Search

BACKGROUND: About one-third of older adults aged 65 years and older often have mild cognitive impairment or dementia. Acoustic and psycho-linguistic features derived from conversation may be of great diagnostic value because speech involves verbal memory and cognitive and neuromuscular processes. The relative decline in these processes, however, may not be linear and remains understudied. OBJECTIVE: This study aims to establish associations between cognitive abilities and various attributes of speech and natural language production. To date, the majority of research has been cross-sectional, relying mostly on data from structured interactions and restricted to textual versus acoustic analyses. METHODS: In a sample of 71 older (mean age 83.3, SD 7.0 years) community-dwelling adults who completed qualitative interviews and cognitive testing, we investigated the performance of both acoustic and psycholinguistic features associated with cognitive deficits contemporaneously and at a 1-2 years follow up (mean follow-up time 512.3, SD 84.5 days). RESULTS: Combined acoustic and psycholinguistic features achieved high performance (F1-scores 0.73-0.86) and sensitivity (up to 0.90) in estimating cognitive deficits across multiple domains. Performance remained high when acoustic and psycholinguistic features were used to predict follow-up cognitive performance. The psycholinguistic features that were most successful at classifying high cognitive impairment reflected vocabulary richness, the quantity of speech produced, and the fragmentation of speech, whereas the analogous top-ranked acoustic features reflected breathing and nonverbal vocalizations such as giggles or laughter. CONCLUSIONS: These results suggest that both acoustic and psycholinguistic features extracted from qualitative interviews may be reliable markers of cognitive deficits in late life.

The purpose of this paper is to improve the fault early warning effect of smart grid equipment through multi-sensor information fusion technology. Therefore, based on the analytical model of power grid fault diagnosis, this paper considers the influence of distributed generation in distribution network on fault diagnosis, as well as the misoperation or refusal of protection and switch, and the false alarm or leakage of alarm signal. At the same time, in order to display the results of fault diagnosis accurately and intuitively, an analytical model of fault diagnosis of distribution network based on multi-source information fusion is proposed. Finally, this paper verifies the effectiveness of this method through an example application. This article uses the PEDL dataset for experimental research, Through the comparison of fault data, it can be seen that compared with existing methods, the method proposed in this paper achieves the highest goodness of fit for warning, indicating the best fault warning effect.When there is enough training set, the prediction accuracy of the fault set can reach over 99%, Based on experimental analysis, it can be concluded that the proposed power grid equipment model has higher accuracy and reliability compared to traditional models. And the model in this article integrates the real-time monitoring function of power grid equipment and the equipment fault warning function, which improves the practicality of the power grid equipment monitoring system. [ABSTRACT FROM AUTHOR]

With the increasing penetration of renewable energy in power system, renewable energy power ramp events (REPREs), dominated by wind power and photovoltaic power, pose significant threats to the secure and stable operation of power systems. This paper presents an early warning method for REPREs based on long short-term memory (LSTM) network and fuzzy logic. First, the warning levels of REPREs are defined by assessing the control costs of various power control measures. Then, the next 4-h power support capability of external grid is estimated by a tie line power prediction model, which is constructed based on the LSTM network. Finally, considering the risk attitudes of dispatchers, fuzzy rules are employed to address the boundary value attribution of the early warning interval, improving the rationality of power ramp event early warning. Simulation results demonstrate that the proposed method can generate reasonable early warning levels for REPREs, guiding decision-making for control strategy. [ABSTRACT FROM AUTHOR]

Background: Adverse events in psychiatric settings present ongoing challenges for both patients and staff. Despite advances in psychiatric interventions and treatments, research on early warning scores and tools to predict patient deterioration is limited. This review provides a summary of the few tools that have been developed in a psychiatric setting, comparing machine learning (ML) and nonmachine learning/traditional methodologies. The outcomes of interest include the selected key variables that contribute to adverse events and the performance and validation measures of the predictive models. Methods: Three databases, Ovid MEDLINE, PsycINFO, and Embase, were searched between February 2023 and April 2023 to identify all relevant studies that included a combination of (and were not limited to) the following search terms: "Early warning," "Alerting tool," and "Psychiatry". Peer-reviewed primary research publications were included without imposing any date restrictions. A total of 1,193 studies were screened. A total of 9 studies met the inclusion and exclusion criteria and were included in this review. The PICOS model, the Joanna Briggs Institute (JBI) Reviewer's Manual, and PRISMA guidelines were applied. Results: This review identified nine studies that developed predictive models for adverse events in psychiatric settings. Encompassing 41,566 participants across studies that used both ML and non-ML algorithmic approaches, performance metrics, primarily AUC ROC, varied among studies between 0.62 and 0.95. The best performing model that had also been validated was the random forest (RF) ML model, with a score of 0.87 and a high sensitivity of 74% and a specificity of 88%. Conclusion: Currently, few predictive models have been developed for adverse events and patient deterioration in psychiatric settings. The findings of this review suggest that the use of ML and non-ML algorithms show moderate to good performance in predicting adverse events at the hospitals/units where the tool was developed. Understanding these models and the methodology of the studies is crucial for enhancing patient care as well as staff and patient safety research. Further research on the development and implementation of predictive tools in psychiatry should be carried out to assess the feasibility and efficacy of the tool in psychiatric patients. [ABSTRACT FROM AUTHOR]

AbstractRecent studies have shown that United Nations (UN) peacekeepers are deployed to active conflict zones and are effective in reducing violence against civilians and between armed actors. Yet, while existing research has explored where peacekeepers are initially deployed, we know less about where peacekeepers patrol after deployment in which existing evidence remains largely anecdotal. We contend that UN peacekeeping patrols are generally conducted in areas where they are most needed in areas of armed violence and where civilians are targeted as UN peacekeepers are mandated to anticipate and respond to violence. We assess this argument using unique, geocoded mission report data compiled by the Joint Mission Analysis Center (JMAC) on UNAMID patrols across Darfur between January 2008 and April 2009. We find that, while UN patrols often stayed closer to the base, many patrols did venture far from base into the “sea of instability,” in locations with armed clashes and civilian violence. [ABSTRACT FROM AUTHOR]

Effective use of the wealth of information provided by Distributed Acoustic Sensing (DAS) for mass movement monitoring remains a challenge. We propose a semi‐supervised neural network tailored to screen DAS data related to a series of rock collapses leading to a major failure of approximately 1.2 million m3 ${\mathrm{m}}^{3}$ on 15 June 2023 in Brienz, Eastern Switzerland. Besides DAS, the dataset from 16 May to 30 June 2023 includes Doppler radar data for partially ground‐truth labeling. The proposed algorithm is capable of distinguishing between rock‐slope failures and background noise, including road and train traffic, with a detection precision of over 95% $95\%$. It identifies hundreds of precursory failures and shows sustained detection hours before and during the major collapse. Event size and signal‐to‐noise ratio (SNR) are the key performance dependencies. As a critical part of our algorithm operates unsupervised, we suggest that it is suitable for general monitoring of natural hazards. Plain Language Summary: Steep mountains and hills produce dangerous rockfalls and similar phenomena such as landslides and debris flows. A major collapse is typically preceded by a series of rockfalls over days or months. It is therefore crucial to reliably detect these events and recognize the warning signs of an impending major collapse. When rocks bounce on the ground they release seismic waves, which generate vibrations that propagate long distances. Such vibrations stretch and compress fiber optic cables within the ground enough so they can be measured with a novel technique called Distributed Acoustic Sensing (DAS). Here we show how to identify such DAS signals using machine learning algorithms to detect precursory rockfall activity and a major collapse on a slope in Switzerland. We compare our detections with radar measurements, which are highly reliable but also come at a greater cost for installation. Since we can apply DAS to unused fiber within the ground, our approach may pave the way for the next generation of natural hazard warning. Key Points: A semi‐supervised neural network is developed for rock‐slope failure monitoring with Distributed Acoustic Sensing at Brienz, SwitzerlandOur model achieves over 95% precision for rock slope failures detected by a Doppler radar system over 45 daysThe sustained detection of slope failures before the major collapse highlights the potential of our approach for early warning [ABSTRACT FROM AUTHOR]

This article explores the recent history of early warning systems in Kenya, determining key features of the entangled political, technical and conceptual processes that prefigure contemporary drought management there. In doing so, it draws out wider implications regarding drought and anticipatory action across Africa's drylands, considering the friction between the dynamics of disaster risk management that structure formal early warning systems and those that shape pastoralist engagements with the volatile and uncertain worlds they inhabit. Surveying recent literature on pastoralism's unique relationship with uncertainty, and associated forms of networked, relational resilience, it reflects on some of the inherent limitations of current approaches to "local knowledge" in the humanitarian sphere. In doing so, it emphasises the need for new, creative approaches to early warning and anticipatory action, which are not merely established via the external synthesis of data but are rather oriented around local pastoralist drought preparation and mitigation strategies and comprise enough flexibility to adapt to a fast-shifting terrain of challenges and possibilities. [ABSTRACT FROM AUTHOR]

The purpose of this research was to analyze the performance of pupils (N = 6,023) who took part in Reading Recovery (RR) in England on a decoding test, the Phonics Screening Check (PSC), administered at the end of Year 1 when children are approximately 5 to 6 years of age. The data cover two academic years (2015/2016 and 2016/2017) and include demographic information, pre- and post-intervention achievement test scores and PSC results. Descriptive statistics and linear regression modeling (using a linear spline specification for timing) were used. Results indicated that pupils who had an RR intervention before the PSC performed better than peers who had the intervention during or after the PSC. There was a positive and statistically significant increase in PSC performance among those whose RR intervention began earlier relative to the PSC. [ABSTRACT FROM AUTHOR]

Background: Tsunami caused by volcanic collapse are categorized as non-seismic uncommon events, unlike tsunamis caused by earthquakes, which are common events. The traditional tsunami early warning based on the seismic sensor (e.g. earthquake detectors) may not be applicable to volcanic tsunamis because they do not generate seismic waves. Consequently, these tsunamis cannot be detected in advance, and warnings cannot be issued. New methods should be explored to address these non-seismic tsunamis caused by volcanic collapse. Objective: This study explored the potential of machine learning algorithms in supporting early warning level issuing for nonseismic tsunamis, specifically volcanic tsunamis. The Anak Krakatau volcano event in Indonesia was used as a case study. Methods: This study generated a database of 160 collapse scenarios using numerical simulation as input sequences. A classification model was constructed by defining the worst tsunami elevation and its arrival time at the coast. The database was supervised by labeling the warning levels as targets. Subsequently, a decision tree algorithm was employed to classify the warning levels. Results: The results demonstrated that the classification model performs very well for the Major Tsunami, Minor Tsunami, and Tsunami classes, achieving high precision, recall, and F1-Score with very high accuracy of 98%. However, the macro average indicates uneven performance across classes, as there are instances of 'No Warning' in some coastal gauges. Conclusion: To improve the model performance in the 'No Warning' class, it is necessary to balance the dataset by including more 'No Warning' scenarios, which can be achieved by simulating additional scenarios involving very small-volume collapse. Additionally, exploring additional collapse parameters such as dip angle and outlier volume could contribute to developing a more robust classification model. [ABSTRACT FROM AUTHOR]

Landslides are highly destructive geological disasters, often preceded by changes in surface displacement. This study explores the effectiveness of real aperture radar (RAR) in landslide monitoring and early warning. Using the three-stage creep theory, the short-term simple moving average velocity (SMA) and long-term simple moving average velocity (LMA) were used to determine the end point of the constant displacement stage, while the hypothesis test method was used to confirm its starting point. Based on these points, the average velocity was calculated. A five-level warning model and criteria were established by integrating acceleration, velocity change, and tangent angle. Three landslide cases in Northeast China were analyzed to evaluate the dynamic application of this model. The results indicate that: (1) RAR effectively identifies abnormal displacement region; (2) Successful warnings in the three cases validate the effectiveness of the warning model and criteria; (3) The five-level warning model and criteria of RAR demonstrate strong application potential in the dynamic monitoring and early warning of landslide disasters. [ABSTRACT FROM AUTHOR]

This paper systematically reviews the behavior of numerical indicators in predicting future bankruptcy of companies through statistical analysis models. Following the PRISMA standard, ten primary studies were included in the review. The obtained results underline (1) the ability of numerical indicators, through simple statistical analysis models, to forecast the bankruptcy of businesses and companies and (2) the reliability of cash flows in predicting financial distress through statistical analysis, and (3) models are built with indicators from a specific economy; it is impossible to consider them stable and unchanging, as changes in a country's economic conditions can potentially impact their predictive accuracy. [ABSTRACT FROM AUTHOR]

As the fleet of high-speed rail vehicles expands, ensuring train safety is of the utmost importance, emphasizing the critical need to enhance the precision of axel temperature warning systems. Yet, the limited availability of data on the unique features of high thermal axis temperature conditions in railway systems hinders the optimal performance of intelligent algorithms in alarm detection models. To address these challenges, this study introduces a novel dynamic principal component analysis preprocessing technique for tolerance temperature data to effectively manage missing data and outliers. Furthermore, a customized generative adversarial network is devised to generate distinct data related to high thermal axis temperature, focusing on optimizing the network's objective functions and distinctions to bolster the efficiency and diversity of the generated data. Finally, an integrated model with an optimized transformer module is established to accurately classify alarm levels, provide a comprehensive solution to pressing train safety issues, and, in a timely manner, notify drivers and maintenance departments (DEPOs) of high-temperature warnings. [ABSTRACT FROM AUTHOR]

During the COVID-19 pandemic, wastewater surveillance was used to monitor community transmission of SARS-CoV-2. As new genetic variants emerged, the need for timely identification of these variants in wastewater became an important focus. In response to increased reports of Omicron transmission across the United States, the Oklahoma Wastewater Surveillance team utilized allele-specific RT-qPCR assays to detect and differentiate variants, such as Omicron, from other variants found in wastewater in Oklahoma. The PCR assays showed presence of the Omicron variant in Oklahoma on average two weeks before official reports, which was confirmed through genomic sequencing of selected wastewater samples. Through continued surveillance from November 2021 to January 2022, we also demonstrated the transition from prevalence of the Delta variant to prevalence of the Omicron variant in local communities. We further assessed how this transition correlated with certain demographic factors characterizing each community. Our results highlight RT-qPCR assays as a rapid, simple, and cost-effective method for monitoring the community spread of SARS-CoV-2 genetic variants in wastewater. Additionally, they demonstrate that specific demographic factors such as ethnic composition and household income can correlate with the timing of SARS-CoV-2 variant introduction and spread. [ABSTRACT FROM AUTHOR]

Background: It is difficult to detect the outbreak of emergency infectious disease based on the exiting surveillance system. Here we investigate the utility of the Baidu Search Index, an indicator of how large of a keyword is in Baidu's search volume, in the early warning and predicting the epidemic trend of COVID-19. Methods: The daily number of cases and the Baidu Search Index of 8 keywords (weighted by population) from December 1, 2019 to March 15, 2020 were collected and analyzed with times series and Spearman correlation with different time lag. To predict the daily number of COVID-19 cases using the Baidu Search Index, Zero-inflated negative binomial regression was used in phase 1 and negative binomial regression model was used in phase 2 and phase 3 based on the characteristic of independent variable. Results: The Baidu Search Index of all keywords in Wuhan was significantly higher than Hubei (excluded Wuhan) and China (excluded Hubei). Before the causative pathogen was identified, the search volume of "Influenza" and "Pneumonia" in Wuhan increased with the number of new onset cases, their correlation coefficient was 0.69 and 0.59, respectively. After the pathogen was public but before COVID-19 was classified as a notifiable disease, the search volume of "SARS", "Pneumonia", "Coronavirus" in all study areas increased with the number of new onset cases with the correlation coefficient was 0.69 ~ 0.89, while "Influenza" changed to negative correlated (rs: -0.56 ~ -0.64). After COVID-19 was closely monitored, the Baidu Search Index of "COVID-19", "Pneumonia", "Coronavirus", "SARS" and "Mask" could predict the epidemic trend with 15 days, 5 days and 6 days lead time, respectively in Wuhan, Hubei (excluded Wuhan) and China (excluded Hubei). The predicted number of cases would increase 1.84 and 4.81 folds, respectively than the actual number of cases in Wuhan and Hubei (excluded Wuhan) from 21 January to 9 February. Conclusion: The Baidu Search Index could be used in the early warning and predicting the epidemic trend of COVID-19, but the search keywords changed in different period. Considering the time lag from onset to diagnosis, especially in the areas with medical resources shortage, internet search data can be a highly effective supplement of the existing surveillance system. [ABSTRACT FROM AUTHOR]

Simple Summary: Mercury represent a serious threat for marine ecosystems due to its persistence in the environment. Fishes are the most numerous and widely distributed group of vertebrates, living in the sea with different species often studied and used as bioindicators of the quality of aquatic systems being able to reflect even small changes in environmental parameters. Mitochondria are small cell organelles with their own DNA and the number of mitochondria within a cell is highly variable in different animal tissues, depending on metabolic requirements. Mitochondrial genome is vulnerable to reactive oxygen species (ROS) which in turn impair mitochondrial function. Therefore, the aim of the present study was the validation of the variation in the number of mitochondrial DNA copies (mtDNAcn) as biomarker of oxidative stress in aquatic environment. Three selected fish species were collected in Augusta Bay, a contaminated area remarkable by past Hg inputs, and in a control area (Marzamemi and Portopalo di Capo Passero), both in the South-East of Sicily. Based on the evidence found, the assessment of mtDNAcn variation emerges as a valid biomarker of oxidative stress deriving from contaminant exposure. Mercury (Hg) pro-oxidant role on biological systems and its biogeochemical cycle represent a serious threat due to its persistence in marine environment. As the mitochondrial genome is exposed to reactive oxygen species (ROS), the aim of the present study is the validation of the variation in the number of mitochondrial DNA copies (mtDNAcn) as biomarker of oxidative stress in aquatic environment. During summer 2021, three selected fish species (Mullus barbatus, Diplodus annularis and Pagellus erythrinus) were collected in Augusta Bay, one of the most Mediterranean contaminated areas remarkable by past Hg inputs, and in a control area, both in the south-east of Sicily. The relative mtDNAcn was evaluated by qPCR on specimens of each species from both sites, characterized respectively by higher and lower Hg bioaccumulation. M. barbatus and P. erythrinus collected in Augusta showed a dramatic mtDNAcn reduction compared to their control groups while D. annularis showed an incredible mtDNAcn rising suggesting a higher resilience of this species. These results align with the mitochondrial dynamics of fission and fusion triggered by environmental toxicants. In conclusion, we suggest the implementation of the mtDNAcn variation as a valid tool for the early warning stress-related impacts in aquatic system. [ABSTRACT FROM AUTHOR]

A common and largely unresolved problem of national-scale landslide early warning systems is their independent evaluation. In a recent paper, Mondini et al. (Nat Commun 14:2466, 2023) proposed a deep-learning system for short-term forecasting of rain-induced shallow landslides in Italy. Here, we independently evaluate the performance of this national-scale system by demonstrating its application between 1 January and 31 May 2021. For the purpose, we use hourly rainfall measurements from the same rain gauge network and different and independent information on the timing and location of 163 rain-induced landslides obtained from the FraneItalia catalogue that occurred in Italy in a period non considered in the construction of the system (https://zenodo.org/records/7923683). Independent demonstration confirmed the good predictive performance of the forecasting system and revealed no geographical or temporal bias in the forecasts. The analysis also showed that the system was more effective at predicting multiple landslides in the same general area than single landslides. This was a good result as multiple landslides are inherently more dangerous than single failures. Analysis of the few misclassified landslides showed that approximately one-third of the landslides were rockfalls, and for approximately another third there was uncertainty about when or where the landslides occurred. We conclude that, despite the inevitable misclassifications inherent in any probabilistically based national-scale landslide forecasting system, the deep-learning system analysed is well suited for short-term operational forecasting of rain-induced shallow landslides in Italy. [ABSTRACT FROM AUTHOR]

Determining the magnitude of an earthquake rapidly and correctly is essential to starting simulations to evaluate the potential for tsunami generation and early warning for tsunami-prone countries and rapid response, considering countries that lie in seismically active regions. Although the UK does not have a high degree of tsunami hazard, the UK seismic network can estimate the moment magnitude for large earthquakes which will occur around the globe. This study aimed to test the UK Seismological Network Broadband Seismic Stations to calculate the P-wave moment magnitude (Mwp) using teleseismic waves. The standard way to calculate the Mwp is using the P-wave portion of a seismic wave recorded at different epicentral distances. We selected twenty-five seismic events with a magnitude greater than 6.5Mw and epicentral distances between 17 and 90 degrees. The main issue is selecting the P-wave portion of a seismic wave and using a trial P-wave velocity to estimate the Mwp. We simplified the selection of a P-wave portion of seismic waves using a theoretical formula that works with epicentral distance, P-wave arrival time and an apparent P-wave velocity, which calculates the S-wave arrival time. The results show the variation between the Harvard centroid moment tensor (CMT—Mw) and Mwp, which is about ± 0.1 magnitude units in most events and ± 0.2 for some events. These results prove the Mwp technique can be applied to the UK broadband seismic network broadband seismic stations and encourage the use of it immediately following a destructive earthquake anywhere in the world. [ABSTRACT FROM AUTHOR]

The establishment of an accurate early warning and intervention mechanism for re-poverty (i.e., returning to poverty) is a valuable tool for consolidating the achievements of the Chinese government in poverty alleviation and the effective connection with rural revitalization since completing the task of eliminating absolute poverty. The occurrence of the re-poverty phenomenon is closely related to the vulnerability characteristics of the subject. This paper constructs a vulnerability to re-poverty analysis framework that integrate regional and household perspectives based on "capital-capacity-welfare". Zherong County was selected as the case study where the vulnerability assessment model and GeoDetector were adopted to undertake an early warning and Interactive detection analysis respectively. The results show that: (1) The degree of vulnerability to re-poverty of most townships and households in Zherong County is relatively low after the withdrawal of absolute poverty; (2) At the regional level, among 9 townships of Zherong county, the social welfare is more vulnerable than geographical capital and economic capacity, and the degree of vulnerability to re-poverty of Fuxi and Zhayang are relatively high, with warning level III; (3) Among the 737 low-income households registered, 98.4% of them aligned with warning level I and II, only 1.6% of them aligned with warning level III. However, households' livelihood capital vulnerability is generally relatively high, and the improvement of household self-development motivation is still insufficient; (4) Household vulnerability to re-poverty is influenced by both regional and household factors, and the interaction between the two factors can enhance each other's explanatory power to HVRI. We divided the risk into four types and proposed corresponding policy implications based on the coupling of regional and household vulnerability to re-poverty early warning. [ABSTRACT FROM AUTHOR]

As the preferred technology in the current energy storage field, lithium-ion batteries cannot completely eliminate the occurrence of thermal runaway (TR) accidents. It is of significant importance to employ real-time monitoring and warning methods to perceive the battery's safety status promptly and address potential safety hazards. Currently, the monitoring and warning of lithium-ion battery TR heavily rely on the judgment of single parameters, leading to a high false alarm rate. The application of multi-parameter early warning methods based on data fusion remains underutilized. To address this issue, the evaluation of lithium-ion battery safety status was conducted using the cloud model to characterize fuzziness and Dempster–Shafer (DS) evidence theory for evidence fusion, comprehensively assessing the TR risk level. The research determined warning threshold ranges and risk levels by monitoring voltage, temperature, and gas indicators during lithium-ion battery overcharge TR experiments. Subsequently, a multi-parameter fusion approach combining cloud model and DS evidence theory was utilized to confirm the risk status of the battery at any given moment. This method takes into account the fuzziness and uncertainty among multiple parameters, enabling an objective assessment of the TR risk level of lithium-ion batteries. [ABSTRACT FROM AUTHOR]

Abstract Wastewater-based epidemiological surveillance has proven to be a useful and cost-effective tool for detecting COVID-19 outbreaks. Here, our objective was to evaluate its potential as an early warning system in Venezuela by detecting SARS-CoV-2 RNA in wastewater and its correlation with reported cases of COVID-19. Viral RNA was concentrated from wastewater collected at various sites in Caracas (northern Venezuela), from September 2021 to July 2023, using the polyethylene glycol (PEG) precipitation method. Viral quantification was performed by RT-qPCR targeting the N1 and ORF1ab genes. A significant association (p

Abstract Background Adverse events in psychiatric settings present ongoing challenges for both patients and staff. Despite advances in psychiatric interventions and treatments, research on early warning scores and tools to predict patient deterioration is limited. This review provides a summary of the few tools that have been developed in a psychiatric setting, comparing machine learning (ML) and nonmachine learning/traditional methodologies. The outcomes of interest include the selected key variables that contribute to adverse events and the performance and validation measures of the predictive models. Methods Three databases, Ovid MEDLINE, PsycINFO, and Embase, were searched between February 2023 and April 2023 to identify all relevant studies that included a combination of (and were not limited to) the following search terms: "Early warning," "Alerting tool," and "Psychiatry". Peer-reviewed primary research publications were included without imposing any date restrictions. A total of 1,193 studies were screened. A total of 9 studies met the inclusion and exclusion criteria and were included in this review. The PICOS model, the Joanna Briggs Institute (JBI) Reviewer's Manual, and PRISMA guidelines were applied. Results This review identified nine studies that developed predictive models for adverse events in psychiatric settings. Encompassing 41,566 participants across studies that used both ML and non-ML algorithmic approaches, performance metrics, primarily AUC ROC, varied among studies between 0.62 and 0.95. The best performing model that had also been validated was the random forest (RF) ML model, with a score of 0.87 and a high sensitivity of 74% and a specificity of 88%. Conclusion Currently, few predictive models have been developed for adverse events and patient deterioration in psychiatric settings. The findings of this review suggest that the use of ML and non-ML algorithms show moderate to good performance in predicting adverse events at the hospitals/units where the tool was developed. Understanding these models and the methodology of the studies is crucial for enhancing patient care as well as staff and patient safety research. Further research on the development and implementation of predictive tools in psychiatry should be carried out to assess the feasibility and efficacy of the tool in psychiatric patients.

Abstract Background It is difficult to detect the outbreak of emergency infectious disease based on the exiting surveillance system. Here we investigate the utility of the Baidu Search Index, an indicator of how large of a keyword is in Baidu’s search volume, in the early warning and predicting the epidemic trend of COVID-19. Methods The daily number of cases and the Baidu Search Index of 8 keywords (weighted by population) from December 1, 2019 to March 15, 2020 were collected and analyzed with times series and Spearman correlation with different time lag. To predict the daily number of COVID-19 cases using the Baidu Search Index, Zero-inflated negative binomial regression was used in phase 1 and negative binomial regression model was used in phase 2 and phase 3 based on the characteristic of independent variable. Results The Baidu Search Index of all keywords in Wuhan was significantly higher than Hubei (excluded Wuhan) and China (excluded Hubei). Before the causative pathogen was identified, the search volume of “Influenza” and “Pneumonia” in Wuhan increased with the number of new onset cases, their correlation coefficient was 0.69 and 0.59, respectively. After the pathogen was public but before COVID-19 was classified as a notifiable disease, the search volume of “SARS”, “Pneumonia”, “Coronavirus” in all study areas increased with the number of new onset cases with the correlation coefficient was 0.69 ~ 0.89, while “Influenza” changed to negative correlated (rs: -0.56 ~ -0.64). After COVID-19 was closely monitored, the Baidu Search Index of “COVID-19”, “Pneumonia”, “Coronavirus”, “SARS” and “Mask” could predict the epidemic trend with 15 days, 5 days and 6 days lead time, respectively in Wuhan, Hubei (excluded Wuhan) and China (excluded Hubei). The predicted number of cases would increase 1.84 and 4.81 folds, respectively than the actual number of cases in Wuhan and Hubei (excluded Wuhan) from 21 January to 9 February. Conclusion The Baidu Search Index could be used in the early warning and predicting the epidemic trend of COVID-19, but the search keywords changed in different period. Considering the time lag from onset to diagnosis, especially in the areas with medical resources shortage, internet search data can be a highly effective supplement of the existing surveillance system.

Background Cardiovascular disease (CVD) is a major cause of human mortality worldwide, characterized by its insidious onset, intricate and variable course, and poor prognosis. Early identification and active intervention of potentially critically ill patients is essential to improve their prognosis. Objective To conduct a scoping review of the research on early warning assessment tools for cardiovascular disease risk at home and abroad, summarize and analyze their assessment content and application, ultimately providing reference for the selection of appropriate early warning tools for cardiovascular disease patients in China. Methods CNKI, Wanfang Data, VIP, CBM, PubMed, Web of Science, Cochrane Library, Embase, CINAHL, and Scopus were systematically searched from inception to May 2023. Two investigators independently screened literature and extracted data, analyzed in terms of assessment content, study subjects, validation method, reliability and validity, and predictive efficacy. Results A total of 16 papers were included, comprising 7 papers on the development and validation of assessment tools and 9 papers on the localized application of these tools, involving 20 early warning assessment tools for cardiovascular disease risk. The results of the analysis showed that each assessment tool contained 3 to 17 assessment items, with the most frequently mentioned items of age, systolic blood pressure, respiratory rate, oxygen saturation, heart rate, comorbidities, level of consciousness, and gender. The results of the reliability and validity tests for 2 papers indicated robust reliability and validity, while all other studies lacked reliability and validity evaluations. Ten papers reported the area under the curve (AUC), with values ranging from 0.550 to 0.926 9. Conclusion Diverse early warning assessment tools for cardiovascular disease risk are available, however, their overall quality remains to be improved and there is a lack of specific assessment tools. In the future, it is imperative to conduct further validations of the reliability and validity of the existing tools, and develop localized early warning assessment tools specialized for cardiovascular diseases considering the unique characteristics of the disease, which exhibit robust reliability and validity.

The phenomenon of coal spontaneous combustion poses a serious threat to mine safety, and monitoring and warning of coal spontaneous combustion has become an important issue that needs to be urgently addressed in coal mines. The current monitoring and early warning methods for coal spontaneous combustion have their limitations, and a single indicator cannot accurately mark the degree of coal spontaneous combustion danger inside the goaf. Therefore, this article proposes a new method for monitoring coal spontaneous combustion through infrasound waves. Infrasound waves have advantages such as low attenuation and long transmission distance. However, current research on monitoring and warning coal spontaneous combustion in goaf through infrasound waves is not yet complete, and there is a lack of research on the characteristics of infrasound signal changes during coal spontaneous combustion. Based on this, the article first tested the characteristic temperature and release changes of indicator gases (CO, C2H4) through thermogravimetric experiments and coal oxidation and heating experiments. Then, the generation and variation of infrasonic signals during coal spontaneous combustion (CSC) was studied and analyzed using a self-designed CSC infrasonic testing system. The results showed that obvious infrasound signals could be generated during the CSC process, there is a good mapping relationship between signals and temperature. Furthermore, the analysis revealed the inherent relationship between the infrasonic signal, temperature, and indicator gas of coal at different oxidation stages. The research in this article has promoted the use of infrasound waves for temperature inversion and promoted the development of multi-parameter analysis and early warning of CSC, which is of great significance for the field of CSC monitoring. [ABSTRACT FROM AUTHOR]

Maintaining safety is a fundamental goal in logistics infrastructure management. Current research on logistics infrastructure safety constructed assessment models without accounting for the catastrophe property of accidents. This research aims at developing an innovative methodology for assessing the safety of logistics infrastructure, which will consider catastrophe property of accident and providing early warning signals for managers and designers. The concept of Logistics Infrastructure Safety Carrying Capacity (LISC) is explored based on the perspective of carrying capacity. The carrier-load model is used to define logistics infrastructure safety. The evaluation of LISC performance employs the Catastrophe Progression Method (CPM) to determine the safety state of logistics infrastructure. By applying the LISC-CPM model to the empirical study of China's logistics infrastructure safety from 2011 to 2022, some conclusions are drawn: (1) The LISC-CPM method is suitable for logistics infrastructure safety monitoring. This model can combine the characteristics of different transportation modes and the catastrophe attributes of safety accidents for early safety warning; (2) Over a 12-year period, the early warning level for logistics infrastructure in China significantly improved, transitioning from "severe-level unsafe warning" to "safe." (3) There is considerable variation in safety performance across different types of logistics infrastructure. The safety of railway and waterway has the most significant influence on the safety of logistics infrastructure. In general, the study can provide valuable tools for enhancing the safety of logistics infrastructure. • Analyzed logistics infrastructure safety based on the perspective of carrying capacity. • Proposed a (Logistics infrastructure safety carrying capacity) LISC assessment method that considers catastrophe property of the accidents. • Obtained the hierarchical early warning of logistics infrastructure safety based on the proposed model measurements. [ABSTRACT FROM AUTHOR]

Landslides, as a common natural disaster, pose a significant threat to human society and the natural environment, including loss of life, economic damage, and environmental destruction. Effective landslide early warning is key to reducing these negative impacts. However, current warning methods face two major challenges: one is the reliance on static threshold judgments, which not only easily leads to false and missed alarms but also cannot adapt to complex and changing natural conditions. The second is the lack of ground data support in areas with complex terrain, which greatly limits the application range and accuracy of traditional warning methods. To overcome these challenges, this study designed an efficient processing system for Interferometric Synthetic Aperture Radar (InSAR) based on the (Artificial Intelligence) AI Earth Cloud platform, integrated with the Comprehensive Standardized Deformation Index (CSDI) approach, to provide an early warning analysis for the Zhenxiong landslide in Yunnan Province, China on January 22, 2024. Utilizing the cloud platform for rapid generation of deformation rates and selection of characteristic deformation points to reflect landslide trends, and applying the CSDI method for time-displacement curve analysis, enabled a fast and accurate landslide early warning. The research results show that the method proposed in this study can effectively warn of landslide events, significantly improving the accuracy and practicality of the warning. By combining InSAR technology with the CSDI model, this study not only addresses the challenges faced by traditional methods but also provides new insights and solutions in the field of landslide early warning, demonstrating the great potential of technological innovation in natural disaster management. [ABSTRACT FROM AUTHOR]

The occurrence of coal spontaneous combustion has a significant impact on both the safety of personnel and mine recovery. In order to establish an early warning system for combustion, it is crucial to develop a mathematical model that characterizes indicator gases and coal temperature. In this study, we investigated the O2, CO, and CO2 characteristics of data collected from a goaf beam pipe in the Mengcun mine. Our findings demonstrate a linear decrease in O2 concentration with goaf depth and a strong negative correlation between CO and O2. We observed that CO/∆O2 and CO/CO2 increased to a maximum and then decreased as the goaf depth increased. Furthermore, we found that the peaks of these parameters at the same sampling point corresponded to the same goaf depth, and both occurred at the junction between the air-leakage and oxidation zones. By using a logistic model to fit the CO and C2H4 data, we developed a model that characterizes the relationships among CO, C2H4, and coal temperature based on statistical laws. The model provides direct information about the inflection point temperatures of C2H4 and CO, with the former being slightly lower within the same coal sample. The overall difference between the inflection point temperatures is relatively small, about 10°C. The initial temperature ratio of C2H4 and CO remains essentially constant at 3.8. C2H2 concentrations are low and irregular, and the presence of this gas can be used to assess when coal enters the accelerated oxidation stage. This research result provides a new research view for elucidating the distribution characteristics of coal spontaneous combustion index gas. [ABSTRACT FROM AUTHOR]

Abstract To clarify the complex relationship between the factors causing safety accidents in metallurgical enterprises and predict the risk of accidents in enterprises, a correlation analysis model of the factors causing safety accidents in metallurgical enterprises based on grey Decision-Making Trial and Evaluation Laboratory/Interpretative Structural Modeling (DEMATEL/ISM) was established, and a Bayesian network early warning model was constructed on this basis. The relationship and action path of accident-causing factors in metallurgical enterprises were clarified. The factors were hierarchically divided and a multi-layer hierarchical structure model was established to obtain the neighboring cause, transitional cause, and essential cause of the accident. The results showed that the employee violation rate, the hazardous substances reserves, the toxic gas and dust pollution control compliance rate, the pass rate for equipment maintenance, and the qualification rate of special equipment were the neighboring causes of the accident. The perfection of the safety production management system was the essential cause. The Bayesian network early warning model was applied to the Fuxin Jiuxing Titanium work site. The expected risk probability of an accident was 17.9%, which was in a comparatively safe state (State2). The results obtained by the Bayesian model are consistent with those obtained by AHP and fuzzy comprehensive evaluation method, which proved the accuracy of the early warning model. The Bayesian model can give the risk probability value of the accident and the risk probability value of the accident cause factors at the same time, and include the causal relationship and conditional correlation relationship among the indicator variables in the reasoning process, which can provide targeted technical support for the construction of the emergency system of risk classification management and control.

As area surveillance technology, the camera is still suboptimal because it cannot detect suspicious human movement and there is no real-time security alert. Although motion detection is implemented, it is only activated when a person passes the PIR sensor, triggering the camera to capture the object. Due to its lengthy process, it is less effective. This study aims to develop a home surveillance system that uses object detection technology to detect unusual human movements. The system is also equipped with real-time early warning through a Telegram Messenger application. The system is then tested using various parameters that may impact the precision of detection results, including object poses, camera height, and camera distance. The system can detect objects that make unusual movements in 69 images or 57.5% of the tests, based on the analysis of 120 test data. Through the integration of object detection technology and real-time Telegram-based alerts, this home surveillance system significantly demonstrates the capability to accurately identify suspicious human motions thereby enhancing area surveillance effectiveness and adaptability to various environmental conditions.

Abstract Background Nosocomial infections with heavy disease burden are becoming a major threat to the health care system around the world. Through long-term, systematic, continuous data collection and analysis, Nosocomial infection surveillance (NIS) systems are constructed in each hospital; while these data are only used as real-time surveillance but fail to realize the prediction and early warning function. Study is to screen effective predictors from the routine NIS data, through integrating the multiple risk factors and Machine learning (ML) methods, and eventually realize the trend prediction and risk threshold of Incidence of Nosocomial infection (INI). Methods We selected two representative hospitals in southern and northern China, and collected NIS data from 2014 to 2021. Thirty-nine factors including hospital operation volume, nosocomial infection, antibacterial drug use and outdoor temperature data, etc. Five ML methods were used to fit the INI prediction model respectively, and to evaluate and compare their performance. Results Compared with other models, Random Forest showed the best performance (5-fold AUC = 0.983) in both hospitals, followed by Support Vector Machine. Among all the factors, 12 indicators were significantly different between high-risk and low-risk groups for INI (P

Currently, the digital transformation of the financial industry in China has moved from multiple breakthroughs into a new stage of deepening and high-quality development, which necessitates a collaborative governance mechanism that coordinates multiple parties including governments, enterprises, and individuals. In view of the new, complex, and potentially harmful financial risks arising in the context of digital transformation, the financial industry urgently needs to improve its financial risk monitoring and earlywarning capabilities to effectively protect financial security. This study analyzes the progress of digital transformation of the financial industry as well as the implications and characteristics of new financial risks through literature research and theoretical analysis. It also investigates the mainstream financial risk monitoring and early-warning technologies in China and abroad, and clarifies the prominent problems regarding risk characterization and recognition, transmission and tracking, and inference assessment. Furthermore, we propose the overall framework, innovative research methods, and improving paths for the financial risk monitoring and earlywarning system in the context of digital transformation. This study reveals that financial risks have new characteristics in the context of digital transformation, such as faster update and iteration, higher risk frequency, and stronger concealment. Existing financial risk monitoring and early-warning technologies have numerous deficiencies and face multiple challenges in dealing with new financial risks, such as difficulty in characterizing, tracking, and assessing risks. Therefore, to improve the financial risk prevention capability of China and guarantee national financial security, it is proposed to develop cross-industry sharing standards for financial data, establish a knowledge representation paradigm and a cross-industry transmission mechanism of financial risks, and build a large model regarding financial risk monitoring and early warning.

The outbreak and scale of harmful algal blooms (HABs) have been on the rise in recent years, mainly attributed to the effects of worsening seawater eutrophication and climate-change-related temperature increases. Yet, current approaches for detecting HABs fail to meet the requirements of rapid qualification and on-site quantification of the algae species and early warning of the outbreaks. Herein, an electrochemical biosensor based on In2O3/NC/Au NP nanomaterials was developed for the dynamic detection of Skeletonema costatum (S. costatum), one of the typical HABs. Specifically, the biosensor demonstrated a lower limit of detection (LOD, 671 fg/μL or 3528 cells/L) and had been confirmed to be accurate and reliable when compared to droplet digital PCR (ddPCR) and traditional microscope techniques. Moreover, for actual sample analysis, the concentrations of S. costatum were determined as 3.8 × 103 to 2.1 × 105 cells/L by the biosensor, which demonstrated a lower risk of S. costatum bloom outbreak in the sampling region and was consistent with the standard survey method. Therefore, the biosensor has great potential in the early stage qualitative analysis and on-site quantification of S. costatum and serves as an ideal warning technology of HAB outbreaks. [ABSTRACT FROM AUTHOR]

Wastewater-based surveillance has emerged as an important method for monitoring the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). This study investigated the presence of SARS-CoV-2 in wastewater in Zambia. We conducted a longitudinal study in the Copperbelt and Eastern provinces of Zambia from October 2023 to December 2023 during which 155 wastewater samples were collected. The samples were subjected to three different concentration methods, namely bag-mediated filtration, skimmed milk flocculation, and polythene glycol-based concentration assays. Molecular detection of SARS-CoV-2 nucleic acid was conducted using real-time Polymerase Chain Reaction (PCR). Whole genome sequencing was conducted using Illumina COVIDSEQ assay. Of the 155 wastewater samples, 62 (40%) tested positive for SARS-CoV-2. Of these, 13 sequences of sufficient length to determine SARS-CoV-2 lineages were obtained and 2 sequences were phylogenetically analyzed. Various Omicron subvariants were detected in wastewater including BA.5, XBB.1.45, BA.2.86, and JN.1. Some of these subvariants have been detected in clinical cases in Zambia. Interestingly, phylogenetic analysis positioned a sequence from the Copperbelt Province in the B.1.1.529 clade, suggesting that earlier Omicron variants detected in late 2021 could still be circulating and may not have been wholly replaced by newer subvariants. This study stresses the need for integrating wastewater surveillance of SARS-CoV-2 into mainstream strategies for monitoring SARS-CoV-2 circulation in Zambia. [ABSTRACT FROM AUTHOR]

It is essential in the protection of public health to monitor diseases and have an early warning system. However, current early warning systems have limitations, such as low accuracy and the speed of an early warning. This study used experimental research to compare the early warning performance of random forest early warnings and traditional early warnings, including early warning accuracy and warning time. Experimental research approach was used to compare early warning performance involving early warning accuracy and warning time of random forest early warning and traditional early warning. The experimental group used the random forest system, and the control group used the traditional early warning. The group recorded the early warnings of the experimental group and compared them to the control group early warnings. The experiment results showed the early warning accuracy of the experimental group used random forests early warning were 94-99% from the 4th to the 15th round. The highest early warning was 99%. The experimental group reached an early warning accuracy as well as fast early warning that was higher and stronger than the traditional method. [ABSTRACT FROM AUTHOR]

To clarify the complex relationship between the factors causing safety accidents in metallurgical enterprises and predict the risk of accidents in enterprises, a correlation analysis model of the factors causing safety accidents in metallurgical enterprises based on grey Decision-Making Trial and Evaluation Laboratory/Interpretative Structural Modeling (DEMATEL/ISM) was established, and a Bayesian network early warning model was constructed on this basis. The relationship and action path of accident-causing factors in metallurgical enterprises were clarified. The factors were hierarchically divided and a multi-layer hierarchical structure model was established to obtain the neighboring cause, transitional cause, and essential cause of the accident. The results showed that the employee violation rate, the hazardous substances reserves, the toxic gas and dust pollution control compliance rate, the pass rate for equipment maintenance, and the qualification rate of special equipment were the neighboring causes of the accident. The perfection of the safety production management system was the essential cause. The Bayesian network early warning model was applied to the Fuxin Jiuxing Titanium work site. The expected risk probability of an accident was 17.9%, which was in a comparatively safe state (State2). The results obtained by the Bayesian model are consistent with those obtained by AHP and fuzzy comprehensive evaluation method, which proved the accuracy of the early warning model. The Bayesian model can give the risk probability value of the accident and the risk probability value of the accident cause factors at the same time, and include the causal relationship and conditional correlation relationship among the indicator variables in the reasoning process, which can provide targeted technical support for the construction of the emergency system of risk classification management and control. [ABSTRACT FROM AUTHOR]

This document is an editorial from the journal Frontiers in Earth Science titled "Prevention, Mitigation, and Relief of Compound and Chained Natural Hazards." It discusses the increasing frequency of extreme natural disasters due to global climate warming and frequent earthquakes, which pose significant threats to human life and property. The editorial highlights the importance of preventing, mitigating, and relieving compound and chained natural hazards, and the role of technological advancements in addressing these hazards. The document provides an overview of nine published papers that focus on earthquakes, geological hazards, earthquake-triggered landslides, and landslide susceptibility. It concludes by emphasizing the need for continued research on comprehensive natural hazards and disaster chains, beyond earthquakes and geological disasters, such as meteorological events, floods, droughts, wildfires, and tsunamis. [Extracted from the article]

Microseismic monitoring has proven to be an effective approach for detecting and preempting water inrush incidents within mining operations. However, challenges persist, particularly in terms of relying on a singular early warning index and the complexities involved in quantification. In response to these obstacles, a dedicated investigation was undertaken against the backdrop of mining activities at the 11,023 working face of Paner Coal Mine. Primarily, a novel methodology for categorizing the roof and floor into distinct zones was established based on the vertical distribution of microseismic events. Furthermore, this study delves into the dynamic evolution of key source parameters, such as microseismic energy, apparent stress, and apparent volume, amidst mining disturbances, enabling a comprehensive evaluation of the risk associated with roof and floor cracking, as well as potential water inrush incidents. A groundbreaking approach to early warning was proposed, operating on three pivotal dimensions: the depth of fractures, the intensity of fractures, and the likelihood of water inrush. Through rigorous validation during mining operations at the 11,023 working face, the efficacy was substantiated. Ultimately, the achievements offer invaluable insights and practical guidance for the advancement and implementation of water inrush early warning systems in coal mining contexts. [ABSTRACT FROM AUTHOR]

Landslides are a widely recognized phenomenon, causing huge economic and human losses worldwide. The detection of spatial and temporal landslide deformation, together with the acquisition of precursor information, is crucial for hazard prediction and landslide risk management. Advanced landslide monitoring systems based on remote sensing techniques (RSTs) play a crucial role in risk management and provide important support for early warning systems (EWSs) at local and regional scales. The purpose of this article is to present a review of the current state of knowledge in the development of RSTs used for identifying landslide precursors, as well as detecting, monitoring, and predicting landslides. Almost 200 articles from 2010 to 2024 were analyzed, in which the authors utilized RSTs to detect potential precursors for early warning of hazards. The applications, challenges, and trends of RSTs, largely dependent on the type of landslide, deformation pattern, hazards posed by the landslide, and the size of the area of interest, were also discussed. Although the article indicates some limitations of the RSTs used so far, integrating different techniques and technological developments offers the opportunity to create reliable EWSs and improve existing ones. [ABSTRACT FROM AUTHOR]

Objectives: Mine slope instability is one of the main factors restricting the safety production of open-pit mines in China. Ground-based synthetic aperture radar interferometry technology has been gradually introduced into the application of slope safety monitoring and early warning prediction in open-pit mines. However, the high-frequency rolling update characteristics of ground radar interferometry data lead to large data error accumulation and unobvious curve mutation characteristics. Methods: Processing the original data by dislocation subtraction and velocity reciprocal method can effectively reduce the vibration of high-frequency data, improve the readability of critical sliding data. After data processing, it can highlight the trend characteristics of key deformation data. The research is based on the analysis of cumulative displacement curve, velocity curve and reciprocal velocity curve group treated with different periods. Results: It is found that there are three characteristic points in the curve group: Sudden deformation increase point, velocity increase point and stable vibration point. Through these characteristic points, the slope landslide disaster can be predicted. The trend of key deformation data can be highlighted by using the three feature points of deformation sudden increase point, velocity growth point and stable vibration point. Conclusions: Through the identification of three feature points, the possible landslide can be effectively identified in advance and the landslide time can be predicted, which provides a new technical path and solution for landslide early warning and prediction analysis based on ground-based interferometric radar [ABSTRACT FROM AUTHOR]

Weathered rock (especially granite) slopes are prone to failure under the action of rainfall, making it necessary to study the response of weathered rock slope to rainfall infiltration for landslide prevention. In this study, a series of model tests of weathered rock slope under different conditions were conducted. The matric suction, volumetric water content, earth pressure and deformation of slope were monitored in real time during rainfall. The response of the slope to rainfall infiltration, failure process and failure mode of slope under different conditions were analyzed, and the early warning criterion for the failure of weathered rock slope caused by rainfall was studied. The results show that the slope deformation evolution process under rainfall condition was closely related to the dissipation of matric suction. When the distribution of the matrix suction (or water content) of slope met the condition that the resistance to sliding of the slip-mass was overcome, the displacement increased sharply and landslide occurred. Three factors including rainfall process, lithologic condition and excavation condition significantly affect the response of weathered rock slope to rainfall. It can be found from the test results under different conditions that compared with intermittent rainfall condition, the rainfall intensity and infiltration depth were smaller when the slope entering accelerated deformation stage under the condition of incremental rainfall. The accumulated rainfall when weathered clastic landslide occurring was greater than that of weathered granite, which results in greater disaster risk. The excavation angle and moisture distribution of a slope were the main factors affecting the stability of a slope. In addition, the evolution processes and critical displacement velocities of slopes were studied by combining the deformation curves and matrix suction curves, which can be used as reference for early warning of rainfall-induced weathered rock landslide. [ABSTRACT FROM AUTHOR]

In this study, we present a machine‐learning model capable of predicting food insecurity in the Horn of Africa, which is one of the most vulnerable regions worldwide. The region has frequently been affected by severe droughts and food crises over the last several decades, which will likely increase in future. Therefore, exploring novel methods of increasing early warning capabilities is of vital importance to reducing food‐insecurity risk. We present a XGBoost machine‐learning model to predict food‐security crises up to 12 months in advance. We used >20 data sets and the FEWS IPC current‐situation estimates to train the machine‐learning model. Food‐security dynamics were captured effectively by the model up to 3 months in advance (R2 > 0.6). Specifically, we predicted 20% of crisis onsets in pastoral regions (n = 96) and 20%–50% of crisis onsets in agro‐pastoral regions (n = 22) with a 3‐month lead time. We also compared our 8‐month model predictions to the 8‐month food‐security outlooks produced by FEWS NET. Over a relatively short test period (2019–2022), results suggest the performance of our predictions is similar to FEWS NET for agro‐pastoral and pastoral regions. However, our model is clearly less skilled in predicting food security for crop‐farming regions than FEWS NET. With the well‐established FEWS NET outlooks as a basis, this study highlights the potential for integrating machine‐learning methods into operational systems like FEWS NET. Plain Language Summary: In the face of increasing droughts and food crises, this study explored the use of machine learning to provide predictions of food crises in the Horn of Africa, up to 12 months in advance. We used an algorithm called "XGBoost," which we fed with over 20 data sets of potential food security drivers. After training the model, we found that food security dynamics were accurately predicted up to 3 months in advance, especially in pastoral and agro‐pastoral regions. The model accurately predicted 20% of crisis onsets in pastoral areas and 20%–50% in agro‐pastoral regions with a 3‐month lead time. In agro‐pastoral and pastoral regions, our machine learning algorithm showed a similar performance to the established early warning system from FEWS NET. The machine‐learning model did not show good performance in crop‐farming areas. Nonetheless, this study underscores the potential of integrating machine‐learning methods into existing operational systems like FEWS NET. By doing so, it paves the way for improved early warning capabilities, crucial in mitigating the looming threat of food insecurity in the Horn of Africa. Key Points: A machine‐learning model is presented to predict food‐security crises in the Horn of AfricaThe model demonstrates high overall performance, and performs similarly to FEWS NET outlooks in the (agro‐) pastoral regionsThis study can be utilized to integrate machine learning into existing early warning systems, thereby creating hybrid solutions for the future [ABSTRACT FROM AUTHOR]

The effectiveness of ecological security patterns (ESPs) in maintaining regional ecological stability and promoting sustainable development is widely recognized. However, limited research has focused on the early warning of risks inherent in ESPs. In this study, the Guangdong–Hong Kong–Macao Greater Bay Area (GHKMGBA) is taken as the study area, and ecological security risk zones are delineated by combining the landscape ecological risk index and habitat quality, and a multi-level ESP is constructed based on the circuit theory. The PLUS model was employed to simulate future built-up land expansion under different scenarios, which were then extracted and overlaid with the multi-level ESP to enable the multi-scenario early warning of ESP risks. The results showed the following: The ESP in the central plains and coastal areas of the GHKMGBA exhibits a high level of ecological security risk, whereas the peripheral forested areas face less threat, which is crucial for regional ecological stability. The ESP, comprising ecological sources, corridors, and pinch points, is crucial for maintaining regional ecological flow stability, with tertiary corridors under significant stress and risk in all scenarios, requiring focused restoration and enhancement efforts. There are significant differences in risk early warning severity within the ESP across various development scenarios. Under the ecological protection scenario, the ESP will have the best early warning situation, effectively protecting ecological land and reducing ecological damage, providing a valuable reference for regional development policies. However, it must not overlook economic development and still needs to further seek a balance between economic growth and ecological protection. [ABSTRACT FROM AUTHOR]

Water toxicity determination with electrochemically active bacteria (EAB) shows promise for providing early warnings for heavy metal pollution in water. However, thus far, only idealized tests with a few types of heavy metals have been conducted. In this study, an automatic water-toxicity-determination system with high technical maturity was established, and the toxicological properties of common heavy metals were systematically assessed. The results demonstrated that the common heavy metals linearly inhibited EAB currents in the range of 0.1 mg/L to 0.5 mg/L. The toxicity ranking of the tested heavy metals was Pb2+ > Tl3+ > Cu2+ > Cd2+ > Zn2+ > Ni2+ > Hg2+ > As2+. The toxicity interaction mainly exhibited an antagonistic effect in binary heavy metal mixtures. The system can accurately determine surface water toxicity and rapidly monitor heavy metal pollution, with good repeatability and a long lifetime. Overall, this study demonstrates that EAB are capable of long-term (> 60 d) surface water quality monitoring and on-site early warning of heavy metal pollution. [ABSTRACT FROM AUTHOR]

Due to the uncertainty in soil landslide failure mechanisms, lack of early warning systems for soil landslides and adoption of improper excavation configurations, soil landslides accidents triggered by highway excavation in Chinese mountainous areas generally require expensive remedial measures. This paper describes a soil landslide associated with excavation through integrating field reconnaissance and finite element method simulation. According to the obtained results, the adoption of toe excavation and the presence of a silty clay layer are the two main factors contributing to the failure of the soil landslide, and a strong negative correction was observed between the toe excavation and surface displacement and the safety factor of the investigated cut slope; therefore, a four-level early warning system for this excavationinduced soil landslide was established by employing toe excavation and surface displacement thresholds as the warning indicators. Lastly, a preferable excavation configuration was proposed to facilitate excavation designs in similar landslide-prone areas. [ABSTRACT FROM AUTHOR]

This research aims to develop predictive models that use artificial intelligence (AI) to forecast early pest infestations in agriculture by integrating climate and soil data. Pests significantly threaten global food security, causing up to 40% of crop losses annually, highlighting the need for proactive pest management strategies. The study uses a hybrid approach, combining Gradient Boosting Decision Trees (GBDT) and Long Short-Term Memory (LSTM) networks, to analyze how variables such as temperature, humidity, rainfall, soil pH, soil moisture, and nutrient levels influence pest behavior. The models were trained and tested on diverse datasets, and evaluation metrics like accuracy, precision, recall, F1-score, and ROC-AUC were used to determine their effectiveness. The Random Forest model showed the highest accuracy at 89%, making it the most reliable for early pest detection. The findings demonstrate the potential of AI in enhancing agricultural productivity by enabling early warnings, reducing pesticide use, and supporting more sustainable farming practices. This study contributes to the development of scalable, data-driven solutions that integrate environmental variables, enabling better pest management and supporting global food security efforts. [ABSTRACT FROM AUTHOR]

Throughout its history, Papua New Guinea (PNG) has faced recurrent agricultural droughts, imposing considerable strain on both livelihoods and the economy. Particularly severe droughts have been associated with El Niño climate patterns. During these episodes, PNG becomes especially vulnerable to extended periods of aridity and diminished precipitation. Historically, humanitarian assistance for these events has primarily focused on responding to emergencies after an agricultural drought has been declared and communities have already been impacted. Here, we developed a proactive agricultural drought-triggering method for anticipatory action (AA) in PNG to offer a more sustainable and cost-effective approach to address this hazard. Our AA uses weather forecasts and risk data to identify and implement mitigative actions before a disaster occurs. The research details a step-by-step guide from early warning to action implemented by the Food and Agricultural Organization of the United Nations and the Government of Papua New Guinea. This preemptive disaster risk management initiative integrates a combined drought index (CDI) with specific thresholds and tailored anticipatory actions based on crop calendars. Moreover, the developed CDI provides a 3-month lead time for implementing AA to reduce the impact of the agricultural drought. During the El Niño-induced drought event that began in 2023, the CDI was tested and the AA was piloted for the first time. [ABSTRACT FROM AUTHOR]

Background: Nosocomial infections with heavy disease burden are becoming a major threat to the health care system around the world. Through long-term, systematic, continuous data collection and analysis, Nosocomial infection surveillance (NIS) systems are constructed in each hospital; while these data are only used as real-time surveillance but fail to realize the prediction and early warning function. Study is to screen effective predictors from the routine NIS data, through integrating the multiple risk factors and Machine learning (ML) methods, and eventually realize the trend prediction and risk threshold of Incidence of Nosocomial infection (INI). Methods: We selected two representative hospitals in southern and northern China, and collected NIS data from 2014 to 2021. Thirty-nine factors including hospital operation volume, nosocomial infection, antibacterial drug use and outdoor temperature data, etc. Five ML methods were used to fit the INI prediction model respectively, and to evaluate and compare their performance. Results: Compared with other models, Random Forest showed the best performance (5-fold AUC = 0.983) in both hospitals, followed by Support Vector Machine. Among all the factors, 12 indicators were significantly different between high-risk and low-risk groups for INI (P < 0.05). After screening the effective predictors through importance analysis, prediction model of the time trend was successfully constructed (R2 = 0.473 and 0.780, BIC = -1.537 and -0.731). Conclusions: The number of surgeries, antibiotics use density, critical disease rate and unreasonable prescription rate and other key indicators could be fitted to be the threshold predictions of INI and quantitative early warning. [ABSTRACT FROM AUTHOR]