Landslide susceptibility mapping (LSM) is a useful tool to estimate the probability of landslide occurrence, providing a scientific basis for natural hazards prevention, land use planning, and economic development in landslide-prone areas. To date, a large number of machine learning methods have been applied to LSM, and recently the advanced convolutional neural network (CNN) has been gradually adopted to enhance the prediction accuracy of LSM. The objective of this study is to introduce a CNN-based model in LSM and systematically compare its overall performance with the conventional machine learning models of random forest, logistic regression, and support vector machine. Herein, we selected Zhangzha Town in Sichuan Province, China, and Lantau Island in Hong Kong, China, as the study areas. Each landslide inventory and corresponding predisposing factors were stacked to form spatial datasets for LSM. The receiver operating characteristic analysis, area under the curve (AUC), and several statistical metrics, such as accuracy, root mean square error, Kappa coefficient, sensitivity, and specificity, were used to evaluate the performance of the models. Finally, the trained models were calculated, and the landslide susceptibility zones were mapped. Results suggest that both CNN and conventional machine learning-based models have a satisfactory performance. The CNN-based model exhibits an excellent prediction capability and achieves the highest performance but also significantly reduces the salt-of-pepper effect, which indicates its great potential for application to LSM.

/pdf/comparative-study-of-convolutional-neural-network-and-86zlxfbz.pdf

Comparative Study of Convolutional Neural Network and Conventional Machine Learning Methods for Landslide Susceptibility Mapping

The uncertainty of landslide susceptibility prediction modeling: suitability of linear conditioning factors

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. 

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

Deep learning (DL) shows remarkable performance in extracting buildings from high resolution remote sensing images. However, how to improve the performance of DL based methods, especially the perception of spatial information, is worth further study. For this purpose, we proposed a building extraction network with feature highlighting, global awareness, and cross level information fusion (B-FGC-Net). The residual learning and spatial attention unit are introduced in the encoder of the B-FGC-Net, which simplifies the training of deep convolutional neural networks and highlights the spatial information representation of features. The global feature information awareness module is added to capture multiscale contextual information and integrate the global semantic information. The cross level feature recalibration module is used to bridge the semantic gap between low and high level features to complete the effective fusion of cross level information. The performance of the proposed method was tested on two public building datasets and compared with classical methods, such as UNet, LinkNet, and SegNet. Experimental results demonstrate that B-FGC-Net exhibits improved profitability of accurate extraction and information integration for both small and large scale buildings. The IoU scores of B-FGC-Net on WHU and INRIA Building datasets are 90.04% and 79.31%, respectively. B-FGC-Net is an effective and recommended method for extracting buildings from high resolution remote sensing images.

/pdf/b-fgc-net-a-building-extraction-network-from-high-resolution-n19j9lj9.pdf

B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery

Groundwater is considered to be one of the most valuable natural resources in the world. However, the availability of groundwater is of concern. Therefore, understanding the potential of groundwater is very important for the utilization of water resources. The main goal of the study was to predict and assess the groundwater using hybrid machine learning and metaheuristic algorithms to automatically tune the parameters, namely the Random Forest (RF), Support Vector Machines (SVM), the Grey Wolf Algorithm (GWO), and the Sparrow Search Algorithm (SSA). A total of 608 groundwater locations were identified by field surveys. Three different sample datasets (D1-D3) were created to increase the confidence of the result, and each dataset was divided randomly into a training set (70%) and a validation set (30%). Fifteen conditioning factors involving geology, human activity, and hydrology were extracted from the available materials. The Evidential Belief Function (EBF) was employed to determine the correlation between groundwater and factors. Then fourteen relevant factors were selected by feature selection. After that, the hybrid models of RF-GWO, RF-SSA, SVM-GWO, and SVM-SSA built using the datasets (D1-D3) were applied to generate groundwater potential maps (GPMs). Results showed that the performances of the hybrid models can be considered to be stable. The global performance of these hybrid models was assessed using the area under the receiver operating characteristic curve (AUC-ROC) and related statistical indexes. According to the D1 dataset validation results, the AUC values for the RF-GWO, RF-SSA, SVM-GWO, and SVM-SSA were 0.832, 0.840, 0.790, and 0.809, respectively. The RF-SSA had the highest accuracy (0.764), with an AUC of 0.840, and the SVM-GWO showed the least accuracy (0.723), with an AUC of 0.790. The outcomes revealed that all hybrid models had a good predictive performance. However, the RF outperformed the SVM model, and the SSA algorithm is superior to the GWO algorithm. Overall, the results of this study show that the construction of the groundwater potential model using a metaheuristic optimization algorithm is a feasible approach. 

Spatial prediction of groundwater potentiality using machine learning methods with Grey Wolf and Sparrow Search Algorithms

This study proposed a new hybrid model based on the convolutional neural network (CNN) for making effective use of historical datasets and producing a reliable landslide susceptibility map. The proposed model consists of two parts; one is the extraction of landslide spatial information using two-dimensional CNN and pixel windows, and the other is to capture the correlated features among the conditioning factors using one-dimensional convolutional operations. To evaluate the validity of the proposed model, two pure CNN models and the previously used methods of random forest and a support vector machine were selected as the benchmark models. A total of 621 earthquake-triggered landslides in Ludian County, China and 14 conditioning factors derived from the topography, geological, hydrological, geophysical, land use and land cover data were used to generate a geospatial dataset. The conditioning factors were then selected and analyzed by a multicollinearity analysis and the frequency ratio method. Finally, the trained model calculated the landslide probability of each pixel in the study area and produced the resultant susceptibility map. The results indicated that the hybrid model benefitted from the features extraction capability of the CNN and achieved high-performance results in terms of the area under the receiver operating characteristic curve (AUC) and statistical indices. Moreover, the proposed model had 6.2% and 3.7% more improvement than the two pure CNN models in terms of the AUC, respectively. Therefore, the proposed model is capable of accurately mapping landslide susceptibility and providing a promising method for hazard mitigation and land use planning. Additionally, it is recommended to be applied to other areas of the world.

https://www.mdpi.com/2072-4292/13/11/2166/pdf

Incorporating Landslide Spatial Information and Correlated Features among Conditioning Factors for Landslide Susceptibility Mapping

With the development of science and technology, real-time software has become widely used, and software security issues have become prominent. Many real-time systems need to provide strict guarantees for response time, so it is an inevitable problem to study and calculate the Worst-Case Execution Time of a program. In the Worst-Case Execution Time analysis method using model checking technology, this paper proposes a parallel computing acceleration method for the control flow analysis part of Worst-Case Execution static analysis. The results show that the method can alleviate the state space explosion problem in WorstCase Execution analysis method based on model checking technology to a certain extent.

CUDA Acceleration of Worst-Case Execution Time Analysis Based On Model Checking

Because the numerical model dynamic downscaling takes a long time and requires high computing resources, a statistical downscaling model of residual network based on unsupervised learning is proposed. First of all, this network is inspired by the “zero-shot” super-resolution, using ResNet50 as the network residual module, making the network deeper while simplifying the degree of training. It link the low-scoring information of low-scoring pictures to the depths of the network to improve the effect of the network on feature extraction. In addition, KernelGAN is used to train it with the low spatial resolution pictures output by the WRF mode instead of the down sampling blur kernel of the low resolution pictures corresponding to the input in ZSSR. Finally, the channel attention and the spatial attention mechanism are added to change the equality of feature extraction by the main body network. The simulated high temperature image (T2) of Tianjin Port and Bohai Bay two meters from the ground, which is better than Bicubic, Kriging, SRCNN, ZSSSR, KernelGAN+ZSSR and other methods.

Unsupervised learning statistical downscaling based on residual network of attention mechanism

The traditional A* algorithm in the field of meteorological navigation performance and accuracy is insufficient, and cannot meet the use of ships in navigation habits. This paper provides a feasible ocean weather routing optimization algorithm, in order to improve the computing performance and satisfy the navigation of ships used as optimization object, with ship characteristics and voyage forecasting meteorological as constraint conditions, sea conditions to calculate the accurate time saving fuel recommended route as the ultimate goal, through dynamic adding neighbor relationships between each grid, The ship dynamic model based on meteorological sea state influence factor was constructed, the whole route calculation process in A* algorithm was optimized, and the effective solution to the problem was realized by smoothing Bessel function. The experiment and the captain's actual use prove that the meteorological navigation is optimized by optimizing the calculation performance and smoothing process of the route.

Improvement of meteorological navigation route method based on A* algorithm

Metaheuristic algorithm is a generalization of heuristic algorithm that can be applied to almost all optimization problems. For optimization problems, metaheuristic algorithm is one of the methods to find its optimal solution or approximate solution under limited conditions. Most of the existing metaheuristic algorithms are designed for serial systems. Meanwhile, existing algorithms still have a lot of room for improvement in convergence speed, robustness, and performance. To address these issues, this paper proposes an easily parallelizable metaheuristic optimization algorithm called team competition and cooperation optimization (TCCO) inspired by the process of human team cooperation and competition. The proposed algorithm attempts to mathematically model human team cooperation and competition to promote the optimization process and find an approximate solution as close as possible to the optimal solution under limited conditions. In order to evaluate the performance of the proposed algorithm, this paper compares the solution accuracy and convergence speed of the TCCO algorithm with the Grasshopper Optimization Algorithm (GOA), Seagull Optimization Algorithm (SOA), Whale Optimization Algorithm (WOA) and Sparrow Search Algorithm (SSA). Experiment results of 30 test functions commonly used in the optimization field indicate that, compared with these current advanced metaheuristic algorithms, TCCO has strong competitiveness in both solution accuracy and convergence speed. 

Jingjue Chen

Papers

Incorporating Landslide Spatial Information and Correlated Features among Conditioning Factors for Landslide Susceptibility Mapping

CUDA Acceleration of Worst-Case Execution Time Analysis Based On Model Checking

Unsupervised learning statistical downscaling based on residual network of attention mechanism

Improvement of meteorological navigation route method based on A* algorithm

A Novel Metaheuristic Algorithm: The Team Competition and Cooperation Optimization Algorithm