Estimation of spectral responses and chlorophyll based on growth stage effects explored by machine learning methods

Estimation of leaf chlorophyll content(LCC) by proximal sensing is an important tool for photosynthesis evaluation in high-throughput phenotyping. The temporal variability of crop biochemical properties and canopy structure across different growth stages has great impacts on wheat LCC estimation, known as growth stage effects. It will result in the heterogeneity of crop canopy at different growth stages, which would mask subtle spectral response of biochemistry variations. This study aims to explore spectral responses on the growth stage effects and establish LCC models suited for different growth stages. A total number of 864 pairwise samples of wheat canopy spectra and LCC values with 216 observations of each stage were sampled at the tillering, jointing, booting and heading stages in 2021. Firstly, statistical analysis of LCC and spectral response presented different distribution traits and typical spectral variations peak at 470, 520 and 680 nm. Correlation analysis between LCC and reflectance showed typical red edge shifts. Secondly, the testing model of partial least square(PLS) established by the entire datasets to validate the predictive performance at each stage yielded poor LCC estimation accuracy. The spectral wavelengths of red edge(RE) and blue edge(BE) shifts and the poor estimation capability motivated us to further explore the growth stage effects by establishing LCC models at respective growth periods.Finally, competitive adaptive reweighted sampling PLS(CARS-PLS), decision tree(DT) and random forest(RF) were used to select sensitive bands and establish LCC models at specific stages. Bayes optimisation was used to tune the hyperparameters of DT and RF regression. The modelling results indicated that CARS-PLS and DT did not extract specific wavelengths that could decrease the influences of growth stage effects. From the RF out-of-bag(OOB) evaluation, the sensitive wavelengths displayed consistent spectral shifts from BE to GP and from RE to RV from tillering to heading stages. Compared with CARS-PLS and DT,results of RF modelling yielded an estimation accuracy with deviation to performance(RPD) of 2.11, 2.02,3.21 and 3.02, which can accommodate the growth stage effects. Thus, this study explores spectral response on growth stage effects and provides models for chlorophyll content estimation to satisfy the requirement of high-throughput phenotyping.

Subway Embedded Track Geometric Irregularity Safety Limits

A coupling dynamic model of a subway train and an embedded track is established to study the safety limits of track irregularities.The simulated vehicle system was a 74-degrees of freedom multi-rigid body model,and the rail was a Timoshenko beam.The slab was a three-dimensional solid finite element model.The sensitive wavelength irregularity was first studied,and then the safety limit of the sensitive wavelength was analyzed.The wheel-rail lateral force exhibited a substantial effect on the track alignment and gauge irregularity safety limit.The wheel-rail vertical force and the rate of wheel load reduction significantly affected the height and cross-level irregularity safety limit.The results demonstrate that the safety limits of the alignment,gauge,height,and cross-level embedded track geometric irregularity are 5.3 mm,[−10.5,8]mm,5.6 mm,and 6 mm,respectively.

Optimal design for elliptical holey fiber with stable polarization beat-length

In order to design birefringent holey fiber with beat-length independent of wavelength, an asymmetric structure is introduced to reduce its wavelength-sensitivity. The influence of structural parameters on the modal birefringence is calculated and analyzed. After optimizing the parameters, a flat dispersion curve of beat-length is obtained. The beat-length changes from 89.8 mm to 91.0 mm in wavelength range from 1.1 μm, to 1.7μm, and its relative variation is 1.38%. If this fiber is made into zero-order quarter wave plate, the phase delay can be easily controlled in （90±1）°.

Wheel/rail dynamic interaction due to excitation of rail corrugation in high-speed railway

Characteristics of wheel-rail dynamic interaction due to the rail corrugation in a high-speed railway are analyzed based on the theory of vehicle-track coupled dynamics in this paper.Influences of the corrugation wavelength and depth on the wheel-rail dynamic performance are investigated.The results show that,under the excitation of a measured rail corrugation,the wheel-rail dynamic interaction of high-speed railway is enhanced obviously,and the high-frequency dynamic force between wheel and rail is generated,which has an obvious impact on the vibrations of the wheelset and rail,and little effect on the vibration of the frame and carbody.If the corrugation wavelength is shorter than the sensitive wavelength,the wheel-rail vertical force will increase with the growth of the corrugation wavelength,otherwise,it will decrease.However,the wheel-rail vertical force keeps increasing with the growth of corrugation depth.Furthermore,if the corrugation wavelength is shorter than the sensitive wavelength,the wheel-rail vertical force will increase with the decrease of the running speed,otherwise,it will decrease.It is also found that the critical wavelength of corrugation increases with the growth of the corrugation depth and the running speed,and the critical depth of corrugation is nonlinearly related to the sensitive wavelength.

Spectroscopy-Based Soil Organic Matter Estimation in Brown Forest Soil Areas of the Shandong Peninsula, China

Soil organic matter (SOM) is important for plant growth and production. Conventional analyses of SOM are expensive and time consuming. Hyperspectral remote sensing is an alternative approach for SOM estimation. In this study, the diffuse reflectance spectra of soil samples from Qixia City, the Shandong Peninsula, China, were measured with an ASD FieldSpec 3 portable object spectrometer (Analytical Spectral Devices Inc., Boulder, USA). Raw spectral reflectance data were transformed using four methods: nine points weighted moving average (NWMA), NWMA with first derivative (NWMA + FD), NWMA with standard normal variate (NWMA + SNV), and NWMA with min-max standardization (NWMA + MS). These data were analyzed and correlated with SOM content. The evaluation model was established using support vector machine regression (SVM) with sensitive wavelengths. The results showed that NWMA + FD was the best of the four pretreatment methods. The sensitive wavelengths based on NWMA + FD were 917, 991, 1 007, 1 996, and 2 267 nm. The SVM model established with the above-mentioned five sensitive wavelengths was significant ( R 2 = 0.875, root mean square error (RMSE) = 0.107 g kg −1 for calibration set;R 2 = 0.853, RMSE = 0.097 g kg −1 for validation set). The results indicate that hyperspectral remote sensing can quickly and accurately predict SOM content in the brown forest soil areas of the Shandong Peninsula. This is a novel approach for rapid monitoring and accurate diagnosis of brown forest soil nutrients.

Sensitivity of on-line wavelength during retrieval of atmospheric CO2 vertical profile

Accurately measuring the differential molecular absorption cross section is the key to obtaining a high-precision concentration of atmospheric trace gases in a differential absorption lidar（DIAL） system. However, the CO2 absorption line is meticulous at 1.6 μm, easily translating and broadening because of the change of temperature and pressure. Hence, measuring the vertical profile of atmospheric temperature and pressure to calculate the vertical profile of the CO2 weight parameter is necessary. In general, measuring atmospheric temperature and pressure has a certain amount of uncertainty. Therefore, this study proposes the concept of a balanced on-line wavelength,where the differential molecular absorption cross section is larger and the CO2 weight parameter is insensitive to the uncertainty of atmospheric temperature and pressure. In this study, we analyzed the influence of uncertainty on the CO2 weight parameter at every preselected wavelength, as well as determined an appropriate wavelength near one of the absorption peaks. Our result shows that 1572.023 nm should be one of the appropriate balanced online wavelengths. The measurement errors of the mixing ratio of CO2 molecule in this wavelength are only 0.23%and 0.25% and are caused by 1 K temperature error and 1h Pa pressure error, respectively. This achievement of a balanced on-line wavelength will not only depress the requirement of the laser’s frequency stabilization but also the demand for measurement precision of the atmospheric temperature and pressure profile. Furthermore, this study can achieve the exact measurement of the vertical profile of atmospheric CO2 based on an independent differential absorption laser.