, accuracy test of models using validation dataset highlighted the remarkable performance of PLSR for Car/Chla (<italic>R</italic>²_{leaf level} = 0.87 and <italic>R</italic>²_{canopy level} = 0.84) and Car (<italic>R</italic>²_{leaf level} = 0.73 and<italic> R</italic>²_{canopy level} = 0.74) estimated by hyperspectral reflectance at both the leaf and canopy levels. The results further prove the remarkable performance of hyperspectral reflectance for the estimation of Car/Chla ratio, and enrich the parameters for monitoring high temperature stress, water deficit stress, and nutrient stress and pest diseases by remote sensing in cotton.

A state-based probabilistic method for decoding hand position during movement from ECoG signals in non-human primate

Objective. In this study, we proposed a state-based probabilistic method for decoding hand positions during unilateral and bilateral movements using the ECoG signals recorded from the brain of Rhesus monkey. Approach. A customized electrode array was implanted subdurally in the right hemisphere of the brain covering from the primary motor cortex to the frontal cortex. Three different experimental paradigms were considered: ipsilateral, contralateral, and bilateral movements. During unilateral movement, the monkey was trained to get food with one hand, while during bilateral movement, the monkey used its left and right hands alternately to get food. To estimate the hand positions, a state-based probabilistic method was introduced which was based on the conditional probability of the hand movement state (i.e. idle, right hand movement, and left hand movement) and the conditional expectation of the hand position for each state. Moreover, a hybrid feature extraction method based on linear discriminant analysis and partial least squares (PLS) was introduced. Main results. The proposed method could successfully decode the hand positions during ipsilateral, contralateral, and bilateral movements and significantly improved the decoding performance compared to the conventional Kalman and PLS regression methods . The proposed hybrid feature extraction method was found to outperform both the PLS and PCA methods . Investigating the kinematic information of each frequency band shows that more informative frequency bands were (15–30 Hz) and (50–100 Hz) for ipsilateral and and (100–200 Hz) for contralateral movements. It is observed that ipsilateral movement was decoded better than contralateral movement for (5–15 Hz) and bands, while contralateral movements was decoded better for (30–200 Hz) and hfECoG (200–400 Hz) bands. Significance. Accurate decoding the bilateral movement using the ECoG recorded from one brain hemisphere is an important issue toward real-life applications of the brain-machine interface technologies.

Quantitative Estimation of Soil Salinization in an Arid Region of the Keriya Oasis Based on Multidimensional Modeling

Soil salinity is one of the major factors causing land degradation and desertification on earth, especially its important damage to farming activities and land-use management in arid and semiarid regions. The salt-affected land is predominant in the Keriya River area of Northwestern China. Then, there is an urgent need for rapid, accurate, and economical monitoring in the salt-affected land. In this study, we used the electrical conductivity (EC) of 353 ground-truth measurements and predictive capability parameters of WorldView-2 (WV-2), such as satellite band reflectance and newly optimum spectral indices (OSI) based on two dimensional and three-dimensional data. The features of spectral bands were extracted and tested, and different new OSI and soil salinity indices using reflectance of wavebands were built, in which spectral data was pre-processed (based on First Derivative (R-FD), Second Derivative (R-SD), Square data (R-SQ), Reciprocal inverse (1/R), and Reciprocal First Derivative (1/R-FD)), utilizing the partial least-squares regression (PLSR) method to construct estimation models and mapping the regional soil-affected land. The results of this study are the following: (a) the new OSI had a higher relevance to EC than one-dimensional data, and (b) the cross-validation of established PLSR models indicated that the β-PLSR model based on the optimal three-band index with different process algorithm performed the best result with R2V = 0.79, Root Mean Square Errors (RMSEV) = 1.51 dS·m−1, and Relative Percent Deviation (RPD) = 2.01 and was used to map the soil salinity over the study site. The results of the study will be helpful for the study of salt-affected land monitoring and evaluation in similar environmental conditions.

QSAR modeling with ETA indices for cytotoxicity and enzymatic activity of diverse chemicals

The discharge of huge amount of chemicals from industries into the environment has led to toxicity towards different living species. Therefore, risk assessment of these chemicals is essential. In order to comply with the ethical issues, in this present work, we have developed quantitative structure-activity relationship (QSAR) models for cytotoxicity against GFS (goldfish scale) tissue (Crassius auratus) and enzymatic activity against PLHC-1 cell line (topminnow hepatoma cell line) (Poeciliopsis lucida). The final models were developed by means of PLS (Partial Least Squares) regression method applying only ETA (extended topochemical atom) descriptors. The results obtained from various validation parameters (obtained from the both datasets) suggested that the developed models are statistically robust and predictive. From the insights obtained from the models developed from the Neutral Red dye (NR) dataset, it can be concluded that presence of bulky atoms, unsaturation, branching and hetero atoms (most importantly N, Cl) enhance the cytotoxicity towards the Goldfish scale tissue. On the other hand, in case of the Ethoxyresorufin-O-deethylase (EROD) dataset, presence of higher electronegative atoms (O, Cl), polycyclic aromatic hydrocarbons (PAHs) with more number of rings and absence of polar groups and hydrogen bond acceptors enhance enzymatic activity of the PLHC-1 cell line.

Hyper-spectral inversion of soil organic carbon content under different land use types

Soil spectral information differ across different land use types. Understanding the appropriate modeling methods for different land use types can efficiently and accurately invert soil organic carbon content. We collected 248 samples from forest, cultivated land and orchard in the north-central part of Fengxin County, Jiangxi Province. First, original spectral reflectance curves were reduced noises with Savitzky-Golay (SG) filter. Then 10 nm resampling method was used to reduce data redundancy. We used partial least squares regression (PLSR), support vector machine regression based on grid search method (GRID-SVR) and support vector machine regression based on particle swarm optimization (PSO-SVR) to construct the inversion models of soil organic carbon content. The results showed that when constructing a single land-use type inversion model, RPD of the PLSR method for forest, cultivated land and orchard was 1.536, 1.315 and 1.493 respectively. RPD of GRID-SVR method increased 0.150, 0.183 and 0.502 than that of PLSR method, respectively. The PSO-SVR method had higher accuracy, with RPD being 20.8%, 10.0% and 2.7% higher than GRID-SVR for forest, cultivated land and orchard, respectively. The RPD of forest and orchard were 2.036 and 2.049, which well predicts soil organic carbon. The RPD of cultivated land was 1.647, which can make a rough estimate of soil organic carbon. The PSO-SVR model had the best prediction effect on soil organic carbon of different land use types, with the prediction accuracy of soil organic carbon content in forest and orchard being close and higher than cultivated land. Soil nutrition diffed acorss different land use types, which affect the prediction of soil organic carbon content. Models for inversion of soil organic carbon should be constructed separately for different land use types.

Estimation of Crop Growth Parameters Using UAV-Based Hyperspectral Remote Sensing Data.

Above-ground biomass (AGB) and the leaf area index (LAI) are important indicators for the assessment of crop growth, and are therefore important for agricultural management. Although improvements have been made in the monitoring of crop growth parameters using ground- and satellite-based sensors, the application of these technologies is limited by imaging difficulties, complex data processing, and low spatial resolution. Therefore, this study evaluated the use of hyperspectral indices, red-edge parameters, and their combination to estimate and map the distributions of AGB and LAI for various growth stages of winter wheat. A hyperspectral sensor mounted on an unmanned aerial vehicle was used to obtain vegetation indices and red-edge parameters, and stepwise regression (SWR) and partial least squares regression (PLSR) methods were used to accurately estimate the AGB and LAI based on these vegetation indices, red-edge parameters, and their combination. The results show that: (i) most of the studied vegetation indices and red-edge parameters are significantly highly correlated with AGB and LAI; (ii) overall, the correlations between vegetation indices and AGB and LAI, respectively, are stronger than those between red-edge parameters and AGB and LAI, respectively; (iii) Compared with the estimations using only vegetation indices or red-edge parameters, the estimation of AGB and LAI using a combination of vegetation indices and red-edge parameters is more accurate; and (iv) The estimations of AGB and LAI obtained using the PLSR method are superior to those obtained using the SWR method. Therefore, combining vegetation indices with red-edge parameters and using the PLSR method can improve the estimation of AGB and LAI.

Influence of polarized reflection on airborne remote sensing of canopy foliar nitrogen content

ABSTRACT Radiation detected by sensors can reveal information regarding canopy structure and leaf surface properties. It has been shown that the scattering coefficient (Wλ ), a ‘pure’ spectrum obtained after correction for the effect of canopy structure on the bidirectional reflectance factor (BRF), can provide information about biochemical composition; e.g. nitrogen content, more objectively. However, specular radiation reflected from leaf surface (without any information from the leaf interior) has a potential influence on Wλ and thus consequently affects the estimation of canopy nitrogen content (CNC). The so-called specular reflection influence has rarely been studied. Polarized reflectance (R p), as part of the specular reflectance, was used to assess this kind of influence. To model the accurate R p within the study area, six bidirectional polarization distribution function (BPDF) models were intercompared, using the existing POLDER/PARASOL R p database, to produce R p for three vegetation types: needleleaf, broadleaf, and mixed forest. Then, correction for polarized reflection and canopy structure was made to yield a more reasonable and accurate Wλ . An efficient interval partial least-squares regression (iPLSR) method for CNC estimation was used to analyse the impact of polarized reflection on both the 400 nm–2,500-nm canopy Wλ and CNC estimation. The results showed that the contribution of polarization was greater in the strong-absorption spectral region, with an influence on Wλ estimation of up to 25% and 28% in the visible and short-wave infrared regions, respectively. Also, improvements of 0.93% in average regarding the relative mean square error of cross-validation (RMSECV) were seen in CNC estimation accuracy. Moreover, sensitivity analyses of BPDF model parameters, and of the fixed total number of intervals in the iPLSR were also conducted. Improvements with an average of 1.19% regarding the RMSECV was consistently seen in the accuracy of CNC regression after polarization correction, no matter how many fixed intervals were. The results also gave guides on the selection of spectral regions used to estimate forest CNC.