Chengming Ye

Chengdu University of Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Jonathan Li

University of Waterloo

Yao Li

Tianjin University

Ruilong Wei

University of Chinese Academy of Sciences

Yonggang Ge

Institute of Mountain Hazards and Environment

José Marcato

Universidade Federal de Mato Grosso do Sul

Tianbo Sui

Chengdu University of Technology

Hongfu Li

Chengdu University of Technology

Peng Cui

Institute of Mountain Hazards and Environment

Rong Tang

China Institute of Water Resources and Hydropower Research

Saied Pirasteh

Saveetha University

Cooperative Institutions

Chengdu University of Technology

Chinese Academy of Sciences

University of Chinese Academy of Sciences

Institute of Mountain Hazards and Environment

China Geological Survey

University of Electronic Science and Technology of China

University of Waterloo

Ministry of Education of the People's Republic of China

China University of Geosciences

Tsinghua University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Accurate Prediction of Earthquake-Induced Landslides Based on Deep Learning Considering Landslide Source Area

Remote Sensing (2021)

Yao Li Peng Cui Chengming Ye José Marcato Zhengtao Zhang

An earthquake-induced landslide (EQIL) is a rapidly changing process occurring at the Earth’s surface that is strongly controlled by the earthquake in question and predisposing conditions. Predicting locations prone to EQILs on a large scale is significant for managing rescue operations and disaster mitigation. We propose a deep learning framework while considering the source area feature of EQIL to model the complex relationship and enhance spatial prediction accuracy. Initially, we used high-resolution remote sensing images and a digital elevation model (DEM) to extract the source area of an EQIL. Then, 14 controlling factors were input to a stacked autoencoder (SAE) to search for robust features by sparse optimization, and the classifier took advantage of high-level abstract features to identify the EQIL spatially. Finally, the EQIL inventory collected from the Wenchuan earthquake was used to validate the proposed model. The results show that the proposed method significantly outperformed conventional methods, achieving an overall accuracy (OA) of 91.88%, while logistic regression (LR), support vector machine (SVM), and random forest (RF) achieved 80.75%, 82.22%, and 84.16%, respectively. Meanwhile, this study reveals that shallow machine learning models only take advantage of significant factors for EQIL prediction, but deep learning models can extract more effective information related to EQIL distribution from low-value density data, which is why its prediction accuracy is growing with increasing input factors. There is hope that new knowledge of EQILs can be represented by high-level abstract features extracted by hidden layers of the deep learning model, which are typically acquired by statistical methods.

Autoencoder

Deep belief network

10.3390/rs13173436

Cite

Citations (30)

An attention-constrained neural network with overall cognition for landslide spatial prediction

Landslides (2022)

Ruilong Wei Chengming Ye Yonggang Ge Yao Li

10.1007/s10346-021-01841-z

Cite

Citations (13)

Two stages power generation test of the hot dry rock exploration and production demonstration project in the Gonghe Basin, northeastern Qinghai-Tibet plateau, China

China Geology (2024)

Eryong Zhang Dong-guang Wen Guiling Wang Xian-peng Jin Lin-you Zhang

Sichuan basin

Inner mongolia

10.31035/cg2024082

Cite

Citations (1)

Dynamic graph attention networks for point cloud landslide segmentation

International Journal of Applied Earth Observation and Geoinformation (2023)

Ruilong Wei Chengming Ye Yonggang Ge Yao Li Jonathan Li

Accurate landslide segmentation is crucial for obtaining damage information in disaster mitigation and relief efforts. This study aims to develop a deep learning network for accurate point cloud landslide segmentation. The proposed dynamic graph attention network (DGA-Net) has four steps. First, the down-sampling and neighbor search are applied to generate the samples that effectively represent the relevant landslide information. Second, the edge features of neighbor points are constructed based on graph structure to extract and enhance point cloud features. Third, the attention mechanism assigns adaptive weights to edge features and aggregates them into new point features. Fourth, the graph structure, edge features, and attention weights are dynamically updated through the hierarchical structures, which enable an expanded receptive field. In the upper reach of the Jinsha River, point clouds were prepared for landslide segmentation. The controlled experiments were designed for effectiveness evaluation. The results reported that proposed DGA-Net achieved the highest mean Intersection over Union (mIoU) of 0.743 and F1-score of 0.786, which was over 6.7% and 3.6% mIoU higher than shallow machine learning and other deep learning models. Besides, we analyzed the effect of super parameters in sampling strategy and the segmentation threshold in prediction stage on the model performance. The results showed that the samples with suitable sampling diameters and appropriate neighboring points are beneficial for landslide segmentation, and using optimal thresholds to segment stacked multiple prediction values can improve mIoU by 6%. Furthermore, the visualized feature maps revealed that the proposed model can index landslide points in feature space, which is beneficial to construct graph structures and use attention to enhance features. Comparative studies on the above experiments proved the superiority of the proposed method for landslide segmentation. We hope that our method and research results can contribute to post-disaster relief efforts.

Feature (linguistics)

10.1016/j.jag.2023.103542

Cite

Citations (3)

Combining spatial response features and machine learning classifiers for landslide susceptibility mapping

International Journal of Applied Earth Observation and Geoinformation (2022)

Ruilong Wei Chengming Ye Tianbo Sui Yonggang Ge Yao Li

Reliable landslide susceptibility mapping (LSM) is essential for disaster prevention and mitigation. This study develops a deep learning framework that integrates spatial response features and machine learning classifiers (SR-ML). The method has three steps. First, depthwise separable convolution (DSC) extracts spatial features to prevent confusion of multi-factor features. Second, spatial pyramid pooling (SPP) extracts response features to obtain features under different scales. Third, the high-level features are fused into prepared ML classifiers for more effective feature classification. This framework effectively extracts and uses different-dimension features of samples, explores ML classifiers for beneficial feature classification, and breaks through the limitation of fixed input sample sizes. In the Yarlung Zangbo Grand Canyon region, data on 203 landslides and 11 conditioning factors were prepared for availability verification and LSM. The evaluation indicated that the area under the receiver operating characteristic curve (AUC) for the proposed SR and SR-ML achieved 0.920 and 0.910, which were 6.6% and 5.6% higher than the random forest (RF, with the highest AUC in ML group) method, respectively. Furthermore, the framework using 64×64 size inputs had the lowest mean error of 0.01, revealing that samples considering landslide scales could improve performance for LSM.

Pooling

Feature (linguistics)

Pyramid (geometry)

10.1016/j.jag.2022.102681

Cite

Citations (52)

A Building Roof Identification CNN Based on Interior-Edge-Adjacency Features Using Hyperspectral Imagery

Remote Sensing (2021)

Chengming Ye Hongfu Li Chunming Li Xin Liu Yao Li

Hyperspectral remote sensing can obtain both spatial and spectral information of ground objects. It is an important prerequisite for a hyperspectral remote sensing application to make good use of spectral and image features. Therefore, we improved the Convolutional Neural Network (CNN) model by extracting interior-edge-adjacency features of building roof and proposed a new CNN model with a flexible structure: Building Roof Identification CNN (BRI-CNN). Our experimental results demonstrated that the BRI-CNN can not only extract interior-edge-adjacency features of building roof, but also change the weight of these different features during the training process, according to selected samples. Our approach was tested using the Indian Pines (IP) data set and our comparative study indicates that the BRI-CNN model achieves at least 0.2% higher overall accuracy than that of the capsule network model, and more than 2% than that of CNN models.

Adjacency list

Identification

10.3390/rs13152927

Cite

Citations (3)

Spatio-temporal change monitoring for surface water on the Qinghai-Tibet Plateau from 1990 to 2020 using remote sensing

Frontiers in Earth Science (2023)

Tianbo Sui Chengming Ye Rong Tang Ruilong Wei

Detecting and analyzing changes of water resources is critical for human survival and societal development in the Qinghai Tibet Plateau (QTP). We implemented the cosine similarity method to complete the migration of samples and achieve a more accurate random forest classifier (mean Kappa = 0.872) for each period. Based on these classifiers and 45,370 Landsat images, we estimated the surface water distribution of the QTP for six periods between 1990 and 2020 based on the Google Earth Engine platform. The results indicate that the QTP has a surface water area of 57,229 ± 3,248 km 2 (1990–1995), 58,444 ± 3,248 km 2 (1996–2000), 67,319 ± 3,704 km 2 (2001–2005), 67,399 ± 2,798 km 2 (2006–2010), 70,286 ± 3,033 km 2 (2011–2015), 75,176 ± 2,785 km 2 (2016–2020), that the area of water rose by ap-proximately 31.3% and continued to increase. The area of permanent water remained constant between 1990 and 2020 at 47,280 km 2 . On the QTP, the change in water area can be split into four regions: rapid increase (Qiangtang Plateau), slow increase (eastern basins), decrease (northern and northeastern basins), and relatively stable (southern basins). About 186,408 km 2 area of land is significantly losing water bodies, while about 589,567 km 2 area of land is significantly gaining water bodies. This study provides higher accuracy temporal distribution data of water bodies in the Qinghai-Tibet Plateau, and quantitatively evaluates the area changes of water bodies from multiple spatial scales. Research provides an important scientific reference for hydrological research and effective management of water resources in important rivers in the QTP.

10.3389/feart.2023.1124425

Cite

Citations (0)

Source Model for the 2022 Qinghai Menyuan Ms 6.9 Earthquake Based on D-InSAR

Frontiers in Earth Science (2022)

Jiangtao Liao Chuntao Liang Chaoliang Wang Feihuang Cao Chengming Ye

On 8 January 2022, an Ms 6.9 earthquake occurred in Menyuan County, Qinghai Province, China. This earthquake ruptured a patch of the Qilian-Haiyuan fault in the northeast margin of the Qinghai-Tibet Plateau. In order to understand the seismogenic structure of this earthquake and analyze the fault activity, we use differential synthetic aperture radar interferometry (D-InSAR) technology to obtain a complete co-seismic displacement field on the surface, and use pixel tracking algorithm to extract the trace of the ruptured fault. The slip distribution of the seismogenic fault was inverted using the steepest descent method, and the Coulomb stress change caused by the earthquake was also calculated. Surface deformation results show that the Menyuan earthquake produced obvious surface displacements in an area of 50 × 40 km 2 . The displacements are mainly distributed in the western segment of the Lenglongling fault and the eastern segment of the Tolaishan fault. The maximum displacements in the ascending and descending orbits in the LOS direction are 59.7 and 94.7 cm, respectively. The co-seismic slip results show that the strike, dip and average slip angles of the seismogenic fault are 108°, 79° dipping to SW, and 4°, respectively. On the whole, the fault is mainly of left-lateral, with a small amount of thrust component and only one co-seismic rupture center in our inversion result. The rupture center is located at a depth of ∼5 km below the surface, and the maximum slip is 3.1 m. The total seismic moment released by this earthquake is 1.28 × 10 19 N·m, and the corresponding moment magnitude is 6.67. Finally, the static Coulomb stress change results show that parts of the Lenglongling fault, the Tolaishan fault, the Sunan-Qilian fault and the Minyue-Damaging fault are loaded, emphasizing the importance for earthquake risk assessment of these fault.

Thrust fault

Seismic moment

10.3389/feart.2022.948661

Cite

Citations (8)

ATMOSPHERIC CORRECTION OF HYPERSPECTRAL REMOTE SENSING IMAGE BASED ON FLAASH

Computing Techniques for Geophysical and Geochemical Exploration (2010)

Chengming Ye

The electromagnetic wave received by the sensor have the atmospheric absorption and scattering effect on image.Hyperspectral remote sensing images contain high resolution spectral informations.In order to extract hyperspectral remote sensing information more accurately,the atmospheric correction is essential.In the application of data from Hyperion with a lower SNR,it is important to correct the atmospheric effect on surface reflectance computation.This paper uses FLAASH to make the Atmospheric Correction of Hyperion images,analyzed the different spectral features before or after correction,compared with the standard database and get a desirable result of the case study.

Atmospheric correction

Full spectral imaging

Spectral resolution

Source

Cite

Citations (2)

Analysis of ecosystem resilience in Jiuzhaigou Valley Scenic Area under the effect of geohazards

Frontiers in Earth Science (2023)

Haixia Sui Chang Liu Chengming Ye Xu Xiaolong Tianbo Sui

The effects of geohazards on the ecological environment and ecological spatial pattern have received wide attention from scholars. However, the positive role played by ecological restoration projects on the environment and in the reduction of geohazards has usually been neglected. Jiuzhaigou Valley Scenic Area is a world natural heritage area, has a high incidence of geohazards, and is a demonstration area for ecological restoration projects. Based on remote sensing technology, this paper adopted an InVEST model (Integrated Valuation of Ecosystem Services and Tradeoffs) and ecological landscape index to extract information about spatio-temporal changes in Jiuzhaigou from 2013 to 2020. This study utilized a quantitative analysis of the ecological recoverability of Jiuzhaigou in cases of artificial restoration and spontaneous restoration under different types of geohazards. Results showed that forests play a vital role in maintaining and controlling habitat quality; artificial restoration can significantly ameliorate the impact of geohazards on the scenic area. As of 2020, the forested scenic area recovered 3.868 km2 , and the habitat quality index rebounded to 98.88% of the historical high. The ecological restoration project significantly shortened the scenic area recover time of its ecosystem service capability.

Restoration Ecology

Resilience

10.3389/feart.2022.1053327

Cite

Citations (3)