Jing Huang

Bio: Jing Huang is an academic researcher from Hohai University. The author has contributed to research in topics: Flood myth & Flood mitigation. The author has an hindex of 4, co-authored 7 publications receiving 37 citations.

Prediction of Precipitation Based on Recurrent Neural Networks in Jingdezhen, Jiangxi Province, China

Abstract: Precipitation is a critical input for hydrologic simulation and prediction, and is widely used for agriculture, water resources management, and prediction of flood and drought, among other activities. Traditional precipitation prediction researches often established one or more probability models of historical data based on the statistical prediction methods and machine learning techniques. However, few studies have been attempted deep learning methods such as the state-of-the-art for Recurrent Neural Networks (RNNs) networks in meteorological sequence time series predictions. We deployed Long Short-Term Memory (LSTM) network models for predicting the precipitation based on meteorological data from 2008 to 2018 in Jingdezhen City. After identifying the correlation between meteorological variables and the precipitation, nine significant input variables were selected to construct the LSTM model. Then, the selected meteorological variables were refined by the relative importance of input variables to reconstruct the LSTM model. Finally, the LSTM model with final selected input variables is used to predict the precipitation and the performance is compared with other classical statistical algorithms and the machine learning algorithms. The experimental results show that the LSTM is suitable for precipitation prediction. The RNN models, combined with meteorological variables, could predict the precipitation accurately in Jingdezhen City and provide sufficient time to prepare strategies against potential related disasters.

Affect Path to Flood Protective Coping Behaviors using SEM based on A Survey in Shenzhen, China.

Abstract: The initial concept of flood control has gradually shifted to flood risk management which emphasizes more public participation. Therefore, understanding the public’s protective coping behavioral patterns to floods is significant, and can help improve the effectiveness of public participation and implementation of flood-mitigation measures. However, the quantitative effect of socio-demographic factors on flood risk perception and behaviors is not clear. In this study, the socio-demographic factors are included to explore the quantitative relationship with and the affect path to flood protective coping behaviors with socio-demographic factors are studied. Shenzhen City in China is chosen as the study area, which suffers frequent urban floods every year. Questionnaire surveys are conducted in five flood-prone communities there, and 339 valid questionnaires were collected. The correlations between flood risk perception, flood risk knowledge, flood risk attitude, socio-demographic factors, and protective coping behaviors are analyzed firstly. A structural equation model (SEM) about these factors is then established to verify the correctness of hypothetical paths and discover new paths. The results indicates that socio-demographic factors and flood risk perception do not have impacts on protective coping behaviors directly, but are mediated by flood risk knowledge and flood risk attitude. Flood risk attitude is an important factor that affects protective coping behaviors directly. Moreover, two affect paths to flood protective coping behaviors are proposed. The findings of Shenzhen city in this study can be extended to other cities with similar characteristics, providing support for conducting effective flood mitigation measures.

Analysis of Flood Evacuation Process in Vulnerable Community with Mutual Aid Mechanism: An Agent-Based Simulation Framework.

Abstract: Timely and secure evacuation of residents during flood disasters or other emergency events is an important issue in urban community flood risk management, especially in vulnerable communities. An agent-based modeling framework was proposed in order to indicate how the community properties (e.g., community density and percentage of vulnerable residents), residents' psychological attributes (e.g., flood risk tolerance threshold) and mutual aid mechanism affect the flood evacuation process. Results indicated that: (1) The community density negatively affected the flood evacuation efficiency. The greater the density of the community, the longer the evacuation time. (2) There was a negative correlation between the flood risk tolerance threshold of residents and evacuation efficiency. (3) The proportion of vulnerable resident agents had opposite effects on the evacuation efficiency of different types of communities, which was to negatively affect low-density communities and positively affect high-density communities. (4) Mutual aid mechanism can reduce evacuation time in low-density communities, and the effect was more pronounced with a higher proportion of vulnerable resident agents in the community. These findings can help managers to develop better emergency evacuation management for urban communities.

A Novel Approach to Measuring Urban Waterlogging Depth from Images Based on Mask Region-Based Convolutional Neural Network

Abstract: Quickly obtaining accurate waterlogging depth data is vital in urban flood events, especially for emergency response and risk mitigation. In this study, a novel approach to measure urban waterlogging depth was developed using images from social networks and traffic surveillance video systems. The Mask region-based convolutional neural network (Mask R-CNN) model was used to detect tires in waterlogging, which were considered to be reference objects. Then, waterlogging depth was calculated using the height differences method and Pythagorean theorem. The results show that tires detected from images can been used as an effective reference object to calculate waterlogging depth. The Pythagorean theorem method performs better on images from social networks, and the height differences method performs well both on the images from social networks and on traffic surveillance video systems. Overall, the low-cost method proposed in this study can be used to obtain timely waterlogging warning information, and enhance the possibility of using existing social networks and traffic surveillance video systems to perform opportunistic waterlogging sensing.

Influential Factors Affecting Protective Coping Behaviors of Flood Disaster: A Case Study in Shenzhen, China.

Abstract: As the risk of urban flooding increases worldwide, floods seriously endanger the safety of people's lives and property. Understanding the protective coping behaviors of the public in flood disasters is crucial to the implementation of effective flood mitigation measures and flood risk management. In this study, influential factors affecting protective coping behaviors in the face of flood disasters were identified, and the effects of these factors were discussed as well. Shenzhen City in China was selected as the study area, in which a questionnaire survey of 339 respondents was carried out in three flood-prone districts. Correlation analysis was conducted to preselect potential influential factors. Then, two linear regression models were established to identify main influential factors and to explore the interaction effects of these factors. The results indicated that age, monthly income, flood experience, trust in government and insurance willingness were main influential factors of protective coping behaviors. Trust in government had the highest positive correlation coefficient, while monthly income and age were negatively associated with protective coping behaviors. The interaction between insurance willingness and monthly income jointly affected protective coping behaviors of the public. The findings of this study could help authorities better understand the public's intention to cope with flood and design effective risk reduction measures, not only for Shenzhen, but also for many other similar cities that facing with the same situation.

Insights from socio-hydrology modelling on dealing with flood risk: roles of collective memory, risk-taking attitude and trust (Invited)

Abstract: The risk coping culture of a community plays a major role in the development of urban floodplains. In this paper we analyse, in a conceptual way, the interplay of community risk coping culture, flooding damage and economic growth. We particularly focus on three aspects: (i) collective memory, i.e., the capacity of the community to keep risk awareness high; (ii) risk-taking attitude, i.e., the amount of risk the community is collectively willing to be exposed to; and (iii) trust of the community in risk reduction measures. To this end, we use a dynamic model that represents the feedback between the hydrological and social system components. Model results indicate that, on the one hand, by under perceiving the risk of flooding (because of short collective memory and too much trust in flood protection structures) in combination with a high risk-taking attitude, community development is severely limited because of high damages caused by flooding. On the other hand, overestimation of risk (long memory and lack of trust in flood protection structures) leads to lost economic opportunities and recession. There are many scenarios of favourable development resulting from a trade-off between collective memory and trust in risk reduction measures combined with a low to moderate risk-taking attitude. Interestingly, the model gives rise to situations in which the development of the community in the floodplain is path dependent, i.e., the history of flooding may lead to community growth or recession.

Construction and verification of retinal vessel segmentation algorithm for color fundus image under BP neural network model

Abstract: To improve the accuracy of retinal vessel segmentation, a retinal vessel segmentation algorithm for color fundus images based on back-propagation (BP) neural network is proposed according to the characteristics of retinal blood vessels. Four kinds of green channel image enhancement results of adaptive histogram equalization, morphological processing, Gaussian matched filtering, and Hessian matrix filtering are used to form feature vectors. The BP neural network is input to segment blood vessels. Experiments on the color fundus image libraries DRIVE and STARE show that this algorithm can obtain complete retinal blood vessel segmentation as well as connected vessel stems and terminals. When segmenting most small blood vessels, the average accuracy on the DRIVE library reaches 0.9477, and the average accuracy on the STARE library reaches 0.9498, which has a good segmentation effect. Through verification, the algorithm is feasible and effective for blood vessel segmentation of color fundus images and can detect more capillaries.

How computer vision can facilitate flood management: A systematic review

Abstract: Better prediction and monitoring of flood events are key factors contributing to the reduction of their impact on local communities and infrastructure assets. Flood management involves successive phases characterized by specific types of assessments and interventions. Due to technological advances, computer vision plays an increasing role in flood monitoring, modeling and awareness. However, there is a lack of systemic analysis of computer vision's relative adequacy to specific needs associated with successive flood management phases. This article presents a systematic review of relevant literature and proposes a need-based evaluation of these use-cases. Finally, the article highlights future areas of research in this domain.

The Development of a Hybrid Wavelet-ARIMA-LSTM Model for Precipitation Amounts and Drought Analysis

Abstract: Investigation of quantitative predictions of precipitation amounts and forecasts of drought events are conducive to facilitating early drought warnings. However, there has been limited research into or modern statistical analyses of precipitation and drought over Northeast China, one of the most important grain production regions. Therefore, a case study at three meteorological sites which represent three different climate types was explored, and we used time series analysis of monthly precipitation and the grey theory methods for annual precipitation during 1967–2017. Wavelet transformation (WT), autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) methods were utilized to depict the time series, and a new hybrid model wavelet-ARIMA-LSTM (W-AL) of monthly precipitation time series was developed. In addition, GM (1, 1) and DGM (1, 1) of the China Z-Index (CZI) based on annual precipitation were introduced to forecast drought events, because grey system theory specializes in a small sample and results in poor information. The results revealed that (1) W-AL exhibited higher prediction accuracy in monthly precipitation forecasting than ARIMA and LSTM; (2) CZI values calculated through annual precipitation suggested that more slight drought events occurred in Changchun while moderate drought occurred more frequently in Linjiang and Qian Gorlos; (3) GM (1, 1) performed better than DGM (1, 1) in drought event forecasting.