Application of swarm intelligence algorithms to the characteristic wavelength selection of soil moisture content

Swarm intelligence algorithms own superior performance in solving high-dimensional and multi-objective optimization problems.The application of the swarm intelligence algorithms to visible and near-infrared(VIS-NIR)spectral analysis of soil moisture can contribute to the optimization of the soil moisture prediction model and the development of the real-time soil moisture sensor.In this study,a high-resolution spectrometer was used to obtain spectral data of different levels of soil moisture which were manually configured.Isolation Forest algorithm(iForest)was used to eliminate outliers from the data.Based on the root mean square error of prediction RMSEP of Back Propagation Neural Network(BPNN)model results,a series of new swarm intelligence algorithms,including Manta Ray Foraging Optimization(MRFO),Slime Mould Algorithm(SMA),etc.,were used to select the characteristic wavelengths of soil moisture.The analysis results showed that MRFO owned the best performance if only from the predictive capability perspective and SMA had a better performance when considering the proportion of the selecting wavelengths and the results of the model prediction.By comparing and analyzing the modeling results of traditional intelligence algorithms Genetic Algorithm(GA)and Particle Swarm Optimization(PSO),it was found that the new swarm intelligence had a better performance in selecting the characteristic wavelengths of soil moisture.Integrating the results of all intelligence algorithms used,soil moisture sensitive wavelengths were selected as 490 nm,513 nm,543 nm,900 nm and 926 nm,which provide the basis for the design of real-time soil moisture sensor based on VIS-NIR.

Evaluation of growth characteristics of Aspergillus parasiticus inoculated in different culture media by shortwave infrared(SWIR) hyperspectral imaging

The growth characteristics of Aspergillus parasitic us incubated on two culture media were ex-amined using shortwave infrared(SWIR,1000-2500 nm)hyperspectral imaging(HSI)in this work.HSI images of the A.parasiticus colonies growing on rose bengal medium(RBM)and maize agar medium(MAM)were recorded daily for 6 days.The growth phases of A.parasiticus were indicated through the pixel number and average spectra of colonies.On score plot of the first principal component(PC1)and PC2,four growth zones with varying mycelium densities were identified.Eight characteristic wavelengths(1095,1145,1195,1279,1442,1655,1834 and 1929 nm)were selected from PC1 loading,average spectra of each colony as well as each growth zone.F urthermore,support vector machine(S VM)classifier based on the eight wavelengths was built,and the classification accuracies for the four zones(from outer to inner zones)on the colonies on RBM were 99.77%,9935%,99.75%and 99.60%and 99.77%,9939%,99.31%and 98.22%for colonies on MAM.In addition,a new score plot of PC2 and PC3 was used to differ-entiate the colonies incubated on RBM and MAM for 6 days.Then characteristic wavelengths of 1067,1195,1279,1369,1459,1694,1834 and 1929 nm were selected from the loading of PC2 and PCg.Based on them,a new SVM model was developed to diferentiate colonies on RBM and MAM with accuracy of 100.00%and 9999%,respectively.In conclusion,SWIR hyperspectral image is a powerful tool for evaluation of growth characteristics of A.parasiticus incubated in diferent culture media.

Rapid Determination of Hemicellulose Content in Corn Stalks by Near-infrared Spectroscopy Based on Dung Beetle Optimizer

Corn stalks are a kind of common organic fertilizer and feed material in agriculture in China,as well as an important source of modern biomass energy and new materials.Hemicellulose is an important component in corn stalks,and it is very important to determine its content in corn stalks.In this paper,the feasibility of near-infrared spectroscopy(NIRS)combined with chemometrics for rapid detection of hemicellulose content in corn stalks was studied.In order to improve the accuracy of NIRS detection,a new intelligent optimization algorithm,dung beetle optimizer(DBO),was applied to select characteristic wavelengths of NIRS.Its modeling performance was compared with that based on characteristic wavelength selection using genetic algorithm(GA)and binary particle swarm optimization(BPSO),and it was found that the characteristic wavelength selection performance of DBO was excellent,and the regression accuracy of hemicellulose quantitative detection model established by its preferred characteristic wavelengths was better than the above two intelligent optimization algorithms.

Comparison of algorithms for monitoring wheat powdery mildew using multi-angular remote sensing data

Powdery mildew is a disease that threatens wheat production and causes severe economic losses worldwide. Its timely diagnosis is imperative for preventing and controlling its spread. In this study, the multiangle canopy spectra and disease severity of wheat were investigated at several developmental stages and degrees of disease severity. Four wavelength variable-selected algorithms: successive projection(SPA), competitive adaptive reweighted sampling(CARS), feature selection learning(Relief-F), and genetic algorithm(GA), were used to identify bands sensitive to powdery mildew. The wavelength variables selected were used as input variables for partial least squares(PLS), extreme learning machine(ELM), random forest(RF), and support vector machine(SVM) algorithms, to construct a suitable prediction model for powdery mildew. Spectral reflectance and conventional vegetation indices(VIs) displayed angle effects under several disease severity indices(DIs). The CARS method selected relatively few wavelength variables and showed a relatively homogeneous distribution across the 13 viewing zenith angles.Overall accuracies of the four modeling algorithms were ranked as follows: ELM(0.70–0.82) > PLS(0.63–0.79) > SVM(0.49–0.69) > RF(0.43–0.69). Combinations of features and algorithms generated varied accuracies, with coefficients of determination(R^(2)) single-peaked at different observation angles. The constructed CARS-ELM model extracted a predictable bivariate relationship between the multi-angle canopy spectrum and disease severity, yielding an R^(2)> 0.8 at each measured angle. Especially for larger angles,monitoring accuracies were increased relative to the optimal VI model(40% at-60°, 33% at +60°), indicating that the CARS-ELM model is suitable for extreme angles of-60° and +60°. The results are proposed to provide a technical basis for rapid and large-scale monitoring of wheat powdery mildew.

Non-destructive measurement of chlorophyll in tomato leaves using spectral transmittance

In this study,spectral transmittances were measured in the wavelength range from 300 nm to 1100 nm of tomato leaves with different chlorophyll contents and compositions,and the correlations between the spectral transmittances and the contents of chlorophyll a,chlorophyll b and total chlorophyll were analyzed.With the characteristic wavelengths of 560 nm,650 nm,720 nm and the reference wavelength of 940 nm,nine sets of characteristic spectral parameters were obtained.According to the results of correlation analysis and regression model exploration,characteristic spectral parameters of T940/T560,T940/T650 and log(T940/T560)among the nine sets of parameters were highly correlated to the estimated contents of chlorophyll a,chlorophyll b and total chlorophyll of tomato leaves.The relative errors of total chlorophyll and chlorophyll a/b ratio were(5.1±3.7)%and(4.9±4.3)%,respectively.Therefore,the above three characteristic spectral parameters could be applied in the rapid non-destructive estimation of the contents of chlorophyll a,chlorophyll b and total chlorophyll as well as chlorophyll a/b ratio of tomato leaves.