AI-based Disaster Preparedness and Mitigation Plan

The study aimed to analyze the lived experiences of Agta men and women, including their gender roles, before, during, and after a natural calamity. Also, the study sought to examine the implications of breaking gender stereotypes in disaster preparedness, in the Agta community to develop gender-inclusive and culturally-sensitive disaster risk preparedness, mitigation, response, and recovery plans within the Agta community. Employing a case study research design, in-depth interviews with the Agta research participants, key informant interviews, naturalistic observation, and triangulation using the retrieved documents were conducted to gather relevant and significant data. Based on thematic analysis, the lived experiences of the Agta men and women before, during, and after the typhoon highlighted the traditional roles of men and women from disaster preparedness, risk reduction, and disaster recovery. Agta men typically performed the hard and critical jobs while women performed the household chores and took care of the children during calamities. However, during the observation, there were non-traditional roles that both Agta men and women have performed. The switching of gender roles between Agta men and women formed new schema to the minds of younger Agta regarding the roles of men and women, thus, embracing both traditional and untraditional gender roles.

Coastal areas are increasingly vulnerable to abrasion, flash floods, and seawater intrusion due to climate change and human activities. Addressing these hazards requires an integrated early warning system that enables timely and adaptive disaster mitigation. This study integrates landscape analysis, Mobile GIS technology, and the Ant algorithm into a unified early warning framework. Landscape analysis identifies geomorphological patterns and coastline changes. Mobile GIS supports real-time spatial data acquisition, while the Ant algorithm optimizes evacuation routes, sensor placement, and hazard prediction through agent-based modeling. The system incorporates spatial, topographic, oceanographic, and socio-economic data processed through spatial and computational methods. Validation using historical records and field data shows enhanced hazard detection, more efficient evacuation planning, and quicker response times. The Ant algorithm adapts routes in real time based on environmental changes. Sensor deployment is optimized for high-risk zones. Mobile GIS ensures continuous updates and spatial visualization. Real-time processing supports rapid decision-making and threat modeling. These integrated components demonstrate a strong potential to build a resilient, data-driven early warning system for coastal communities. In conclusion, the proposed system offers a precise, adaptive, and scalable approach to improve disaster preparedness in vulnerable coastal regions. Keywords: early warning system, Mobile GIS, ant algorithm, landscape analysis, coastal disaster mitigation

Highway flood risk assessment research is one of the current hotspots and difficulties in the field of natural disaster research, and it is also an important basis for disaster prevention and mitigation planning and management. The research analyzes the basic system of highway flood risk assessment from the aspects of basic concepts, influencing factors, and assessment contents of highway floods, and uses different methods to analyze the flood danger level from three dimensions: grid unit, small watershed unit, and town-level administrative unit. Combining qualitative analysis and quantitative assessment methods, the risk of highway floods at different spatial scales is evaluated, and the expected loss risk of highway floods in Banan District is estimated. The research shows that: (1) The grid can be used as a research unit to effectively explore the differences in the risk distribution within the study area due to its high data accuracy and complete sample information, it is suitable to use a neural network model for evaluation. (2) Based on the risk assessment at the small watershed scale, it is found that Banan District is mainly composed of low-risk and low-risk areas. The use of small watersheds as a research unit can reflect the spatial integrity of the impact factors of highway floods. The results It can provide decision support for river basin disaster management and prevention. (3) Based on the township-scale highway flood risk assessment, the township administrative unit is selected to analyze the flood danger levels of each town (street), which can meet the needs of management decision-making. Selecting different scales for risk assessment analysis can provide a scientific basis for the formulation, implementation, and allocation of disaster reduction resources for regional disaster management measures.KeywordsHighway floodHarzardMultiscaleRisk assessmentBanan district

Using big data and artificial intelligence to establish a multi-point monitoring, early warning, and disposal system to achieve early warning and intervention of infectious disease outbreaks is an important means of controlling the spread of the epidemic. Taking Xiaoshan district as an example, this study analyzes the monitoring contents, warning methods, and application effectiveness of the infectious disease monitoring, early warning and disposal system. Based on Xiaoshan's health big data resources, the system starts with syndrome, disease diagnosis and etiology. Through advanced technologies such as artificial intelligence and block chain, it realizes early identification of infectious disease outbreaks, data fusion, multi-cross collaboration, and closed-loop management. It has improved the sensitivity of clustered outbreaks monitoring and the effectiveness of epidemic disposal and provided a reference for grassroots disease prevention and control departments to establish an infectious disease monitoring and early warning system.

Floods are one of the most devastating natural disasters, causing significant loss of life, property, and infrastructure. Accurate and early prediction of floods is essential for effective disaster management and mitigation. This paper presents a flood prediction system using machine learning techniques to analyze historical and real-time environmental data such as rainfall, water level, temperature, and humidity. Various machine learning algorithms are applied to identify patterns and predict the probability of flood occurrence. The proposed system improves prediction accuracy and provides early warnings to authorities and the public, enabling timely preventive measures. By leveraging advanced data analytics and artificial intelligence, this system helps in reducing risks and enhancing disaster preparedness. The experimental results demonstrate that the proposed model performs efficiently in forecasting flood conditions and supports sustainable disaster management practices. Keywords: Flood Prediction, Machine Learning, Disaster Management, Data Analysis, Artificial Intelligence, Early Warning System

Early warning and response systems use meteorological forecasts to initiate public health interventions to reduce health impacts associated with weather variables, including climate variability. Effective systems are based on reliable meteorological forecasts; robust understanding of the cause- and effect relationships between meteorological factors and health outcome (allowing identification of high risk thresholds); response measures that can be implemented in a timely manner to reduce morbidity and mortality; and institutions and civil society actors with the resources, capacity, knowledge, and political will to undertake the response measures. Because these systems are effective in reducing adverse health impacts, it is widely assumed that such systems also will reduce the impacts of climate change. However, early warning systems are often designed without consideration of climate change. They establish exposure-response relationships and design response measures based on recent conditions and do not consider the implications for the effectiveness of systems of future and different weather and development patterns. Extreme weather and climate events are projected to increase in frequency, intensity, and duration, and may occur at times of the year different from today. Acclimatization, housing, the demographic structure of the population, technology development, and other factors will influence future vulnerability. Therefore, early warning systems should have flexible structures and processes to support modifications as climate and development baselines shift. Engagement with a broad range of stakeholders will facilitate timely adjustments to early warning and response systems to maintain or improve their effectiveness however the climate changes.

Flooding in Samarinda City is a problem that never ends every year. Based on Law Number 24 of 2007 concerning Disaster Management, the implementation of disaster management in situations of potential disaster includes: preparedness, early warning, and disaster mitigation. This study aims to analyze the stages of flood disaster mitigation in Samarinda City based on Law Number 24 of 2007 concerning Disaster Management. This type of research uses qualitative descriptive research with informant selection through purporsive techniques. Data collection techniques through observation, in-depth interviews, documentation and literature study and data analysis techniques using the triangulation method. The results showed that the efforts made by the BPBD of Samarinda City in disaster mitigation were mapping disaster-prone areas, monitoring in disaster-prone areas, socializing and disseminating information as well as coordinating with local governments and conducting education and training. The inhibiting factors in disaster mitigation are budget constraints, weak regulations, limited human resources in disaster management and low levels of public awareness.

The denseness of urban public buildings and the complication of the underground space spur the enhancement of disaster prevention and mitigation planning. As a result, for the urban public buildings around the densely populated area, the establishment of public buildings disaster prevention system in urban and the study on some related questions lay the basis of disaster prevention and mitigation. Since the concept of public building have the different definitions in the national standards and different types of buildings require different signs on disaster prevention, the category of public buildings has been redefined according to international normative standards. Furthermore, the research on the types, colors, sizes and position of disaster prevention signs has been done according to the internal, external of building and evacuation routes aspects. Finally, the basic functions of disaster prevention sign system in and around the buildings and the settings of the disaster prevention sign system of different types of public buildings are proposed.

Geology and Geomorphology of Natural Hazards and Human-Induced Disasters in Chile

- Successful disaster management and early warning are essential in reducing the effects of natural and human-induced hazards. Advances in real-time monitoring, data analysis, and communication technologies have greatly enhanced the forecast, detection, and response to disasters. This review paper presents a critical evaluation of contemporary methods, such as, geospatial analysis, and artificial intelligence-based prediction models. It also brings to light the shortcomings of current systems and delves into possibilities of building better real-time decision-making, timely warnings, and synchronized response strategies, leading the way for more adaptive and anticipatory disaster management solutions. Key Words: Disaster Management, Disaster Response, Early Warning Systems, Machine Learning, Geospatial Analysis, Mobile Applications, Web-based Platforms, Emergency Preparedness, Predictive Modeling.

Disasters pose a significant threat to human life, infrastructure, and the environment worldwide. Traditional disaster management approaches often face limitations in timeliness, accuracy, and reach of early warnings. This paper proposes an AI-driven disaster management framework that integrates digital media, IoT sensors, and GIS mapping to enhance early warning systems and improve community resilience. The framework leverages machine learning models for predictive analysis of disaster events, using real-time sensor data collected via IoT networks, such as river water levels, seismic activity, and weather parameters. These predictions are then visualized using GIS tools, enabling authorities and communities to identify risk-prone areas efficiently. Additionally, digital media platforms and social networks are employed to disseminate alerts and awareness messages, facilitating rapid information sharing and crowd-sourced data collection from affected populations. The proposed approach not only enhances accuracy and responsiveness in disaster situations but also fosters community participation through digital engagement. Case studies on floods and cyclones demonstrate the practical applicability of the system, highlighting improvements in early detection and response times. This interdisciplinary approach bridges computer science, disaster management, and communication studies, demonstrating the potential of emerging technologies to transform disaster preparedness. The paper concludes by discussing challenges, such as data privacy, false alerts, and infrastructure constraints, while suggesting future directions including integration of drone-based monitoring and AI-enhanced decision support systems. Overall, this study provides a comprehensive framework for leveraging AI and digital technologies to mitigate disaster risks and protect vulnerable communities effectively. Keywords: AI-driven disaster management, IoT, GIS mapping, early warning systems, predictive analytics, digital media alerts, community resilience

Monitoring and early warning system of porcine pasteurellosis based on WebGIS

<p><strong>Many tsunami events that have occurred in Indonesia have been published and also indicate the need for more adequate disaster mitigation efforts. One appropriate disaster mitigation measure is the use of an early warning system. Several studies have found that early warning systems do not work when tsunamis occur. This study aims to identify problems in the implementation of the tsunami early warning system in Indonesia from the perspective of the concept of distortion in communication messages. The research uses qualitative approaches supported by previous studies, various government regulations and supporting data from interviews with residents and tsunami early warning system managers. The research found that the potential for message distortion in communication in early warning systems is grouped into three categories. First, message distortion potential can arise from the operation of tsunami early warning system equipment. Second, message distortion may occur due to coordination in the management of the early warning system. Thirdly, message distortion may arise due to the perception of residents regarding their knowledge of the early warning system. This research recommends eliminating potential message distortion in tsunami early warning system communication by simplifying the flow of the early warning system to shorten coordination among system managers.</strong></p><p><strong><em>Keywords: Distortion, Early Warning System, Message, Tsunami</em></strong><strong>.</strong></p>

BackgroundThe decline of habitat for elephants due to expanding human activity is a serious conservation problem. This has continuously escalated the human–elephant conflict in Africa and Asia. Elephants make extensive use of powerful infrasonic calls (rumbles) that travel distances of up to several kilometers. This makes elephants well-suited for acoustic monitoring because it enables detecting elephants even if they are out of sight. In sight, their distinct visual appearance makes them a good candidate for visual monitoring. We provide an integrated overview of our interdisciplinary project that established the scientific fundamentals for a future early warning and monitoring system for humans who regularly experience serious conflict with elephants. We first draw the big picture of an early warning and monitoring system, then review the developed solutions for automatic acoustic and visual detection, discuss specific challenges and present open future work necessary to build a robust and reliable early warning and monitoring system that is able to operate in situ.FindingsWe present a method for the automated detection of elephant rumbles that is robust to the diverse noise sources present in situ. We evaluated the method on an extensive set of audio data recorded under natural field conditions. Results show that the proposed method outperforms existing approaches and accurately detects elephant rumbles. Our visual detection method shows that tracking elephants in wildlife videos (of different sizes and postures) is feasible and particularly robust at near distances.DiscussionFrom our project results we draw a number of conclusions that are discussed and summarized. We clearly identified the most critical challenges and necessary improvements of the proposed detection methods and conclude that our findings have the potential to form the basis for a future automated early warning system for elephants. We discuss challenges that need to be solved and summarize open topics in the context of a future early warning and monitoring system. We conclude that a long-term evaluation of the presented methods in situ using real-time prototypes is the most important next step to transfer the developed methods into practical implementation.

From the very beginning of the twenty-first century, the world has witnessed many natural disasters. The Sendai Framework for Disaster Risk Reduction 2015–2030 has emphasized on formulating disaster management plans at international, national, regional, and local levels. It also urges the use of traditional, indigenous, and local knowledge and practices for the disaster risk assessment and preparation of disaster mitigation plans and management disasters. The national disaster management policy of India 2009 describes that the local authorities should ensure the capacity building of their officers and manage disasters and carry out relief, rehabilitation, and reconstruction activities in the affected areas. It also calls for setting up a specific institutional framework for dealing with disasters in megacities. The Odisha government has made provisions to prepare the village-level disaster management plans and national, state, and district-level plans. In this context, we critically appraise the progress of India in empowering the local governments for effective management of disasters at the local level. We argue that it is high time to formally add the responsibility of disaster management by the local governments in the eleventh and twelfth schedules of the constitution. In line with the National Disaster Management Fund and State Disaster Management Funds, local governments should be provided with special Disaster Management Funds. A dedicated department should be created for managing various types of disasters. All disaster-prone villages should have a Village Disaster Management Committee, and panchayats should have a Panchayat Disaster Management Committee.KeywordsNatural disasters and their managementLocal governmentIntergovernmental relationsJEL CodesH77Q54