Wavelength selection of terahertz time-domain spectroscopy based on a partial least squares model for quantitative analysis

A multicomponent gas wavelength selection method based on an absorbance mathematical model

In order to quickly and accurately determine the optimal absorption spectra of the gases to be measured, a method for selecting the optimal wavelengths for multicomponent gases was proposed. A mathematical model of the absorbance of multicomponent gases was established, and the selection conditions of the optimal wavelengths were analyzed from the perspective of geometric significance. The best measurement spectra for the gas mixture of CO₂, CH_4, and C₂H₂ were determined and the gas mixture was measured using the supercontinuum laser absorption spectroscopy (SCLAS) technique, and the partial least squares (PLS) model and the least squares (LS) model were established to quantify the experimental results. The results showed that the PLS model had better prediction performance. The root mean square error (RMSE) of the calibration set PLS model for CO₂ and CH₄ was 0.1652 and 0.0053, the RMSE of the prediction set PLS model was 0.1991 and 0.0163, and the determination coefficient (R²) of the models was above 0.9. The experimental results show that the optimal wavelength selection method for multicomponent gases proposed in this study can effectively determine the optimal measurement spectral lines for the gases to be measured.

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework

Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determination R 2 was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.