An Earthquake Early Warning System (EEWS) can save lives. It can also be used to manage the critical lifeline infrastructure and essential facilities. Recent research on earthquake prediction towards ...the development of an EEWS can be classified into two groups based on a) arrival of P waves and b) seismicity indicators. The first approach can provide warnings within a timeframe of seconds. A seismicity indicator-based EEWS is intended to forecast major earthquakes within a time frame of weeks. In this paper, a novel seismicity indicator-based EEWS model, called neural EEWS (NEEWS), is presented for forecasting the earthquake magnitude and its location weeks before occurrence using a combination of a classification algorithm (CA) based on machine learning concepts and a mathematical optimization algorithm (OA). The role of the CA is to find whether there is an earthquake in a given time period greater than a predefined magnitude threshold and the role of the OA is to find the location of that earthquake with the maximum probability of occurrence. The model is tested using earthquake data in southern California with a combination of four CAs and one OA to find the best EEWS model. The proposed model is capable of predicting strong disastrous events as long as sufficient data are available for such events. The paper provides a novel solution to the complex problem of earthquake prediction through adroit integration of a machine learning classification algorithm and the robust neural dynamics optimization algorithm of Adeli and Park.
•Earthquake Early Warning System for forecasting earthquake magnitude and location.•It combines of a classification algorithm with a mathematical optimization algorithm.•Classification algorithms are neural dynamic classification, PNN, EPNN, and SVM.•The optimization algorithm is the neural dynamics model of Adeli and Park.•The model is tested using earthquake data in southern California.
•Long-range infrasound data detect the activity of Indonesian Volcanoes•The Infrasound Parameter, IP, can notify VEI ≥ 3 eruptions in near real-time•The IP is improved with the threshold on signal ...persistency and on the amplitude
Detecting and notifying ongoing volcanic explosive eruptions is crucial in supporting the Volcanic Ash Advisory Centre (VAAC). However, local monitoring systems are missing at many active volcanoes, but long range infrasound monitoring might provide useful information if able to detect and notify volcanic explosive events. Indeed, many studies have already highlighted the utility and the potential of long-range infrasound monitoring for this aim, but still open questions remain concerning its actual efficiency and reliability. In this study we investigate the potential of the IS06 array (Cocos Island, Australia) of the International Monitoring System (IMS) of the Comprehensive Nuclear-Test-Ban Treaty Organization (CTBTO) to remotely detect volcanic explosive eruptions in the Indonesian Arc between 2012 and 2019, when 11 volcanoes, positioned at a distance between 1000 and 2000 km from the array, erupted with an energy spanning from mild explosions to VEI (Volcanic Explosivity Index) 4 eruptions. For each volcano, using infrasonic data recorded at a single array and accounting for realistic infrasound propagation conditions, we calculate a range corrected Infrasound Parameter (IP) and propose two additional empirical thresholds on signal strength and persistency. The IP is used eventually to define an alert whenever an established threshold is exceeded and the corresponding reliability estimated. Results show that the range corrected IP is highly reliable for events VEI = 3 or greater under favorable propagation conditions, but smaller scale short-lasting explosive eruptions still remain usually undetected. Unresolved ambiguity remains due to short spacing among volcanoes with respect to the array. For regional scale monitoring purposes, this can be solved only considering volcanic sectors rather than single volcanic edifices that, despite preventing unambiguous notification of a given volcano, might allow to increase the attention of the VAAC over a specific area.
Under the background of global industrialization, PM2.5 has become the fourth-leading risk factor for ischemic stroke worldwide, according to the 2019 GBD estimates. This highlights the hazards of ...PM2.5 for ischemic stroke, but unfortunately, PM2.5 has not received the attention that matches its harmfulness. This article is the first to systematically describe the molecular biological mechanism of PM2.5-induced ischemic stroke, and also propose potential therapeutic and intervention strategies. We highlight the effect of PM2.5 on traditional cerebrovascular risk factors (hypertension, hyperglycemia, dyslipidemia, atrial fibrillation), which were easily overlooked in previous studies. Additionally, the effects of PM2.5 on platelet parameters, megakaryocytes activation, platelet methylation, and PM2.5-induced oxidative stress, local RAS activation, and miRNA alterations in endothelial cells have also been described. Finally, PM2.5-induced ischemic brain pathological injury and microglia-dominated neuroinflammation are discussed. Our ultimate goal is to raise the public awareness of the harm of PM2.5 to ischemic stroke, and to provide a certain level of health guidance for stroke-susceptible populations, as well as point out some interesting ideas and directions for future clinical and basic research.
Display omitted
•The public awareness of the harm of PM2.5 to stroke is relatively insufficient.•PM2.5 is one of the major risk factors for ischemic stroke.•PM2.5 accelerates ischemic stroke by influencing cerebrovascular risk factors.•PM2.5 mediates platelet activation, endothelial injury, and neuroinflammation.•Establishment of PM2.5 warning system for stroke is necessary.
Waves overtop berms and seawalls along the shoreline of Imperial Beach (IB), CA when energetic winter swell and high tide coincide. These intermittent, few-hour long events flood low-lying areas and ...pose a growing inundation risk as sea levels rise. To support city flood response and management, an IB flood warning system was developed. Total water level (TWL) forecasts combine predictions of tides and sea-level anomalies with wave runup estimates based on incident wave forecasts and the nonlinear wave model SWASH. In contrast to widely used empirical runup formulas that rely on significant wave height and peak period, and use only a foreshore slope for bathymetry, the SWASH model incorporates spectral incident wave forcing and uses the cross-shore depth profile. TWL forecasts using a SWASH emulator demonstrate skill several days in advance. Observations set TWL thresholds for minor and moderate flooding. The specific wave and water level conditions that lead to flooding, and key contributors to TWL uncertainty, are identified. TWL forecast skill is reduced by errors in the incident wave forecast and the one-dimensional runup model, and lack of information of variable beach morphology (e.g., protective sand berms can erode during storms). Model errors are largest for the most extreme events. Without mitigation, projected sea-level rise will substantially increase the duration and severity of street flooding. Application of the warning system approach to other locations requires incident wave hindcasts and forecasts, numerical simulation of the runup associated with local storms and beach morphology, and model calibration with flood observations.
•Investigated the impact of real-time pedestrian scale info on driver braking using a VR driving simulator and eye-tracking.•Created and evaluated a novel warning system that provides drivers with ...dynamic information about pedestrian crowd size.•Showed that crowd scale info significantly affects drivers' deceleration, yielding behavior, and attention levels.•Found that larger pedestrian groups increase Time to Collision (TTC) and stopping distances, enhancing safety.•Proved the system’s effectiveness in complex road conditions, especially under low visibility, regardless of driver gender.
A driver warning system can improve pedestrian safety by providing drivers with alerts about potential hazards. Most driver warning systems have primarily focused on detecting the presence of pedestrians, without considering other factors, such as the pedestrian’s gender and speed, and whether pedestrians are carrying luggage, that can affect driver braking behavior. Therefore, this study aims to investigate how driver braking behavior changes based on the information about the number of pedestrians in a crowd and examine if a developed warning system based on this information can induce safe braking behavior. For this purpose, an experiment scenario was conducted using a virtual reality-based driving simulator and an eye tracker. The collected driver data were analyzed using mixed ANOVA to derive meaningful conclusions. The research findings indicate that providing information about the number of pedestrians in a crowd has a positive impact on driver braking behavior, including deceleration, yielding intention, and attention. Particularly, It was found that in scenarios with a larger number of pedestrians, the Time to Collision (TTC) and distance to the crosswalk were increased by 12%, and the pupil diameter was increased by 9%. This research also verified the applicability of the proposed warning system in complex road environments, especially under conditions with poor visibility such as nighttime. The system was able to induce safe braking behavior even at night and exhibited consistent performance regardless of gender. In conclusion, considering various factors that influence driver behavior, this research provides a comprehensive understanding of the potential and effectiveness of a driver warning system based on information about the number of pedestrians in a crowd in complex road environments.
Tsunami Warning and Preparedness National Research Council; Division on Earth and Life Studies; Ocean Studies Board ...
04/2011
eBook
Odprti dostop
Many coastal areas of the United States are at risk for tsunamis. After the catastrophic 2004 tsunami in the Indian Ocean, legislation was passed to expand U.S. tsunami warning capabilities. Since ...then, the nation has made progress in several related areas on both the federal and state levels. At the federal level, NOAA has improved the ability to detect and forecast tsunamis by expanding the sensor network. Other federal and state activities to increase tsunami safety include: improvements to tsunami hazard and evacuation maps for many coastal communities; vulnerability assessments of some coastal populations in several states; and new efforts to increase public awareness of the hazard and how to respond.
Tsunami Warning and Preparedness explores the advances made in tsunami detection and preparedness, and identifies the challenges that still remain. The book describes areas of research and development that would improve tsunami education, preparation, and detection, especially with tsunamis that arrive less than an hour after the triggering event. It asserts that seamless coordination between the two Tsunami Warning Centers and clear communications to local officials and the public could create a timely and effective response to coastal communities facing a pending tsuanami.
According to Tsunami Warning and Preparedness , minimizing future losses to the nation from tsunamis requires persistent progress across the broad spectrum of efforts including: risk assessment, public education, government coordination, detection and forecasting, and warning-center operations. The book also suggests designing effective interagency exercises, using professional emergency-management standards to prepare communities, and prioritizing funding based on tsunami risk.
This paper presents an innovative Early Warning System for predicting conflicts and unrest based on Anomaly Detection, identifying sudden and unexpected changes in behavioral patterns that may ...indicate the potential for these events to occur. This approach draws inspiration from various fields – including industry, such as manufacturing, physics and networking – but its application in the domain of diplomacy is entirely new. The system, tested on three case studies, showcase its ability to enhance open-source intelligence technique in the diplomatic arena. The study provides a fresh perspective on predictive analytics and focuses on examining outbreaks.
•The early warning system presented utilizes autoencoder models for anomaly detection to predict conflict and disruption.•Combines ACLED and GDELT datasets for comprehensive conflict analysis.•Tested on three case studies, the system demonstrated high accuracy, with AUC scores ranging from 86.6% to 93.7%.•Prioritizes the identification of sudden outbreaks over precise numerical predictions.•While promising, the method acknowledges the need for rigorous assessment and adaptation to different geopolitical contexts.
Air pollution poses a substantial threat to society and is considered one of the greatest environmental hazards for human beings. It is of great importance to develop air pollution early warning ...systems to alleviate the urgency and necessity of air quality monitoring and analysis. However, current early warning systems rarely focus on mining of pollutant characteristics and their corresponding scientific evaluation. In this study, we investigate an innovative hybrid air quality early warning system that comprises characteristics estimation, prediction, and evaluation. First, four different distribution functions with two estimation methods were applied for quarrying the characteristics of pollutants; Afterward, a hybrid forecasting model was proposed combined with an advanced data processing technique—a neural network and a new heuristic algorithm. For further mining the features of pollutants, two interval approaches as well as Extenics evaluation were utilized as indispensable components of the developed system. Simulation of pollutants series, including PM2.5, SO2, NO2, CO, and O3 are in line with lognormal distribution using certain parameters, and forecasting results are in good accordance with the empirical data using multiple criterion systems, i.e., MAE, MSE, RMSE, MAPE, MdAPE, FB, DA, and R2 for deterministic forecasting and with IFCP and IFNAW for interval forecasting. Eight deterministic forecasting criterion for pollutants forecasting measurement indicate that the developed early warning system can achieve good performance in terms of its accuracy and effectiveness. Additionally, the positive interval forecasting results and good precision of Extenics evaluation indicate the efficiency and scalability of the designed early warning system.
•A hybrid early-warning system is developed for pollutants analysis and prediction.•Distribution estimating is employed to mine characteristics of pollutants.•A predictor named ICEEMDAN-ICA-BPNN is proposed for deterministic and uncertainty prediction.•Extenics evaluation is used for air quality assessment.
•Adapting three machine/deep learning models to predict rice yield at county-level•LSTM performs better than RF and LASSO models•Combining EVI and SIF together improves yield prediction than using ...EVI or SIF•Develop a scalable, simple and inexpensive framework for timely predicting rice yield•The yield prediction framework use publicly available multi-source data
Timely and reliable yield prediction at a large scale is imperative and prerequisite to prevent climate risk and ensure food security, especially with climate change and increasing extreme climate events. In this study, integrating the publicly available data (i.e., satellite vegetation indexes, meteorological indexes, and soil properties) within the Google Earth Engine (GEE) platform, we developed one Least Absolute Shrinkage and Selection Operator (LASSO) regression, one machine learning (Random Forest, RF), and one deep learning (Long Short-Term Memory Networks, LSTM) model to predict rice yield at county-level across China. For satellite data, we compared the contiguous solar-induced chlorophyll fluorescence (SIF), a newly emerging satellite retrieval, with a traditional vegetation index (enhanced vegetation index, EVI). The results showed that LSTM (with R2 ranging from 0.77 to 0.87, RMSE from 298.11 to 724kg/ha) and RF (with R2 ranging from 0.76 to 0.82, RMSE from 366 to 723.3 kg/ha) models outperformed LASSO (with R2 ranging from 0.33 to 0.42, RMSE from 633.46 kg/ha to 1231.39 kg/ha) in yield prediction; and LSTM was better than RF. Besides, ESI (combining EVI and SIF together) could slightly improve the model performance compared with only using EVI or SIF as the single input, primarily due to the ability of satellite-based SIF in capturing extra information on drought and heat stress. Furthermore, we also explored the potential for timely rice yield prediction, and concluded that the optimal prediction could be achieved with approximately two/one-month leading-time before single/double rice maturity. Our findings demonstrated a scalable, simple and inexpensive methods for timely predicting rice yield over a large area with publicly available multi-source data, which can potentially be applied to areas with sparsely observed data and worldwide for estimating crop yields.