Natural Disasters Intensity Analysis and Classification Based on Multispectral Images Using Multi-Layered Deep Convolutional Neural Network

Natural disasters not only disturb the human ecological system but also destroy the properties and critical infrastructures of human societies and even lead to permanent change in the ecosystem. Disaster can be caused by naturally occurring events such as earthquakes, cyclones, floods, and wildfires. Many deep learning techniques have been applied by various researchers to detect and classify natural disasters to overcome losses in ecosystems, but detection of natural disasters still faces issues due to the complex and imbalanced structures of images. To tackle this problem, we propose a multilayered deep convolutional neural network. The proposed model works in two blocks: Block-I convolutional neural network (B-I CNN), for detection and occurrence of disasters, and Block-II convolutional neural network (B-II CNN), for classification of natural disaster intensity types with different filters and parameters. The model is tested on 4428 natural images and performance is calculated and expressed as different statistical values: sensitivity (SE), 97.54%; specificity (SP), 98.22%; accuracy rate (AR), 99.92%; precision (PRE), 97.79%; and F1-score (F1), 97.97%. The overall accuracy for the whole model is 99.92%, which is competitive and comparable with state-of-the-art algorithms.

Analysis of large-scale transmission line icing and galloping event in the Jilin province during November 2020

A large-scale transmission line icing and galloping event occurred in Jilin province during November 2020. First of all, the circulation background and the evolution characteristics of key meteorological factors of the icing and galloping event are analysed, which provide basis for the prediction and early warning of the galloping event in the future. It is found that, the warm and wet air transported northward to the central part of Northeast China due to the abnormal northward position of the western pacific subtropical high, combined with the strong cold air activity in the north, the cold and warm air converged in the middle of Northeast China, resulting in the co-occurrence of temperature decline, precipitation, gale and high humidity, which is the direct cause of this large-scale galloping event. Then, the prediction and actual situation of the disaster event are analysed. The results show that the power gird icing and galloping numerical prediction system accurately predicted the influence area and disaster intensity three days in advance, which can provide effective support for future disaster response. Finally, some relevant suggestions are put forward according to the characteristics of this disaster.

Analysis of agricultural meteorological disasters in Shaanxi Province from 1981 to 2018 and their impact on grain production

This paper studied the change characteristics of four types of agricultural meteorological disasters such as flood, drought, hail and freeze and their impact on the total grain yield of Shaanxi Province. Based on the agricultural statistical data of Shaanxi Province from 1981 to 2018, the disaster-affected rate, disaster-suffered rate and disaster intensity index, as well as the grey correlation analysis method were used to analyze the agricultural meteorological disasters and their impact on grain yield in Shaanxi Province from 1981 to 2018. The results show that drought has the largest disaster-affected area and disaster-suffered area in Shaanxi Province, but the disaster-affected rate and disaster-suffered rate increases first and then decreases. The difference of disaster intensity among flood, drought and hail is relatively small, among which the drought disaster has the strongest disaster intensity and the freeze has a relatively weak disaster intensity. The grey correlation analysis show that the affected area of hail disasters has the greatest impact on the total grain yield of Shaanxi Province, followed by drought and flood, and the affected area of freeze disaster has a relatively small impact on the total grain yield.

DEVELOPING FRAMEWORK FOR IMPROVING DISASTER RESILIENCE IN URBAN SLUM UPGRADING

Abstract_ Disaster resilience has become an important urban agenda due to the increasing disaster intensity and massive impacts. Developing framework for measuring disaster resilience is a critical policy particularly for urban slum area. It requires extensive and comprehensive approach to achieve sustainable measurement. Providing the integration of the research and the present disaster resilience measurement through content analysis of qualitative approach, this study introduces the framework composed of categories and indicators for improving disaster Resilience in urban slum areas under upgrading efforts. It recommends that community capital: the public infrastructure and facilities, human, financial, natural, and social can be categories for indicators development. These capitals can reflect numerous elements, resources, and relationships within an urban slum areas and its main contribution for community.Keywords: Disaster Resilience; Slum Upgrading; Community Capital.

Log Transform Based Optimal Image Enhancement Using Firefly Algorithm for Autonomous Mini Unmanned Aerial Vehicle: An Application of Aerial Photography

The Unmanned Aerial Vehicles (UAV) are widely used for capturing images in border area surveillance, disaster intensity monitoring, etc. An aerial photograph offers a permanent recording solution as well. But rapid weather change, low quality image capturing equipments results in low/poor contrast images during image acquisition by Autonomous UAV. In this current study, a well-known meta-heuristic technique, namely, Firefly Algorithm (FA) is reported to enhance aerial images taken by a Mini Unmanned Aerial Vehicle (MUAV) via optimizing the value of certain parameters. These parameters have a wide range as used in the Log Transformation for image enhancement. The entropy and edge information of the images is used as an objective criterion for evaluating the image enhancement of the proposed system. Inconsistent with the objective criterion, the FA is used to optimize the parameters employed in the objective function that accomplishes the superlative enhanced image. A low-light imaging has been performed at evening time to prove the effectiveness of the proposed algorithm. The results illustrate that the proposed method has better convergence and fitness values compared to Particle Swarm Optimization. Therefore, FA is superior to PSO, as it converges after a less number of iterations.

THE DETERMINATION METHOD OF EXTREME EARTHQUAKE DISASTER AREA BASED ON THE DUST DETECTION RESULT FROM GF-4 DATA

The remote sensing has played an important role in many earthquake emergencies by rapidly providing the building damage, road damage, landslide and other disaster information. The earthquake in the mountains often caused to the loosening of the mountains and the blowing of the dust in the epicentre area. The dust particles are more serious in the epicentre area than the other disaster area. Basis on the analysis of abnormal spectrum characteristics, the dust detection methods from medium and high resolutions satellite imagery are studied in order to determinate the extreme earthquake disaster area. The results indicate the distribution of extreme disaster can be acquired using the dust detection information from imagery, which can provide great help for disaster intensity assessment.

Predicting Delay of Commuting Activities Following Frequently Occurring Disasters Using Location Data from Smartphones

Natural disasters that frequently occur, such as typhoons and earthquakes, heavily affect human activities in urban areas by causing severe congestion and economic loss. Predicting the delay in usual commuting activities of individuals following such disasters is crucial for managing urban systems. We propose a novel method that predicts such delay of individuals’ movements in several frequently occurring disasters using various types of features including the commuters’ usual movement patterns, disaster information, and geospatial information of commuters’ locations. Our method predicts the irregularity of commuting activities in metropolitan Tokyo during several typhoons, and earthquakes, using Yahoo Japan’s GPS dataset of 1 million users. The results show that the irregularity of individuals’ movements are significantly more predictable than with previous models. Also, we are able to understand that commuters’ usual movement patterns, disaster intensity, and geospatial features including road density and population density are main factors that cause commuting delay following disasters.

The quantitative estimation of the vulnerability of brick and concrete wall impacted by an experimental boulder

There is little historic data about the vulnerability of damaged elements due to debris flow events in China. Therefore, it is difficult to quantitatively estimate the vulnerable elements suffered by debris flows. This paper is devoted to the research of the vulnerability of brick and concrete walls impacted by debris flows. An experimental boulder (an iron sphere) was applied to be the substitute of debris flow since it can produce similar shape impulse load on elements as debris flow. Several walls made of brick and concrete were constructed in prototype dimensions to physically simulate the damaged structures in debris flows. The maximum impact force was measured, and the damage conditions of the elements (including cracks and displacements) were collected, described and compared. The failure criterion of brick and concrete wall was proposed with reference to the structure characteristics as well as the damage pattern caused by debris flows. The quantitative estimation of the vulnerability of brick and concrete wall was finally established based on fuzzy mathematics and the proposed failure criterion. Momentum, maximum impact force and maximum impact bending moment were compared to be the best candidate for disaster intensity index. The results show that the maximum impact bending moment seems to be most suitable for the disaster intensity index in establishing vulnerability curve and formula.