Search

Your search keyword '"Zhou, Fengnian"' showing total 26 results
Start Over Author "Zhou, Fengnian"
26 results on '"Zhou, Fengnian"'

3. NWSP: A Novel Indicator for Ocean–Land Interface Extraction Using Bathymetric LiDAR

Author

Zhao, Xinglei, Xia, Hui, and Zhou, Fengnian

Abstract

Because of water-surface uncertainty, green lasers used in airborne bathymetric LiDAR cannot accurately detect the water surface, as they reflect near-water surface penetration (NWSP) into the water column. The existence of the NWSP of a green laser in water is not beneficial for high-accuracy depth measurements; however, it can be useful for ocean–land interface (OLI) extraction. In this study, novel ocean–land discrimination and interface extraction methods based on the NWSPs of green lasers are proposed. First, the NWSPs of different green laser channels are calculated and averaged to obtain a robust NWSP for each laser footprint. Second, a novel NWSP-based ocean–land discriminator is proposed based on the different characteristics of the NWSPs in land and ocean areas. Third, density-based spatial clustering of applications with noise algorithm is used to identify and correct the misclassified points of the NWSP-based ocean–land discriminator, and the OLIs are formed by connecting the land boundary points. Finally, the novel NWSP method is verified using a raw ABL data set collected via Optech coastal zone mapping and imaging LiDAR. The OLIs derived by waveform clustering are used as reference to evaluate the performance of the proposed NWSP method. OLI extraction based on the proposed NWSP method and the traditional point elevation method can reach accuracies of 1.9 and 4.8 m, respectively, in the research area. The proposed NWSP method provides a novel and convenient means for OLI extraction using the NWSPs of green lasers.

Published
2024
Full Text
View/download PDF

5. Deep Learning-Based Simulation of Surface Suspended Sediment Concentration in the Yangtze Estuary during Typhoon In-Fa.

Author

Ren, Zhongda, Liu, Chuanjie, Ou, Yafei, Zhang, Peng, Fan, Heshan, Zhao, Xiaolong, Cheng, Heqin, Teng, Lizhi, Tang, Ming, and Zhou, Fengnian

Subjects
TYPHOONS, SUSPENDED sediments, TERRITORIAL waters, ESTUARIES, PRINCIPAL components analysis, HYDROLOGICAL stations, DEEP learning
Abstract

Effectively simulating the variation in suspended sediment concentration (SSC) in estuaries during typhoons is significant for the water quality and ecological conditions of estuarine shoal wetlands and their adjacent coastal waters. During typhoons, SSC undergoes large variations due to the significant changes in meteorological and hydrological factors such as waves, wind speed, and precipitation, which increases the difficulty in simulating SSC. Therefore, in this study, we use an optimized Principal Component Analysis Long Short-Term Memory (PCA-LSTM) framework with an attention mechanism to simulate the SSC in the Yangtze Estuary during Typhoon In-Fa. First, we integrate data from different sources into a multi-source dataset. Second, we use the PCA to reduce the dimensionality of the multi-source data and eliminate redundant variables in the feature data. Third, we introduce an attention mechanism to optimize the long and short-term memory (LSTM) model. Finally, we use the differential evolution (DE) algorithm for hyperparameter selection and merge the feature data with the SSC data as the input of the optimized LSTM network to simulate SSC. The results showed that SSC's fitting coefficients (R2) at four hydrological stations improved by 7.5%, 6.1%, 7.4%, and 7.8%, respectively, using the attention-based PCA-LSTM compared to the PCA-LSTM. Moreover, compared to the traditional LSTM model, the R2 was improved by 33.8%, 30.5%, 32.0%, and 28.6%, respectively, using the attention-based PCA-LSTM framework. The study indicates that the selection of input variables can affect the model results. Introducing an attention mechanism can effectively optimize the PCA-LSTM framework and improve the simulation accuracy, which helps simulate the non-linear process of SSC variation occurring during Typhoon In-Fa. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

11. Overall calibration method of multibeam echo sounder installation biases based on terrain feature matching

Author

LI Tie, ZHOU Fengnian, and ZHAO Jianhu

Subjects
overall calibration of biases, MBES installation biases, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, SIFT match, matching point pairs, lcsh:Mathematical geography. Cartography, lcsh:GA1-1776
Abstract

The patch test method based on decoupling principle to determine MBES (multibeam echo sounders)installation biases often results in complex operation and low accuracy due to theoretical imperfections. Therefore, the overall calibration of the biases is proposed. Firstly, MBES sounding terrain is converted into grayscale image. Then, SIFT(scale-invariant feature transform) is used for matching related terrain images and founding matching point pairs. Finally, the inequality-constrained least square adjustment is used for obtaining the MBES installation biases by the matching point pairs coordinates. The experiment verifies the validation of this method in simplifying the implementation and improving the accuracy of determining these biases.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results