Spectrum Detection of Rice Planthopper Populations from Canopy Reflectance Based on Principal Component Regression

[ Objective] Aiming at problems of early warning for occurrence of rice pests and dynamic monitoring of rice planthopper in field, a detection model for rice planthopper populations was established based on PCR with spectrum detection technology, r Method] Canopy reflectance data were collected using FieldSpeo 3 spectrometer in paddy field, and rice planthoppers populations in hundred hills were detected simultaneously. The sample size was 71, and there were 51 samples in the calibration set and 20 samples in the prediction set. Modeling band was 350 -1 139 nm, and the original spectra were pretreated by first order differential. [ Result] The correlation coefficient of measured values and predictive values was 0. 78, and the RMSEP was 161. [ Conlmion] Spectrum detection was able to be used in investigation and forecasting of rice planthoppere.

Combining Principal Component Regression and Artificial Neural Network to Predict Chlorophyll-a Concentration of Yuqiao Reservoir’s Outflow

In order to investigate the eutrophication degree of Yuqiao Reservoir, a hybrid method, combining principal component regression (PCR) and artificial neural network (ANN), was adopted to predict chlorophyll-a concentration of Yuqiao Reservoir’s outflow. The data were obtained from two sampling sites, site 1 in the reservoir, and site 2 near the dam. Seven water variables, namely chlorophyll-a concentration of site 2 at time t and that of both sites 10 days before t, total phosphorus(TP), total nitrogen(TN),...

Analysis of York Pigs Feeding Behavior Using Stepwise Regression and Principal Component Regression

A statistical analysis was conducted on the feeding behavior of 106 York breeding pigs.Pearson correlation analysis,principal component correlation analysis and multiple stepwise regression equation methods were applied to establish regression equations of the York breeding pigs total feed intake per time and average feed intake per time with corrected fat thickness,feed conversion rate,and corrected daily gain.The results showed that:①there were three peak feed intake periods for the pigs,and the correlation coefficient between the feed intake and the corrected fat thickness of the pigs in the 24 h period was positive or negative,that is,increasing the number of feeding times and the feed intake was not necessarily conducive to the fat thickness accumulation,but the breeding goal of fat thickness could be achieved by controlling the feeding times and feed intake;②the average feed intake of pigs in the 60-90 kg body weight stage was 30%-50%higher than that of the 30-60 kg body weight stage,but the number of feeding times decreased,the peak feeding time was more concentrated,and the feeding duration per time was 3.0 min longer,indicating that as the weight of pigs increased,the feed intake increased significantly;and③the stepwise regression equations and the principal component equations showed that the feeding behavior of York pigs in the 30-90 kg growth stage was not only affected by the feeding time within 24 h,but also by environmental factors such as temperature and humidity.The feeding behavior of York pigs is a complex process of interaction between environmental factors and animal factors.

Neural network and principal component regression in non-destructive soluble solids content assessment:a comparison

Visible and near infrared spectroscopy is a non-destructive,green,and rapid technology that can be utilized to estimate the components of interest without conditioning it,as compared with classical analytical methods.The objective of this paper is to compare the performance of artificial neural network(ANN)(a nonlinear model)and principal component regression(PCR)(a linear model)based on visible and shortwave near infrared(VIS-SWNIR)(400-1000 nm)spectra in the non-destructive soluble solids content measurement of an apple.First,we used multiplicative scattering correction to pre-process the spectral data.Second,PCR was applied to estimate the optimal number of input variables.Third,the input variables with an optimal amount were used as the inputs of both multiple linear regression and ANN models.The initial weights and the number of hidden neurons were adjusted to optimize the performance of ANN.Findings suggest that the predictive performance of ANN with two hidden neurons outperforms that of PCR.

A Hybrid Model Evaluation Based on PCA Regression Schemes Applied to Seasonal Precipitation Forecast

Possible changes in the structure and seasonal variability of the subtropical ridge may lead to changes in the rainfall’s variability modes over Caribbean region. This generates additional difficulties around water resource planning, therefore, obtaining seasonal prediction models that allow these variations to be characterized in detail, it’s a concern, specially for island states. This research proposes the construction of statistical-dynamic models based on PCA regression methods. It is used as predictand the monthly precipitation accumulated, while the predictors (6) are extracted from the ECMWF-SEAS5 ensemble mean forecasts with a lag of one month with respect to the target month. In the construction of the models, two sequential training schemes are evaluated, obtaining that only the shorter preserves the seasonal characteristics of the predictand. The evaluation metrics used, where cell-point and dichotomous methodologies are combined, suggest that the predictors related to sea surface temperatures do not adequately represent the seasonal variability of the predictand, however, others such as the temperature at 850 hPa and the Outgoing Longwave Radiation are represented with a good approximation regardless of the model chosen. In this sense, the models built with the nearest neighbor methodology were the most efficient. Using the individual models with the best results, an ensemble is built that allows improving the individual skill of the models selected as members by correcting the underestimation of precipitation in the dynamic model during the wet season, although problems of overestimation persist for thresholds lower than 50 mm.

Modeling dam deformation using independent component regression method

In the application of regression analysis method to model dam deformation, the ill-condition problem occurred in coefficient matrix always prevents an accurate modeling mainly due to the multicollinearity of the variables. Independent component regression （ICR） was proposed to model the dam deformation and identify the physical origins of the deformation. Simulation experiment shows that ICR can successfully resolve the problem of ill-condition and produce a reliable deformation model. After that, the method is applied to model the deformation of the Wuqiangxi Dam in Hunan province, China. The result shows that ICR can not only accurately model the deformation of the dam, but also help to identify the physical factors that affect the deformation through the extracted independent components.

Optimal Batching Plan of Deoxidation Alloying based on Principal Component Analysis and Linear Programming

As the market competition of steel mills is severe,deoxidization alloying is an important link in the metallurgical process.To solve this problem,principal component regression analysis is adopted to reduce the dimension of influencing factors,and a reasonable and reliable prediction model of element yield is established.Based on the constraint conditions such as target cost function constraint,yield constraint and non-negative constraint,linear programming is adopted to design the lowest cost batting scheme that meets the national standards and production requirements.The research results provide a reliable optimization model for the deoxidization and alloying process of steel mills,which is of positive significance for improving the market competitiveness of steel mills,reducing waste discharge and protecting the environment.

Analysis of the Variability of Canopy Resistance over a Desert Steppe Site in Inner Mongolia, China

ABSTRACT Canopy resistance substantially affects the partitioning of available energy over vegetated surfaces. This study analyzed the variability of canopy resistance and associated driving environmental factors over a desert steppe site in Inner Mongolia, China, through the use of eddy-flux and meteorological data collected from 2008 to 2010. Distinct seasonal and interannual variabilities in canopy resistance were identified within those three years, and these variabilities were controlled primarily by precipitation. Strong interannual variability was found in vapor pressure deficit （VPD）, similar to that of air temperature. Based on the principal component regression method, the analysis of the relative contribution of five major environmental factors [soil-water content （SWC）, leaf-area index （LAI）, photosynthetically active radiation （Kp）, VPD, and air temperature] to canopy resistance showed that the canopy-resistance variation was most responsive to SWC （with 〉 35% contribution）, followed by LAI, especially for water-stressed soil conditions （〉 20% influence）, and VPD （consistently with an influence of approximately 20%）. Canopy-resistance variations did not respond to Kp due to the small interannual variability in Kp during the three years. These analyses were used to develop a new exponential function of water stress for the widely used Jarvis scheme, which substantially improved the calculation of canopy resistance and latent heat fluxes, especially for moist and wet soils, and effectively reduced the high bias in evaporation estimated by the original Jarvis scheme. This study highlighted the important control of canopy resistance on plant evaporation and growth for the investigated desert steppe site with a relatively low LA1.

Quantitative Structure-biodegradability Relationship Study about the Aerobic Biodegradation of Some Aromatic Compounds

10 quantum chemical descriptors of 21 aromatic compounds have been calculated by the semi-empirical quantum chemical method AM1. The Quantitative Structure-Biodegradability Relationships （QSBR） studies were performed by the multiple linear regression （MLR）, principal component regression （PCR） and back propagation artificial neural network （BP-ANN）, respectively. The root mean square error （RMSE） of the training and validation sets of the BP-ANN model are 0.1363 and 0.0244, the mean absolute percentage errors （MAPE） are 0.1638 and 0.0326, the squared correlation coefficients （R^2） are 0.9853 and 0.9996, respectively. The results show that the BP-ANN model achieved a better prediction result than those of MLR and PCR. In addition, some insights into the structural factors affecting the aerobic biodegradation mechanism were discussed in detail.

Endpoint Prediction of EAF Based on Multiple Support Vector Machines

The endpoint parameters are very important to the process of EAF steel-making, but their on-line measurement is difficult. The soft sensor technology is widely used for the prediction of endpoint parameters. Based on the analysis of the smelting process of EAF and the advantages of support vector machines, a soft sensor model for predicting the endpoint parameters was built using multiple support vector machines （MSVM）. In this model, the input space was divided by subtractive clustering and a sub-model based on LS-SVM was built in each sub-space. To decrease the correlation among the sub-models and to improve the accuracy and robustness of the model, the sub- models were combined by Principal Components Regression. The accuracy of the soft sensor model is perfectly improved. The simulation result demonstrates the practicability and efficiency of the MSVM model for the endpoint prediction of EAF.

Statistical approach to determination of overhaul and maintenance cost of loading equipment in surface mining

The purpose of this research was to develop a new approach in determination of overhaul and maintenance cost of loading equipment in surface mining. Two statistical models including univariate exponential regression (UER) and multivariate linear regression (MLR) were used in this study. Loading equipment parameters such as bucket capacity, machine weight, engine power, boom length, digging depth, and dumping height were considered as variables. The results obtained by models and mean absolute error rate indicate that these models can be applied as the useful tool in determination of overhaul and maintenance cost of loading equipment. The results of this study can be used by the decision-makers for the specific surface mining operations.

Ultrasonic concentration measurement of citrus pectin aqueous solutions using PC and PLS regression

This work demonstrated the use of multivariate statistical techniques called principal component(PC)and partial least squares(PLS)to extract the acoustic features of citrus pectin water solution.The concentration of citrus pectin water solution was predicted by PC and PLS regression method using the spectra of ultrasound pulse echoes travelling through mixtures.The values of root mean square error of validation(RMSEV)were 0.0675 g/100 g and 0.0662 g/100 g for PC and PLS regression model,respectively.Since the response variable was taken into account,PLS regression model was more accurate than PC regression model.Also,a method for temperature compensation was proposed to correct the impact of temperature variation on analyzed data.The proposed methods for pectin concentration measurement are easily adaptable to similar applications using existing hardware.

Incorporation of source contributions to improve the accuracy of soil heavy metal mapping using small sample sizes at a county scale

Estimating heavy metal(HM) distribution with high precision is the key to effectively preventing Chinese medicinal plants from being polluted by the native soil. A total of 44 surface soil samples were gathered to detect the concentrations of eight HMs(As, Hg, Cu, Cr, Ni, Zn, Pb, and Cd) in the herb growing area of Luanping County, northeastern Hebei Province, China. An absolute principal component score-multiple linear regression(APCS-MLR) model was used to quantify pollution source contributions to soil HMs. Furthermore, the source contribution rates and environmental data of each sampling point were simultaneously incorporated into a stepwise linear regression model to identify the crucial indicators for predicting soil HM spatial distributions. Results showed that 88% of Cu, 72% of Cr, and 72% of Ni came from natural sources;50% of Zn, 49% of Pb, and 59% of Cd were mainly caused by agricultural activities;and 44% of As and 56% of Hg originated from industrial activities. When three-type(natural, agricultural, and industrial) source contribution rates and environmental data were simultaneously incorporated into the stepwise linear regression model, the fitting accuracy was significantly improved and the model could explain 31%–86% of the total variance in soil HM concentrations. This study introduced three-type source contributions of each sampling point based on APCS-MLR analysis as new covariates to improve soil HM estimation precision, thus providing a new approach for predicting the spatial distribution of HMs using small sample sizes at the county scale.

Impact of Beijing’s“Coal to Electricity”program on ambient PM_(2.5) and the associated reactive oxygen species(ROS)

The Beijing“Coal to Electricity”program provides a unique opportunity to explore air quality impacts by replacing residential coal burning with electrical appliances.In this study,the atmospheric ROS(Gas-phase ROS and Particle-phase ROS,abbreviated to G-ROS and P-ROS)were measured by an online instrument in parallel with concurrent PM_(2.5) sample collections analyzed for chemical composition and cellular ROS in a baseline year(Coal Use Year-CUY)and the first year following implementation of the“Coal to Electricity”program(Coal Ban Year-CBY).The results showed PM_(2.5) concentrations had no significant difference between the two sampling periods,but the activities of G-ROS,P-ROS,and cellular ROS in CBY were 8.72 nmol H_(2)O_(2)/m^(3),9.82 nmol H 2 O 2/m 3,and 2045.75μg UD/mg PM higher than in CUY.Six sources were identified by factor-analysis from the chemical components of PM_(2.5).Secondary sources(SECs)were the dominant source of PM_(2.5) in the two periods,with 15.90%higher contribution in CBY than in CUY.Industrial Emission&Coal Combustion sources(Ind.&CCs),mainly from regional transport,also increased significantly in CBY.The contributions of Aged Sea Salt&Residential Burning sources to PM_(2.5) decreased 5.31% from CUY to CBY.The correlation results illustrated that Ind.&CCs had significant positive correlations with atmospheric ROS,and SECs significantly associated with cellular ROS,especially nitrates(r=0.626,p=0.000).Therefore,the implementation of the“Coal to Electricity”program reduced PM_(2.5) contributions from coal and biomass combustion,but had little effect on the improvement of atmospheric and cellular ROS.

Understanding spatial patterns in the drivers of greenness trends in the Sahel-Sudano-Guinean region

The region-wide spatial pattern of the drivers of vegetation trends in the African Sahel-Sudano-Guinean region, one of the main drylands of the world, has not been fully investigated. Time-series satellite earth observation datasets were used to investigate spatiotemporal patterns of the vegetation greenness changes in the region and then a principal component regression method was applied to identify the region-wide spatial pattern of driving factors. Results find that vegetation greening is widespread in the region, while vegetation browning is more clustered in central West Africa. The dominant drivers of vegetation greenness have a distinct spatial pattern. Climatic factors are the primary drivers, but the impacts of precipitation decrease from north to south, while the impacts of temperature are contrariwise. Coupled with climatic drivers, land cover changes lead to greening trends in the arid zone, especially in the western Sahelian belt. However, the cluster of browning trends in central West Africa can primarily be attributed to the human-induced land cover changes, including an increasing fractional abundance of agriculture. The results highlight the spatial pattern of climatic and anthropic factors driving vegetation greenness changes, which helps natural resources sustainable use and mitigation of climate change and human activities in global dryland ecosystems.

A Study on Retrieving Atmospheric Profiles from EOS/AIRS Observations

The paper presents the algorithms for retrieving atmospheric temperature andmoisture profiles and surface skin temperature from the high-spectral-resolution AtmosphericInfrared Sounder (AIRS) with a statistical technique based on principal component analysis. Thesynthetic regression coefficients for the statistical retrieval are obtained by using a fastradiative transfer model with atmospheric characteristics taken from a dataset of global radiosondesof atmospheric temperature and moisture profiles. Retrievals are evaluated by comparison withradiosonde observations and European Center of Medium-Range Weather Forecasts (ECMWF) analyses. AIRSretrievals of temperature and moisture are in general agreement with the distributions from ECMWFanalysis fields and radiosonde observations, but AIRS depicts more detailed structure due to itshigh spectral resolution (hence, high vertical spatial resolution).

In Situ Measurement of Ammonia Concentration in Soil Headspace Using Fourier Transform Mid-Infrared Photoacoustic Spectroscopy

Ammonia （NH3） volatilization is one of the important pathways of nitrogen loss in alkaline soil, and the NH3 concentration in soil headspace is directly linked with the NH3 volatilization. Ammonia was characterized by Fourier transform mid-infrared photoacoustic spectroscopy （FTIR-PAS） and two typical absorption bands in the region of 850-1 200 cm-1 were observed, which could be used for the prediction of NH3 concentration in the soil headspaze. An alkaline soil from North China was involved in the soil incubation, pot and field experiments under three fertilization treatments （control without N input （CK）, urea and coated urea）. Ammonia concentrations in the soil headspace were determined in each experiment. In the soil incubation experiment, the NH3 emissions were initiated by the N input, reached the highest concentration on day 2, and decreased to the level as measured in CK after 8 d, with significantly higher NH3 emissions in the urea treatment compared to coated urea treatment, especially during the first 4 d. The NH3 concentration in soil headspace of the pot experiment showed the similar dynamics as that in the incubation experiment; however, the NH3 concentration in the soil headspace in the field experiment demonstrated a significantly different emission pattern with those of the incubation and pot experiments, and there was a 4-d delay for the NH3 concentration. Therefore, the NH3 concentration in the incubation and pot experiments could not be directly used to model the real NH3 emission in the field due to the differences in fertilization method and application rate as well as soil temperature and soil disturbance. It was recommended that light irrigation in the second week after fertilization and involvement of controlled release coated urea could be used to significantly decrease N loss from the perspective of NH3 volatilization. Key Words： ammonia volatilization, cantilevel-type microphone, nitrogen, principal component regression, soil incubation.

Human disturbance, climate and biodiversity determine biological invasion at a regional scale

Many factors may affect biological invasion,but their effects have not been quantitatively calculated.Recent studies on the relationship between biodiversity and biological invasion are still controversial.Native biodiversity and alien species diversity are often positively correlated in large-scale observation studies,but negatively correlated in smallscale experimental studies.By using partial correlation and principal component regression methods,we found that human disturbance,climate,native biodiversity and their interactions explained,respectively,30.3,34.6,26.4 and 4.4%of the variation in alien species diversity(ASD)and 50.3,22.2,10.8 and 5.5%of the variation in the relative invasibility of alien species(RIA=ASD/native biodiversity)at the regional scale in China.The correlation between ASD and native biodiversity is positive,but the correlation between RIA and native biodiversity is negative.Island and coastal provinces have suffered heavier biological invasions than inland provinces.These findings indicate that biological invasion is mostly determined by human disturbance and favorable climate,but less determined by native biodiversity.A disturbance-dependent niche-vacancy hypothesis is proposed to explain the contradictory observations in largeand small-scale studies.

Occurrence of polycyclic aromatic hydrocarbons in the estuarine sediments of the Taihu Lake and their associated toxic effects on aquatic organisms

Polycyclic aromatic hydrocarbons(PAHs)are ubiquitous toxic organic pollutants in the natural environment that are strongly associated with socioeconomic activities.Exploring the distribution,sources,and ecological toxicity of PAHs is essential to abate their pollution and biological risks.The 16 priority PAHs in different lakeside city estuarine sediments in the northern Taihu Lake in China were determined using gas chromatography-mass spectrometry.Results showed that total concentrations of PAHs(ΣPAHs)ranged from 672.07 to 5858.34 ng g^(^(-1)),with a mean value of 2121.37 ng g^(^(-1)).High-molecular-weight PAHs(4-6 rings)were dominant,accounting for 85%of theΣPAHs detected.Due to the barrier of gate/dam in the estuarine area,the concentrations of PAHs in the sediments were significantly different between the river mouth and lake side.Changes in total organic carbon(TOC)content and the spatial distribution of PAHs in the sediments were consistent.Sediment pollution assessment explored using the fuzzy evaluation model indicated 75%of slight PAH pollution.Some estuarine sediments(22%)concentrated in the east of the Wuli Lake in the Meiliang bay of the Taihu Lake were moderately or heavily polluted.The PAHs may lead to occasional detrimental biological consequences in the area.Diagnostic ratios and principal component analysis-multiple linear regression suggested vehicle emission and natural gas combustion as the primary PAH contributors(81%).