Early Warning Data Research Articles

Real-time sharing algorithm of earthquake early warning data of hydropower station based on deep learning

Real-time sharing algorithm of earthquake early warning data of hydropower station based on deep learning

Research on Regional Early Warning of Flash Flood Disasters in Small Watershed Based on Multi-source Early Warning Data Fusion

The research on the early warning method of flash floods serves as an important groundwork for the prediction and early warning of flash flood disasters. Being restricted by various objective factors such as lack of data and complicated formation mechanism of flash flood disasters in small watersheds, accurate and targeted early warning has consistently been a weak link within the flash flood control system. In this regard, focusing on a series of problems, such as "short risk forecasting period", "frequent missing and false reports" and "poor early warning accuracy", this research explores a hierarchical partition management system that fulfills the demands of early warning based on the analysis of watershed lag time and risk situation. Meanwhile, based on the comprehensive consideration of the characteristics of various multi-source early warning data, such as meteorological forecast rainfall and monitoring rainfall water level, this research proposes corresponding early warning modes for different types of early warning objects. On these grounds, this research applies the proposed early warning system to Xiaguan Creek in Shangyu District, Zhejiang Province. Relevant findings indicate that the effective extension of the forecasting period, coupled with the reduction of the phenomenon of "missing and false reports", provides scientific support for the early warning and transfer decision related to flash floods.

Feature Extraction Algorithm of Food Spoilage Early Warning Data Based on Machine Learning and Internet of Things

Abstract In view of the problems of the current method, such as the large error, low detection efficiency, and poor analysis ability of food deterioration early warning, a spectral feature extraction algorithm of food spoilage early warning data based on machine learning and Internet of Things was proposed. Based on Internet of Things technology, collect food spoilage warning images. The k-means algorithm is used to identify the food variable mass spectrometry data, and the three-dimensional visual feature reconstruction method is devised to reconstruct the image characteristics of the food variable mass spectrum, and the spectral characteristics of the food deterioration warning data are obtained. Based on machine learning, the features of food variable mass spectrometry image are decomposed, and the gray pheromone of food variable mass spectrometry image is extracted. Under the convolutional neural network structure, the spectral features of food deterioration early warning data are vectorized. Based on the results of spectral vectorization, the spectral features of food deterioration early warning data are extracted. The experimental results show that the proposed method can effectively improve the efficiency of food deterioration detection and reduce the error of food deterioration detection for safe environment.

Spatio-Temporal Knowledge Graph-Based Research on Agro-Meteorological Disaster Monitoring

Currently, there is a wealth of data and expert knowledge available on monitoring agro-meteorological disasters. However, there is still a lack of technical means to organically integrate and analyze heterogeneous data sources in a collaborative manner. This paper proposes a method for monitoring agro-meteorological disasters based on a spatio-temporal knowledge graph. It employs a semantic ontology framework to achieve the organic fusion of multi-source heterogeneous data, including remote sensing data, meteorological data, farmland data, crop information, etc. And it formalizes expert knowledge and computational models into knowledge inference rules, thereby enabling monitoring, early warning, and disaster analysis of agricultural crops within the observed area. The experimental area for this research is the wheat planting region in three counties in Henan Province. The method is tested using simulation monitoring, early warning, and impact calculation of the past two occurrences of dry hot wind disasters. The experimental results demonstrate that the proposed method can provide more specific and accurate warning information and post-disaster analysis results compared to raw records. The statistical results of NDVI decline also validate the correlation between the severity of wheat damage caused by dry hot winds and the intensity and duration of their occurrences. Regarding remote sensing data, this paper proposes a method that directly incorporates remote sensing data into spatio-temporal knowledge inference calculations. By integrating remote sensing data into the regular monitoring process, the advantages of remote sensing data granted by continuous observation are utilized. This approach represents a beneficial attempt to organically integrate remote sensing and meteorological data for monitoring, early warning, and evaluation analysis of agro-meteorological disasters.

Assessment of Suspected COVID-19 Deaths in Nonhealthcare Settings in Cote d'Ivoire, March 11 to July 31, 2020.

According to hospital records, 5 months after reporting its first case of COVID-19, Cote d'Ivoire reported only 102 deaths. We conducted a community mortality survey in the 13 districts where 95% of COVID-19 cases were reported to assess COVID-19 mortality in nonhealthcare settings. To identify suspected COVID-19 deaths in communities, we used data from social and administrative institutions, such as police and fire departments, funeral homes, and places of worship, whose functions include providing services related to deaths. Our survey identified 54 (17.6%) suspected COVID-19 deaths, which is more than half of the official reported number. Our study showed that in areas with low access to healthcare and poorly functioning death notification and registration systems, community-based data sources could be used to identify suspected COVID-19 deaths outside of the health sector. They can provide early warning data on events, such as an unusual number of community deaths or diseases.

STUDY AND APPLICATION OF FLOOD CONTROL RISK TREND ANALYSIS MODEL

Abstract. In order to analyze the comprehensive risks of natural disasters quantitatively and improve the accuracy of natural disaster management and control, this paper expands the F indicator, Forecast, which is about real-time monitoring and early warning data of natural disasters, and forms the flood control risk trend analysis model framework based on PSR. The framework is named FPSR, i.e. Forecast-Pressure-State-Response, composed of static data and dynamic data. By establishing the four-level index system of flood control risk trend analysis in Fangshan District of Beijing, screening factors, and using analytic hierarchy process, AHP, and experts scoring to determine the weights of each factor, it constructs the flood control risk trend analysis model, FCRTAM. At last, using the real-time monitoring and early warning data of natural disasters in Beijing and the information such as disaster-causing factors, historical natural disasters, major hidden dangers, disaster-bearing bodies, disaster reduction resources (capacities), etc., from National Natural Disaster Comprehensive Risk Census in Fangshan, it analyzes the flood control situation of each town in Fangshan. The results show that the results flood control risk index calculated according to FCRTAM is basically consistent with the actual flood control situation of the towns in Fangshan, and can provide theoretical basis for flood control comprehensive risk trend analysis and the decision-making of disaster prevention and reduction in Fangshan District, which has high use value.

Urban waterlogging prediction and risk analysis based on rainfall time series features: A case study of Shenzhen

In recent years, the frequency of extreme weather has increased, and urban waterlogging caused by sudden rainfall has occurred from time to time. With the development of urbanization, a large amount of land has been developed and the proportion of impervious area has increased, intensifying the risk of urban waterlogging. How to use the available meteorological data for accurate prediction and early warning of waterlogging hazards has become a key issue in the field of disaster prevention and risk assessment. In this paper, based on historical meteorological data, we combine domain knowledge and model parameters to experimentally extract rainfall time series related features for future waterlogging depth prediction. A novel waterlogging depth prediction model that applies only rainfall data as input is proposed by machine learning algorithms. By analyzing a large amount of historical flooding monitoring data, a “rainfall-waterlogging amplification factor” based on the geographical features of monitoring stations is constructed to quantify the mapping relationship between rainfall and waterlogging depths at different locations. After the model is trained and corrected by the measured data, the prediction error for short-time rainfall basically reaches within 2 cm. This method improves prediction performance by a factor of 2.5–3 over featureless time series methods. It effectively overcomes the limitations of small coverage of monitoring stations and insufficient historical waterlogging data, and can achieve more accurate short-term waterlogging prediction. At the same time, it can provide reference suggestions for the government to conduct waterlogging risk analysis and add new sensor stations by counting the amplification factor of other locations.

Usefulness of disease surveillance data in enhanced early warning of the cholera outbreak in Southwest Cameroon, 2018

IntroductionThis study assessed the timeliness and completeness of disease surveillance data for early warning of the cholera outbreak during the socio-political crisis of Southwest Cameroon in 2018. It determined how routine integrated disease surveillance and response (IDSR) data was used for preventative actions and the challenges faced by key health staff in IDSR based decision-making.MethodsThis was a mixed-methods study conducted from June 1st to September 30th 2021. District Health Information System 2 (DHIS2) data from January 2018 to December 2020 for the Southwest region of Cameroon were analysed using simple linear regression on EPI Info 7.2 to determine a potential association of the sociopolitical crisis with timeliness and completeness of data. Qualitative data generated through in-depth interviews of key informants were coded and analyzed using NVivo 12.ResultsDuring high conflict intensity (2018 and 2019), average data timeliness and completeness were 16.3% and 67.2%, respectively, increasing to 40.7% and 80.2%, respectively, in 2020 when the conflict intensity had reduced. There was a statistically significant weak correlation between reduced conflict intensity and increased data timeliness (R2 = 0.17, p = 0.016) and there was also a weak correlation between reduced conflict intensity and data completeness but this was not statistically significant (R2 = 0.01, p = 0.642). During high conflict intensity, the Kumba and Buea health districts had the highest data timeliness (17.2% and 96.2%, respectively) and data completeness (78.8% and 40.4%, respectively) possibly because of proximity to reporting sites and effective performance based financing. Components of IDSR that should be maintained included the electronic report aspect of the DHIS2 and the supportive supervision conducted during the outbreak. Staff demotivation, the parallel multiplicity of data entry tools, poor communication, shortage of staff and the non-usability of data generated by the DHIS2 were systemic challenges to the early alert dimension of the IDSR system. Non–systemic challenges included high levels of insecurity, far to reach outbreak sites and health personnel being targeted during the conflict.ConclusionIn general, routine IDSR data was not a reliable way of providing early warning of the 2018 cholera outbreak because of incomplete and late reports. Nonetheless, reduced conflict intensity correlated with increased timeliness and completeness of data reporting. The IDSR was substantially challenged during the crisis, and erroneous data generated by the DHIS 2 significantly undermined the efforts and resources invested to control the outbreak. The Ministry of Public Health should reinforce efforts to build a reporting system that produces people-centered actionable data that engages health risk management during socio-political crises.

Can North American animal poison control center call data provide early warning of outbreaks associated with contaminated pet food? Using the 2007 melamine pet food contamination incident as a case study.

The 2007 melamine pet food contamination incident highlighted the need for enhanced reporting of toxicological exposures and development of a national quantitative disease surveillance system for companion animals. Data from poison control centers, such as the Animal Poison Control Center (APCC), may be useful for conducting real-time surveillance in this population. In this study, we explored the suitability of APCC call data for early warning of toxicological incidents in companion animal populations by using a-priori knowledge of the melamine-related nephrotoxicosis outbreak. Patient and household-level information regarding possible toxicological exposures in dogs and cats reported to the APCC from 2005 to 2007, inclusive, were extracted from the APCC's AnTox database. These data were used to examine the impact of surveillance outcome, statistical methodology, analysis level, and call source on the ability to detect the outbreak prior to the voluntary recall issued by the pet food manufacturer. Retrospective Poisson temporal scan tests were applied for each combination of outcome, method, level, and call source. The results showed that month-adjusted scans using syndromic data may have been able to help detect the outbreak up to two months prior to the voluntary recall although the success of these methods varied across call sources. We also demonstrated covariate month-adjustment can lead to vastly different results based on the surveillance outcome and call source to which it is applied. This illustrates care should be taken prior to arbitrarily selecting a surveillance outcome and statistical model for surveillance efforts and warns against ignoring the impacts of call source or key covariates when applying quantitative surveillance methods to APCC call data since these factors can lead to very different results. This study provides further evidence that APCC call data may be useful for conducting surveillance in the US companion animal population and further exploratory analyses and validation studies are warranted.

Fault Early Warning Model for High-Speed Railway Train Based on Feature Contribution and Causal Inference

The demands for model accuracy and computing efficiency in fault warning scenarios are increasing as high-speed railway train technology continues to advance. The black box model is difficult to interpret, making it impossible for this technology to be widely adopted in the railway industry, which has strict safety regulations. This paper proposes a fault early warning machine learning model based on feature contribution and causal inference. First, the contributions of the features are calculated through the Shapley additive explanations model. Then, causal relationships are discovered through causal inference models. Finally, data from causal and high-contribution time series are applied to the model. Ablation tests are conducted with the Naïve Bayes, Gradient Boosting Decision Tree, eXtreme Gradient Boosting, and other models in order to confirm the efficiency of the method based on early warning data regarding the on-site high-speed train traction equipment circuit board failure. The findings indicate that the strategy improves the evaluation markers, including the early warning accuracy, precision, recall, and F1 score, by an average of more than 10%. There is a 35% improvement in the computing efficiency, and the model can provide feature causal graph verification for expert product decision-making.

Viability of a circular economy for space debris

The orbital debris population is rapidly growing, increasing the chance of a Kessler-style collision event. We report a novel method for the production of estimates for the total monetary value of all debris objects and total mass of all objects currently in orbit. The method was devised using debris object data from the European Space Agency’s DISCOS dataset, classified via a decision tree. ‘Reuse’ and ‘scrap material’ scenarios were developed. A high-end estimate for reuse shows a net value of $1.2 trillion. Median and low-end net value estimates of $600 billion and $570 billion, respectively, are probably judicious. A scrap material scenario produced a high mass estimate of 19,124 tonnes, a median of 6,978 tonnes and a low estimate of 5,312 tonnes. Development of in-orbit services will be crucial to solve the orbital debris problem. A future circular economy for space may be financially viable, with potentially beneficial consequences for risk reduction; resource efficiency; additional high-value employment; and climate-change knowledge, science, monitoring and early warning data.

Power-Sensitive Early Warning Data Conversion Method Combined with Multiobjective Differential Evolution Algorithm

Aiming at the problems of economy, security, and reliability of power system operation, the multiobjective gap evolutionary algorithm is introduced into power-sensitive early warning data conversion. A power-sensitive early warning data conversion (PSEWDC) method based on multiobjective gap evolutionary algorithm (MOGEA) is proposed. According to the type of equipment with problems in the operation of the power system and the rapid diagnosis of defects and problems, the method quickly locates the problems and analyzes the causes, replaces and rearranges the original data by using the substitution data method to eliminate the nonlinear autocorrelation, and then, according to the convergence of the long-range correlation index, identifies the abnormal values that have no impact on the overall fluctuation of the original sequence, judges that the current sequence reaches the critical point of extreme events, and provides a reference threshold for real-time risk early warning. Finally, the example analysis shows that this method can finally determine the risk early warning threshold of power peak and valley load by analyzing the convergence of long-range correlation index, so as to avoid the blindness of subjective experience, provide a theoretical basis for power load risk early warning, effectively solve the problems of subjectivity, lack of dynamics, and lack of theoretical basis for setting risk threshold in traditional power risk early warning research, and have an intelligent insight into the security situation of power big data.

BP Neural Network Algorithm Based on Big Data for Monitoring and Early Warning of China’s Public Finance

Public finance plays an important role in the development and construction of the country. Public finance is derived from and used by the people. On the one hand, public finance mainly comes from national taxes and the income of some state-owned enterprises or state-owned assets. On the other hand, public finance is used for national infrastructure, military investment, scientific and technological research and development, national daily operation, and other expenses. Therefore, the state of public finance is closely related to people's lives, and it is also one of the basic symbols of a country's prosperity and strength. How to ensure that the country's public finance is in a good state, grasp the leverage balance of public finance revenue and expenditure, and avoid the situation of national “bankruptcy” is additional attention that the public finance department should pay in the process of operation. Therefore, we urgently need a set of public finance monitoring and early warning system that matches China's public finance operation mechanism and conforms to China's basic national conditions. At present, previous studies rely on the existing detailed data on public finance to measure the situation of China's public finance, but this method refers to fewer data and is not forward-looking enough. Therefore, this paper adopts a BP neural network algorithm to monitor and warn the situation of China's public finance based on computer big data.

Integration of Wifi and Mobile Communications in Fire Early Warning Data Sending in Home Based on The Internet of Things

House fires are one of the disasters that are often encountered in the community, especially when the area is a dry geographical area. Not to mention the catastrophic house fires that took the most lives and losses for homeowners. The purpose of this research is how to build a disaster early warning system by utilizing the integration of wifi and cellular communications. In this study using blackbox testing and hardware testing methods as well as several tools such as Arduino Mega2560, ESP32, DHT-22, MQ-2, LDR Array, SIM900, Pump Mini DC and Fan Mini DC. After the results of the system design, where the system works with online and offline conditions and as well as each sensor works according to the input conditions of fire, gas and smoke.

Dynamic Early-Warning Model of College Students’ Psychological Crisis Based on Characteristic Attribute

At present, the existing dynamic early-warning model of college students' psychological crisis cannot obtain psychological characteristics, and the error of psychological crisis prediction is large. The early-warning result of psychological crisis appears big deviation. A new dynamic early-warning model of college students' psychological crisis is designed based on characteristic attributes. In the process of modeling negative psychological crisis of college students, the fusion constraint fuzzy theory obtains the essence of college students' psychology from subjective and objective reasons, gives the different stages of college students' psychology, obtains the corresponding information entropy of the behavior hindrance in each stage of college students' psychology, and calculates the threshold value of the behavior tendency of college students' psychology. Based on the psychological state information of college students obtained by perception, the fuzzy comprehensive early-warning data model of feature attributes is constructed. According to the fuzzy comprehensive early-warning method and the early-warning index system, the early-warning factor set of college students' psychological crisis is constructed, and the dynamic early-warning model of college students' psychological crisis is constructed. Experimental results show that the mining results are consistent with the actual situation, and the grey relational degree, small error probability, and mean square ratio index are better than the present model.

Analysis of College Students' Psychological Education Management in Public Emergencies Based on Big Data.

In recent years, college students' psychological problems have occurred frequently, and the early warning of college students' psychological crisis has received social attention. Artificial intelligence and big data, as emerging technologies that have attracted much attention in recent years, have broad application and development space in improving the development of intelligent and refined education in colleges and universities. Applying artificial intelligence and big data to the practice of college students' mental health education plays a very positive role in accurately finding and scientifically solving college students' mental health problems. This paper combs the current application and research of artificial intelligence and big data in college students' mental health education and then clarifies the problems existing in the practical application. Finally, on the basis of in-depth analysis of the characteristics of college students' psychological crisis, the paper designs college students' psychological crisis early warning data collection system from six aspects, including the educational administration system and the access control system. And from the aspects of establishing a multilevel linkage feedback early warning system, building a team of big data technical personnel and mental health education personnel, it puts forward countermeasures for college students' psychological crisis, so as to provide theoretical and methodological support for college mental health management.

Impact of geomagnetic disturbances on power transformers: risk assessment of extreme events and data availability

Certain rare events can have a drastic impact on power systems. Such events are generally known as high-impact low-probability (HILP) events. It is challenging to predict the occurrence of a HILP event mainly due to lack of data or sparsity and scarcity of data points. Yet, it is essential to implement an evidence-driven asset management strategy. In this paper, event tree analysis is used to assess the risk of power transformer failure due to a geomagnetically induced currents (GIC). Those currents are caused by geomagnetic disturbances in Earth’s magnetic field due to solar activity. To assess the impact on power transformers, an understanding of the mechanism and sequence of sub-events that lead to failure is required to be able to construct an event tree. Based on the constructed event tree, mitigation actions can be derived. GIC blockers or reducers can be used. However, that would require extensive installation and maintenance efforts, and the impact on system reliability has to be studied. Also, such technology is still in its infancy and needs extensive validation. A suggested alternative is to combine early warning data from solar observatories with a load management plan to keep transformers below their rated operation point such that a DC offset due to GIC would not cause magnetic core saturation and overheating. Load management and the risk of early warning false positives can incur a negative effect on reliability. Nevertheless, the risk assessment performed in this paper show that incorporating load management in asset planning is a viable measure that would offset the probability of catastrophic failure.

Landslide Monitoring and Early Warning System based on Edge Computing

With the advancement of modern sensing technology and network communication, the geological disaster monitoring and early warning technology is changing toward intelligence, continuity, and real-time monitoring. The most effective way to improve real-time monitoring and early warning is to conduct front-end analysis in the field of geological disasters. With the application of the Internet of Things technology in geological disasters, field data collection and field-level data strategies belong to the edge computing gateway for execution. According to the latest research trend of landslide on-site monitoring and early warning, edge computing gateways usually use thresholds for monitoring and early warning. On the basis of the empirical model of simple statistics or the theoretical model of landslide deformation early warning, key early warning indicators and weights are proposed to judge the stage of landslide evolution or disaster level. This study starts with a comprehensive analysis of the temporal and spatial evolution of the surface deformation area in the field of geological disaster monitoring. Then, an edge computing smart gateway is designed on the basis of the Linux operating system. The Long Range Radio field wireless sensor network is used to develop an automated monitoring system for slopes of displacement monitoring points, rainfall, and soil moisture content-inducing factors. Subsequently, the effective methods of obtaining multilevel topographic data of slopes are investigated using field information, such as the velocity and acceleration of surface displacement data. The slope multielement trigger monitoring model with multiple induced element coupling modes is explored to realize the front-end edge computing strategy method of slope monitoring and early warning. The analysis results can be sent to high-level data analysis servers, such as the software deployed on the Local Area Network and cloud servers of the relevant department for secondary use. This research overcomes the problems of regular collection of existing on-site monitoring instruments, loss of catastrophic information, and low effective data rate. Compared with traditional working modes, such as uploading the original monitoring data to a server for data extraction and analysis and then feedback to control the field equipment, using front-end edge computing is more efficient in realizing the first data processing utilization and adaptive monitoring processing. It can also provide more effective and reliable data for disaster monitoring and early warning. In conclusion, this research is of great significance in effectively capturing the laws of early evolution, improving real-time early warning capabilities, and promoting the industrialization of national geological disaster monitoring and early warning technology and equipment.

Research on Monitoring System of Cable Joints of Ring Network Cabinet Based on Wireless Temperature Sensor

In this paper, a state monitoring system for the cable joints of the ring main unit is constructed based on the passive wireless temperature sensor. Considering the sensor packaging structure and housing material, a temperature sensor that can meet the monitoring requirements of the T-shaped insulating sheath of the cable joint is designed. Based on the thermal circuit method, the real temperature value of the internal cable joint is calculated by using the outer surface temperature of the T-shaped insulating sheath to provide more accurate data for monitoring and early warning. The background monitoring software of the monitoring system is designed to realize the temperature of the T-shaped cable joint in the ring network cabinet. Online monitoring and abnormal early warning facilitate the operation and maintenance personnel to take timely measures, which can effectively improve the operation and maintenance efficiency of the ring cabinet of the distribution network and ensure the reliability of power supply.

Effective Training Data Extraction Method to Improve Influenza Outbreak Prediction from Online News Articles: Deep Learning Model Study.

BackgroundEach year, influenza affects 3 to 5 million people and causes 290,000 to 650,000 fatalities worldwide. To reduce the fatalities caused by influenza, several countries have established influenza surveillance systems to collect early warning data. However, proper and timely warnings are hindered by a 1- to 2-week delay between the actual disease outbreaks and the publication of surveillance data. To address the issue, novel methods for influenza surveillance and prediction using real-time internet data (such as search queries, microblogging, and news) have been proposed. Some of the currently popular approaches extract online data and use machine learning to predict influenza occurrences in a classification mode. However, many of these methods extract training data subjectively, and it is difficult to capture the latent characteristics of the data correctly. There is a critical need to devise new approaches that focus on extracting training data by reflecting the latent characteristics of the data.ObjectiveIn this paper, we propose an effective method to extract training data in a manner that reflects the hidden features and improves the performance by filtering and selecting only the keywords related to influenza before the prediction.MethodsAlthough word embedding provides a distributed representation of words by encoding the hidden relationships between various tokens, we enhanced the word embeddings by selecting keywords related to the influenza outbreak and sorting the extracted keywords using the Pearson correlation coefficient in order to solely keep the tokens with high correlation with the actual influenza outbreak. The keyword extraction process was followed by a predictive model based on long short-term memory that predicts the influenza outbreak. To assess the performance of the proposed predictive model, we used and compared a variety of word embedding techniques.ResultsWord embedding without our proposed sorting process showed 0.8705 prediction accuracy when 50.2 keywords were selected on average. Conversely, word embedding using our proposed sorting process showed 0.8868 prediction accuracy and an improvement in prediction accuracy of 12.6%, although smaller amounts of training data were selected, with only 20.6 keywords on average.ConclusionsThe sorting stage empowers the embedding process, which improves the feature extraction process because it acts as a knowledge base for the prediction component. The model outperformed other current approaches that use flat extraction before prediction.