Effective Early Warning System Research Articles

Penggunaan Media Sosial untuk Penyebarluasan Informasi Peringatan Dini Banjir ke Masyarakat (Studi Kasus: BPBD Provinsi DKI Jakarta)

This study aims to analyze the role of social media in the dissemination of flood early warning information carried out by the Jakarta Provincial BPBD. Against the background of the importance of an effective early warning system, this study explores the use of social media as a communication channel that can reach the wider community quickly. Using a qualitative approach, this case study observed post data from BPBD social media platforms such as X (Twitter), Facebook, and Instagram in the period from November 2023 to February 2024. The results of the study show that BPBD actively uses social media to provide early warning information related to floods from various sources, such as upstream rain, local rain, and coastal floods. The conclusion of this study is that social media is effective in increasing public preparedness against potential floods, despite the challenges in maintaining public trust and ensuring understanding of the message conveyed.

Wastewater surveillance of antibiotic resistant bacteria for public health action: Potential and Challenges.

Antibiotic resistance is an urgent public health threat. Actions to reduce this threat include requiring prescriptions for antibiotic use, antibiotic stewardship programs, educational programs targeting patients and healthcare providers, and limiting antibiotic use in agriculture, aquaculture, and animal husbandry. Wastewater surveillance might complement clinical surveillance by tracking time/space variation essential for detecting outbreaks and evaluating efficacy of evidence-based interventions; identifying high-risk populations for targeted monitoring; providing early warning of the emergence and spread of antibiotic resistant bacteria and identifying novel antibiotic resistant threats. Wastewater surveillance was an effective early warning system for SARS-CoV-2 spread and detection of the emergence of new viral strains. In this data-driven commentary we explore whether monitoring wastewater for antibiotic resistant genes and/or bacteria resistant to antibiotics might provide useful information for public health action. Using carbapenem resistance as an example, we highlight technical challenges associated with using wastewater to quantify temporal/spatial trends in antibiotic resistant bacteria (ARBs) and antibiotic resistant genes (ARGs) and compare with clinical information. While ARGs and ARBs are detectable in wastewater enabling early detection of novel ARGs, quantitation of ARBs and ARGs with current methods is too variable to reliably track space/time variation.

Integrating Intelligent Hydro-informatics into an effective Early Warning System for risk-informed urban flood management

The urban drainage system constantly facing flooding issues in coastal and urban areas. Robust and accurate urban flood management, particularly considering fast-moving compound floods, is crucial to minimize the impact of flood disasters in coastal cities. Till now, Ho Chi Minh City (HCMC) lacks an effective means of urban flood management because of flood risk communication among residents. Existing flood risk communication tools rely on post-disaster flood model outcomes and data. Therefore, this research proposes a real-time Early Urban Flooding Warning System (EUFWS) integrated with a user-friendly web and app interface. The backbone of this system consists of flood models developed using machine learning (ML) algorithms, combined with big data and Web-GIS visualization, with ML serving as the core for constructing the EUFWS. EUFWS offer several key advantages: they are available at all times, accessible from anywhere, and provide a real-time, multi-user working platform. Additionally, the system is flexible, allowing for the easy addition of components and services and scalable, adjusting to workload demands. EUFWS have been successfully deployed in Thu Duc City, Vietnam, as a case study and are operating effectively. EUFWS have been successfully deployed in Thu Duc City, Vietnam, as a case study and are operating effectively. Research results indicate that EUFWS supported decision-makers to be effectively risk informed and make intelligent decisions during urban flood emergencies. This underscores the significant potential of integrating ML and information technology to enhance the management of smart urban drainage systems in flood-prone cities worldwide.

Research on machine learning and financial risk early warning of listed companies based on random forest model

This paper explores the application of machine learning technology based on random forest model in financial risk early warning of listed companies. By analyzing the data, we constructed a random forest model to identify potential financial risk factors. The study found that the random forest model showed high accuracy and stability in dealing with financial risk early warning issues. The model can effectively identify key indicators that affect the company's financial status and provide timely risk warning signals for investors and management. In addition, we also discussed the limitations of the model and the direction of future research, aiming to provide listed companies with a more accurate and effective financial risk early warning system, thereby helping companies to identify and respond to potential financial challenges as early as possible.

Child development lags and learning trajectories in primary school in Uruguay: compensation or divergence? / Rezagos en el desarrollo infantil y trayectorias de aprendizaje en la enseñanza primaria de Uruguay: ¿compensación o divergencia?

We evaluate two rival hypotheses of: (a) divergent trajectories — or cumulative learning gaps — between children with severe and moderate developmental lags and developmentally on-track children; and (b) convergent trajectories — which predict the inverse pattern. We estimate growth curves using panel data from a cohort of students first assessed by the Early Years Evaluation (Uruguay) at the end of kindergarten (age five), assessed up to three times in language and mathematics on an annual basis during years three to five since their transition to first grade. By the third year in school, substantial differences are found in reading and maths skills between children that did and did not show early developmental lags (effects range between .31 and .46 sd). We find a prevalent pattern of divergence in learning gains between years three to five in school (gaps increase by .10 sd per year). Our results suggest that tackling academic gaps will require timely interventions based on early identification of children who are academically at risk. Uruguay has developed early developmental assessment tools and learning monitoring systems, both of which should serve as the basis of an effective early warning system to deal with learning disparities from early ages.

Early warning COVID-19 outbreak in long-term care facilities using wastewater surveillance: correlation, prediction, and interaction with clinical and serological statuses

The unprecedented COVID-19 pandemic has highlighted the strategic value of wastewater-based surveillance (WBS) of SARS-CoV-2. This multisite 28-month-long study focused on WBS for older residents in 12long-term care facilities (LTCFs) in Edmonton (AB, Canada) by assessing relationships between COVID-19, WBS, and serostatus during the pandemic. Wastewater samples collected two to three times per week were tested for SARS-CoV-2 using RT-quantitative PCR. Theserostatus of antibodies was examined using immunoassays. The data of clinical COVID-19 outbreaks based on extensive testing were obtained from local public health officials. Analyses included calculating correlations between 7-day rolling averages for WBS and COVID-19 cases and investigating whether WBS led or lagged confirmed outbreaks using a multinomial test. Wastewater results correlated well with clinical COVID-19 infections and outbreaks at participating LTCFs. 1058 (36·0%) of 2936collected wastewater samples were SARS-CoV-2 positive, compared with 1247people (resident n=671, staff n=572, and unknown n=4) reporting positive test results of 21 673clinical samples assessed (5·8%). WBS led clinical testing in 32 (60·4%) confirmed outbreaks, which was significantly different from WBS lagged (12outbreaks [22·6%, 95% CI 11·3-33·7]). Non-detection of WBS SARS-CoV-2 served as a negative predictor for outbreaks. WBS results attested protective immunity in vaccinated individuals before the omicron wave. Aparallel increase in the proportions of positive WBS SARS-CoV-2 and anti-nucleocapsid antibodies underlined that omicron was an immunity-evading variant despite high seropositivity of neutralising antibodies after multiple doses of vaccine. Implementation of WBS could enable targeted clinical investigations and improve cost-effectiveness of COVID-19 outbreak management in LTCFs. WBS and serostatus provided informed dynamic changes of infections and immunity. Critical evidence was that LTCF WBS is an effective early warning system to support rapid public health outbreak management and protect vulnerable older populations. Canadian Immunity Task Force for COVID-19 and Alberta Health.

Preparedness of Lab School Middle School Students Towards Earthquakes for Disaster Risk Reduction

The primary objective of this research is to observe and analyze the preparedness of Labschool Middle School students in Palu City for Disaster Risk Reduction. The population in this study consisted of all students at Palu City Labschool Middle School, using a total sampling technique, resulting in a sample size of 100 students. Data was collected using structured questionnaires that were directly filled out by the students. The questionnaires were designed to cover all aspects of the research variables and provide a comprehensive assessment of the student's preparedness. Data processing in this study utilized a computerized system via MS Excel. Knowledge: 95% of respondents rated their knowledge on the subject as not good. This indicates that the majority of respondents have a poor understanding of the topic. Early Warning System: 57% of respondents rated the early warning system as not good. Resource Mobilization: 73% of respondents rated resource mobilization as not good. This indicates significant issues in resource mobilization, with the majority of respondents feeling that improvements are needed in this area. The findings indicate a significant gap in disaster preparedness among Labschool Middle School students. The majority lack basic knowledge about natural disasters and have minimal exposure to disaster-related training or education. Despite the availability of disaster warning tools in schools, awareness and understanding of their use remain limited. An effective early warning system is crucial for community safety, yet many students exhibit low awareness and preparedness levels

Expert consensus on the key technologies for a multi-point trigger intelligent surveillance and early warning system for infectious diseases

An effective infectious disease surveillance and early warning system is a crucial component of public health safety and is essential for preventing and controlling outbreaks of infectious diseases. Enhancing surveillance and early warning capabilities is an urgent priority for advancing high-quality disease prevention and control efforts. Combining the research findings and practical experiences of experts in epidemiology, clinical medicine, disease prevention and control, data science, and computer science, and following multiple rounds of expert discussions, we have developed a consensus on the key technologies for a multi-point trigger intelligent surveillance and early warning system for infectious diseases. This consensus primarily covers the related concepts and definitions of the multi-point trigger intelligent surveillance and early warning system for infectious diseases, the key technical framework, sources, acquisition, and governance of multi-channel warning data, classification of early warning methods, multi-point trigger intelligent surveillance and early warning paths, multi-point trigger warning and comprehensive assessment, response to warning signals, and evaluation of early warning effectiveness. It aims to provide technical references for the construction and application of a multi-point trigger intelligent surveillance and early warning system for infectious diseases.

Development of earthquake early warning algorithm magnitude scale for the 2023 Kahramanmaraş earthquake region

On 6 February 2023, Türkiye suffered two major earthquakes with magnitudes of Mw = 7.7 and Mw = 7.6 at 04:17 and 13:24 local time in Pazarcık and Elbistan districts of Kahramanmaraş, which were called as the disaster of the century. On 20 February 2023 at 20:04 local time, another major earthquake with Mw = 6.4 occurred in Yayladağı, Hatay. This disaster caused great loss of life and heavy destruction. The burden of the earthquake on the Turkish economy is extremely heavy. The purpose of earthquake early warning systems (EEWS) is to protect people and property, save time for precautions to be taken and prepare emergency response teams. An effective EEWS has a major role in reducing life, structural and economic losses. This study is an implementation of the original California optimized EPIC, an early warning algorithm, in the region of the 2023 Kahramanmaraş earthquakes. A total of 212 earthquakes in the region are replayed to derive magnitude scaling equations based on peak displacement amplitude (Pd) and predominant period (Tpmax). The performance of the modified equations is tested for three large earthquakes. By comparing the magnitudes estimated by Pd and Tpmax, it is observed that Pd gives more suitable results. The 2023 Kahramanmaras earthquakes real-time tests suggested a warning time of 32 s for the first earthquake in Antakya (Hatay), where the heaviest destruction and loss of life was observed. In the other earthquakes, the warning times were interpreted as quite useful to minimize the loss of life. The geography of the 2023 Kahramanmaraş earthquakes is a seismically active region and will be subject to earthquakes in the future. As a result of this study, a region-specific scaling of the magnitude, which is the most important parameter if an early warning system is established in the region, is presented. It is also a good example of how an effective earthquake early warning system can reduce potential hazards.

Effective early-warning tool in detecting structural anomalies and preventing progressive collapse.

Addressing the challenges of structural monitoring, this research introduces a cutting-edge method for Structural Health Monitoring (SHM). The study investigates the correlation between deformation work patterns occurring during random damage scenarios. The method focuses on deformation work and related parameters as key indicators of structural health, showing promising results in the early detection of potential issues. Despite evidence indicating the robust nature of structurally complex systems in parallel arrangements, no specific study has been conducted in the case of mixed systems presenting series and parallel elements configurations . In this study, the structural response of a set of systems made of rods in series and parallel arrangements has been analyzed. Damage to the system, occurring randomly on elements, is considered, and an energy-based metric is employed.The purpose of the study is not only to explore the behaviour of rods working in the coupled mechanism, but also to identify relevant trends in the case of certain load patterns or geometrical configurations in order to design an effective targeted monitoring system. The findings highlight the feasibility of this approach in detecting structural anomalies, underscoring its potential as an effective early-warning system for preemptive maintenance and contributing to the improvement of structural integrity and safety.

Multivariate Hydrological Modeling Based on Long Short-Term Memory Networks for Water Level Forecasting

In the Department of Chocó, flooding poses a recurrent and significant challenge due to heavy rainfall and the dense network of rivers characterizing the region. However, the lack of adequate infrastructure to prevent and predict floods exacerbates this situation. The absence of early warning systems, the scarcity of meteorological and hydrological monitoring stations, and deficiencies in urban planning contribute to the vulnerability of communities to these phenomena. It is imperative to invest in flood prediction and prevention infrastructure, including advanced monitoring systems, the development of hydrological prediction models, and the construction of hydraulic infrastructure, to reduce risk and protect vulnerable communities in Chocó. Additionally, raising public awareness of the associated risks and encouraging the adoption of mitigation and preparedness measures throughout the population are essential. This study introduces a novel approach for the multivariate prediction of hydrological variables, specifically focusing on water level forecasts for two hydrological stations along the Atrato River in Colombia. The model, utilizing a specialized type of recurrent neural network (RNN) called the long short-term memory (LSTM) network, integrates data from hydrological variables, such as the flow, precipitation, and level. With a model architecture featuring four inputs and two outputs, where flow and precipitation serve as inputs and the level serves as the output for each station, the LSTM model is adept at capturing the complex dynamics and cross-correlations among these variables. Validation involves comparing the LSTM model’s performance with linear and nonlinear Autoregressive with Exogenous Input (NARX) models, considering factors such as the estimation error and computational time. Furthermore, this study explores different scenarios for water level prediction, aiming to utilize the proposed approach as an effective flood early warning system.

Flood early warning system at Jakarta dam using internet of things (IoT)-based real-time fishbone method to support industrial revolution 4.0

This research aims to develop an effective flood early warning system to provide timely information to the public and support the government in disaster management. The Raspberry Pi mini-computer functions as the central control, collecting data from the Water Level Sensor to measure water height, the Ultrasonic Sensor for further monitoring, the DHT11 Sensor to monitor temperature and humidity, and a Buzzer as an audible warning device. The research method involves review of the literature and data acquisition from related journals. These data are utilized to design an Internet of Things (IoT)-based flood detection tool with the Raspberry Pi minicomputer as the main controller. The system can be implemented in vulnerable locations such as reservoirs, sluice gates, and rivers, as part of the Smart City and Smart Environment concepts. The test results indicate that the developed early warning system, integrating the Raspberry Pi minicomputer, the Water Level Sensor, the the Ultrasonic Sensor DHT11 Sensor, and Buzzer, approaches perfection. Real-time information is transmitted through the Twitter social media platform, which is shown to be more effective than manual notifications. The system can provide accurate early warnings, reduce flood-related damages, and positively contribute to flood prevention and disaster management efforts. This research is expected to make a significant contribution to improving the community and government preparedness for future flood disasters.

The Effect of Biotic Stress in Plant Species Induced by ‘Candidatus Phytoplasma solani’—An Artificial Neural Network Approach

Infections with phytoplasma present one of the most significant biotic stresses influencing plant health, growth, and production. The phytoplasma ‘Candidatus Phytoplasma solani’ infects a variety of plant species. This pathogen impacts the physiological and morphological characteristics of plants causing stunting, yellowing, leaf curling, and other symptoms that can lead to significant economic losses. The aim of this study was to determine biochemical changes in peony (Paeonia tenuifolia L.), mint (Mentha × piperita L.), and dill (Anethum graveolens L.) induced by ‘Ca. Phytoplasma solani’ in Serbia as well as to predict the impact of the biotic stress using artificial neural network (ANN) modeling. The phylogenetic position of the Serbian ‘Ca. Phytoplasma solani’ strains originated from the tested hosts using 16S rRNA (peony and carrot strains) and plsC (mint and dill strains) sequences indicated by their genetic homogeneity despite the host of origin. Biochemical parameters significantly differed in asymptomatic and symptomatic plants, except for total anthocyanidins contents in dill and the capacity of peony and mint extracts to neutralize superoxide anions and hydroxyl radicals, respectively. Principal Component Analysis (PCA) showed a correlation between different chemical parameters and revealed a clear separation among the samples. Based on the ANN performance, the optimal number of hidden neurons for the calculation of TS, RG, PAL, LP, NBT, •OH, TP, TT, Tflav, Tpro, Tant, DPPH, and Car was nine (using MLP 8-9-13), as it produced high r2 values (1.000 during the training period) and low SOS values. Developing an effective early warning system for the detection of plant diseases in different plant species is critical for improving crop yield and quality.

Threshold-based flood early warning in an urbanizing catchment through multi-source data integration: Satellite and citizen science contribution

An effective flood early warning system is vital to take action to save lives and protect properties in urban areas which are increasingly prone to flooding. Despite substantial progress in flood early warning systems, limited available and accessible data often impede their advancement and reliability. Engaging communities affected by flooding can help address data and information gaps in flood early warning systems, facilitated by appropriate methods. This study developed and evaluated a flood threshold combination method to support a community-based flood early warning system in the Akaki catchment, home to Addis Ababa, the capital city of Ethiopia. Various flood threshold combinations were formulated, calibrated and validated by integrating multiple sources of data: rainfall, antecedent precipitation index estimates, Sentinel-1 Synthetic Aperture Radar satellite time series of flood extent, long-term simulated streamflow, citizen science data, river water level and three days lead-time numerical weather prediction rainfall forecast. During validation, the rainfall and river water level threshold combination outperformed other threshold combinations with probability of detection, false alarm ratio, and critical success index estimates of 0.74, 0.18 and 0.63, respectively. The flood threshold combination showed high detection performance for most flooding conditions. Flood forecasts with a 1-day lead-time exhibited a high likelihood in detecting historical severe flood events. The study provides a tested methodology for selecting suitable flood threshold-combinations, enhance the engagement of citizen scientists in a community–based flood early warning system in urban communities.

Perspective: the potential of wastewater-based surveillance as an economically feasible game changer in reducing the global burden of pediatric respiratory syncytial virus infection.

Respiratory syncytial virus (RSV) is the leading viral cause of childhood bronchiolitis and pneumonia causing over 3 million hospitalizations and 100,000 deaths in children under 5 years of age annually. Wastewater-based surveillance (WBS) has proven an effective early warning system for high-consequence pathogens, including SARS-CoV-2, polio, mpox, and influenza, but has yet to be fully leveraged for RSV surveillance. A model predicated on the Canadian province of Ontario demonstrates that implementation of a WBS system can potentially result in significant cost savings and clinical benefits when guiding an RSV preventive program with a long-acting monoclonal antibody. A network of integrated WBS initiatives offers the opportunity to help minimize the devastating global burden of RSV in children by optimizing the timing of preventive measures and we strongly advocate that its benefits continue to be explored.

The Spatial and Temporal Variability of the Blue–Green Spatial Structures of the South Dongting Lake Wetland Areas Amidst Climate Change, including Its Relationship with Meteorological Factors

In recent years, the water level of the Dongting Lake (DTL) has been continuously low, and the wetland area and landscape pattern have changed significantly. Considering the obvious spatial heterogeneity of water regime changes in different waters of the DTL, this paper takes two core areas of the South Dongting Lake Nature Reserve (SDLNR) as study areas and analyzes the spatial distribution characteristics of the wetland blue–green landscape patterns by using remote sensing image data and hydrological and meteorological data. The multi-scale correlation between runoff, precipitation, temperature, and evapotranspiration in the SDLNR was studied via cross-wavelet transform analysis. The results show the following: (1) The change in the blue–green spatial patterns in different regions in different periods is inconsistent, and this inconsistency is related to the topography, climate, and human activities in each region; (2) there are seasonal fluctuations in precipitation, air temperature, and evapotranspiration in the SDLNR. Among them, the annual mean temperature shows a rising trend and passes the significance test with 95% confidence, while the annual mean precipitation and annual mean evapotranspiration show no significant change trend; and (3) our Pearson correlation analysis and cross-wavelet change results show that precipitation and temperature are strongly correlated with runoff, with a resonance period of 8–16 months, while the correlation between evapotranspiration and runoff is not significant. We recommend that policymakers establish an effective early warning system and make plans to store water through micro-terrain transformation in possible climate change treatments and strategies.

The evolution of Kenya's animal health surveillance system and its potential for efficient detection of zoonoses.

Animal health surveillance systems in Kenya have undergone significant changes and faced various challenges throughout the years. In this article, we present a comprehensive overview of the Kenya animal health surveillance system (1944 to 2024), based on a review of archived documents, a scoping literature review, and an examination of past surveillance assessments and evaluation reports. The review of archived documents revealed key historical events that have shaped the surveillance system. These include the establishment of the Directorate of Veterinary Services in 1895, advancements in livestock farming, the implementation of mandatory disease control interventions in 1944, the growth of veterinary services from a section to a ministry in 1954, the disruption caused by the Mau Mau insurrection from 1952 to 1954, which led to the temporary halt of agriculture in certain regions until 1955, the transition of veterinary clinical services from public to private, and the progressive privatization plan for veterinary services starting in 1976. Additionally, we highlight the development of electronic surveillance from 2003 to 2024. The scoping literature review, assessments and evaluation reports uncovered several strengths and weaknesses of the surveillance system. Among the strengths are a robust legislative framework, the adoption of technology in surveillance practices, the existence of a formal intersectoral coordination platform, the implementation of syndromic, sentinel, and community-based surveillance methods, and the presence of a feedback mechanism. On the other hand, the system's weaknesses include the inadequate implementation of strategies and enforcement of laws, the lack of standard case definitions for priority diseases, underutilization of laboratory services, the absence of formal mechanisms for data sharing across sectors, insufficient resources for surveillance and response, limited integration of surveillance and laboratory systems, inadequate involvement of private actors and communities in disease surveillance, and the absence of a direct supervisory role between the national and county veterinary services. To establish an effective early warning system, we propose the integration of surveillance systems and the establishment of formal data sharing mechanisms. Furthermore, we recommend enhancing technological advancements and adopting artificial intelligence in surveillance practices, as well as implementing risk-based surveillance to optimize the allocation of surveillance resources.

Extreme rainfall indices and their consequences on the local farming crop calendar: An agro-climatic zone based study

<p>The goal of this study is to investigate the extreme rainfall indices and their consequences on the local farming crop calendar among the agro-climatic zones (ACZs) of the Abiya watershed. Climate Hazards Group Infrared Precipitation (CHIRPS) provided long-term (1981–2019) rainfall data for 50 sample grid points with a spatial resolution of 5 × 5 km. Different crops are affected differently by the same extreme rainfall event depending on when it occurred and how extreme it was; this means crop calendars for a specific time may be properly governed by extreme climatic conditions. There hasn’t been a sufficient published study on extreme rainfall indices and their consequences on crop calendars by considering various ACZ in Ethiopia. The study defined local crop calendar timing and the consequences of the extreme rainfall indices through focus group discussions. INSTAT+ software was applied to calculate eight extreme rainfall indices. The indices were evaluated using Mann-Kendall’s (MK) and Sen’s slope techniques to identify trends and determine variations in the magnitude, respectively. Increase and decrease indications for various crop calendars were found in each ACZ. Further, going-up signals were seen in the highlands, midlands, and all ACZs for land preparation time (LPT), sowing and management time (SaMT), and harvesting and threshing time (HaTP), respectively. While HaTT was found to be uniform in all ACZs, some of the declining trends in the indices were detected for LPT and SaMT in the cold-highland and highland zones. The perceived trend in indices across the whole ACZ will have direct and unintended consequences for watershed crop production. The findings imply that to reduce the unfavourable consequences of these extreme rainfall occurrences in the agricultural sector, it is necessary to develop suitable crop varieties and drought-tolerant crops, as well as an effective early warning system.</p>

Analyzing MC-LR distribution characteristics in natural lakes by a novel fluorescence technology

The death of aquatic and terrestrial organisms caused by cyanobacterial blooms has been a topic of considerable concern since the 19th century. Microcystin-LR (MC-LR) produced by cyanobacterial blooms threaten natural ecosystems and human health. Therefore, establishing an effective monitoring and early warning system to detect MC-LR in water bodies is crucial. However, rapidly and intuitively assessing the distribution traits of MC-LR in lakes is a challenging task due to the complexities and expenses associated with conventional detection methods. To overcome these technical limitations, we introduce a novel and effective method for evaluating the distribution of MC-LR in lakes. This method is achieved by using a fluorescence probe (BAD) technology, marking the first application of this technology in evaluating the distribution of MC-LR in natural lake environments. The probe BAD is endowed with unique functions through clever functionalization modification. Experimental results exhibit that BAD has different fluorescence signals at various lake sampling points. The correlation analysis of fluorescence data and physicochemical indicators determines that the fluorescence data of the probe exhibit good correlation with MC-LR, implying that BAD is capable of detecting MC-LR in lakes. Moreover, the introduction of fluorescence technology to achieve the intuitive distribution of MC-LR in the entire plateau lake. This study provides a new method for evaluating the distribution of MC-LR in plateau lakes. It opens a new avenue for exploring the relationship between cyanobacterial blooms and MC-LR in natural waters.

Analysis of Artificial Intelligence Machine Learning Technology for Mapping and Predicting Flood Locations in Pahlawan Batu Bara Village

This research proposes the application of artificial intelligence technology, especially machine learning, to improve flood predictions. Flooding is a serious threat that can cause major losses to society and the environment. In an effort to overcome this problem, machine learning methods are used to analyze historical data related to weather, rainfall, topography, drainage systems and other factors that influence the occurrence of floods. Machine learning algorithms such as neural networks, decision trees, and other models to predict the potential for flooding in an area. Data collected from weather sensors, satellite maps and other data sources is used to train the model so that it is able to identify patterns that lead to flooding conditions. The research results show that the machine learning approach is able to increase the accuracy of flood predictions with a better level of reliability compared to traditional methods. The implementation of artificial intelligence technology in flood prediction has great potential to provide early warning to the public and authorities, thereby reducing the negative impacts caused by flood disasters. It is hoped that this research can become the basis for developing a more effective early warning system in dealing with the threat of flooding in the future.