Landslide Detection of Hyperspectral Remote Sensing Data Based on Deep Learning With Constrains

<p>There is a growing demand for constructing a complete and accurate landslide maps and inventories in a wide range, which leading explosive growth in extraction algorithm study based on remote sensing images. To the best of our knowledge, no study focused on deep learning-based methods for landslide detection on hyperspectral images.We proposes a deep learning frameworkwith constraints to detect landslides on hyperspectral image. The framework consists of two steps. First, a deep belief network is employed to extract the spectral–spatial features of a landslide. Second, we insert the high-level features and constraints into a logistic regression classifier for verifying the landslide. Experimental results demonstrated that the framework can achieve higher overall accuracy when compared to traditional hyperspectral image classification methods. The precision of the landslide detection on the whole image, obtained by the proposed method, can reach 97.91%, whereas the precision of the linear support vector machine, spectral information divergence, and spectral angle match are 94.36%, 84.50%, and 86.44%, respectively. Also, this article reveals that the high-level feature extraction system has a significant potential for landslide detection, especially in multi-source remote sensing.</p>

Comment on “Size dependence of bubble wetting on surfaces: breakdown of contact angle match between small sized bubbles and droplets” by H. Zhang and X. Zhang, Nanoscale, 2019, 11, 2823

The theoretical arguments of the paper commented contain errors and cannot explain the simulation results. We suggest that line tension and adsorptions at interfaces may be responsible for a difference in the contact angle size dependencies for droplets and bubbles.

Reply to the ‘Comment on “Size dependence of bubble wetting on surfaces: breakdown of contact angle match between small sized bubbles and droplets”’ by A. I. Rusanov, D. V. Tatyanenko and A. K. Shchekin, Nanoscale, 2020, DOI:10.1039/D0NR00232A

In this Reply, we clarify the rationale behind our conclusions and point out that in their derivation Rusanov et al. failed to consider the difference between bubbles and droplets.

A SPECTRALLY IMPROVED POINT CLOUD CLASSIFICATION METHOD FOR MULTISPECTRAL LIDAR

Precise point cloud classification can enhance lidar performance in various applications, such as land cover mapping, forestry management and autonomous driving. The development of multispectral lidar improves classification performance with rich spectral information. However, the employment of spectral information for classification is still underdeveloped. Therefore, we proposed a spectrally improved classification method for multispectral LiDAR. We conducted spectral improvement in two aspects: (1) we improved the eigenentropy-based neighbourhood selection by spectral angle match (SAM) to reform the more reliable neighbour; (2) we utilized both geometric and spectral features and compare the contributions of these features. A three-wavelength multispectral lidar and a complex indoor experimental scene were used for demonstration. The results indicate the effectiveness of our proposed spectrally improved method and the promising potential of spectral information on lidar classification.

Size dependence of bubble wetting on surfaces: breakdown of contact angle match between small sized bubbles and droplets

Bubbles show size-dependent wetting behaviors and contact angles for small bubbles are no longer supplementary to those of droplets.

A Combined Solar Disc Power Generation and Desalination System

A system is designed to combine the solar disc power generation and desalination in this paper. The steam generated in the solar disc system goes into the low-parameter steam turbine to produce electricity. Then the exhaust steam heats seawater in the desalination device, acting as a low temperature heat reservoir which makes the seawater boils to dilute. A tracking system adopting the "Date-time - latitude-longitude - sunlight incident angle" match pattern is designed to track the position of the sun, in order to achieve the maximum solar power input.