Search

As an important waveform feature, the number of peaks indicates the complexity of the surface coverage within the laser footprint. At present, the common methods of determining the number of peaks are based on waveform decomposition because the full waveform can be regarded as the superposition of multiple Gaussian waves. However, the empirical thresholds can affect the performance of the algorithms, and the process is time-consuming and inefficient. This study attempts to develop an automatic peak-number-driven classifier and picker based on machine learning (ML) and convolutional neural network (CNN) models. Waveforms were divided into four categories according to the peak-number. The results of five classifiers show good agreement with the verification data from GLAH14, with overall accuracies of 90.65%, 92.69%, 92.45%, 91.95%, and 93.05%. Moreover, F1 score was calculated to evaluate the classification performance of each classifier for different categories. The results indicate that each classifier accurately distinguishes waveforms with different numbers of crests, especially invalid and single-peak waveforms. The ability to quickly and automatically extract the number of peaks based on ML methods will be of great benefit for specific research to screen suitable experimental data [ABSTRACT FROM AUTHOR]

The shore zone is the most active zone in the atmosphere, hydrosphere, biosphere and lithosphere of nature, and has the environmental characteristics of both ocean and land. The ICESat-2 satellite provides height measurements of shore zone using a photon-counting LiDAR. The purpose of this study is to explore the application potential of ICESat-2 satellite data in shore zone classification. Saint Lawrence Island, Alaska, was chosen as the study area. Firstly, in this study, the upper and lower boundaries of the shore zone of the study area were extracted based on Google Earth images. The slope and width between the two boundaries were then calculated according to the formula. Secondly, six statistical indicators (standard deviation, relative standard deviation, average absolute deviation, relative average deviation, absolute median error and quartile deviation) related to the substrate and sediment classification that could reflect the characteristics of the shore zone profile were extracted, and the statistical indicators were used as input parameters of the softmax regression model for classification. Finally, the accuracy of the shore zone classification was validated using the ShoreZone classification system. The results show that, among the 246 shore zone sections in the study area, 86% (212) has been correctly classified. The results therefore indicate that ICESat-2 data can be used to support the characterization of shore zone morphology. [ABSTRACT FROM AUTHOR]

The ultrastructure of the egg chorion surface in the loachMisgurnus anguillicaudatuswas investigated using scanning electron microscopy (SEM). A single micropyle, which belonged to type II, was found at the animal pole of anM. anguillicaudatusegg. Several sinistral grooves which originated at the micropyle probably served for sperm guidance. The egg envelope had numerous pores with bud-like fillings and a regular arrangement like honeycomb. Lots of small knobs were situated on the zona radiata at the vegetal pole. Water contact triggered egg stickiness within about 10 seconds. The egg surface became smooth after treatment with trypsin solution. The features of the micropyle, pores and stickiness were correlated with the reproductive strategy of the loach and are important for egg identification. [ABSTRACT FROM AUTHOR]