Loss Of Human Life Research Articles

Regional-scale landslide risk assessment in Central Asia

Abstract. Landslides are widespread phenomena that occur in any terrestrial area with slopes, causing massive property damage and, in the worst-case scenario, loss of human life. This propensity to suffer losses is particularly high for developing countries due to their urban development, population growth and drastic land use changes. Social and economic consequences of landslides can be reduced through detailed planning and management strategies, which can be aided by risk analysis. In this study, we performed a detailed quantitative risk analysis for landslides in the whole of Central Asia (4 000 000 km2). Landslide-induced risk was computed, using a 200 m spatial resolution, in terms of exposed population and expected economic losses to buildings and linear infrastructures (roads and railways). The purpose of our study is to produce the first regional-scale landslide risk assessment for Central Asia in order to inform regional-scale risk mitigation strategies, and it represents an advanced step in the landslide risk analysis for extremely broad areas.

Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model

Flash floods (FFs) are amongst the most devastating hazards in arid regions in response to climate change and can cause the loss of agricultural land, human lives and infrastructure. One of the major challenges is the high-intensity rainfall events affecting low-lying areas that are vulnerable to FF. Several works in this field have been conducted using ensemble machine learning models and geohydrological models. However, the current advancement of eXtreme deep learning, which is named eXtreme deep factorisation machine (xDeepFM), for FF susceptibility mapping (FSM) is lacking in the literature. The current study introduces a new model and employs a previously unapplied approach to enhance FSM for capturing the severity of floods. The proposed approach has three main objectives: (i) During- and after-flood effects are assessed through flood detection techniques using Sentinel-1 data. (ii) Flood inventory is updated using remote sensing-based methods. The derived flood effects are implemented in the next step. (iii) An FSM map is generated using an xDeepFM model. Therefore, this study aims to apply xDeepFM to estimate susceptible areas using 13 factors in the emirates of Fujairah, UAE. The performance metrics show a recall of 0.9488), an F1-score of 0.9107), precision of (0.8756) and an overall accuracy of 90.41%. The accuracy of the applied xDeepFM model is compared with that of traditional machine learning models, specifically the deep neural network (78%), support vector machine (85.4%) and random forest (88.75%). Random forest achieves high accuracy, which is due to its strong performance that depends on factors contribution, dataset size and quality, and available computational resources. Comparatively, the xDeepFM model works efficiently for complicated prediction problems having high non-collinearity and huge datasets. The obtained map denotes that the narrow basins, lowland coastal areas and riverbank areas up to 5 km (Fujairah) are highly prone to FF, whilst the alluvial plains in Al Dhaid and hilly regions in Fujairah show low probability. The coastal city areas are bounded by high-rise steep hills and the Gulf of Oman, which can elevate the water levels during heavy rainfall. Four major synchronised influencing factors, namely, rainfall, elevation, drainage density, distance from drainage and geomorphology, account for nearly 50% of the total factors contributing to a very high flood susceptibility. This study offers a platform for planners and decision makers to take timely actions on potential areas in mitigating the effects of FF.

Satellite derived mixing ratio profile, a resourceful indicator of heat waves: INSAT-3DR sounder based analysis

India, being a tropical country, frequently experiences a natural hazard called heat waves especially during the hot summer season. During the summer months of 2022, India experienced moderate to severe heat waves spanning March to the third week of May. This adverse weather situation severely affects the northwest and the central Indian regions, causing loss of human lives, crop damage, and a scarcity of water. The present study is the first attempt to assess the meteorological situations favoring heat waves using Indian National Satellite (INSAT)-3DR sounder data. Such studies using satellite based sounder data have seldom happened. The study is conducted during March-May 2022 using the mixing ratio data derived from the INSAT-3DR sounder at 500 hPa, 620 hPa, 700 hPa, 850 hPa, and 950 hPa pressure levels of the atmosphere. From the present study, it is observed that the INSAT-3DR derived mixing ratio profile gives clear signatures of an impending heat wave condition. The weather signal can be observed as an apparent dryness representing the low mixing ratio values (<6 g/kg) percolating from upper layers (600 hPa) to lower levels (850 hPa). These percolations (seeping) happen prior to the surface layers actually show the effects of the heat wave. The study verifies the prior studies of heat wave strike over northwest frontiers of Indian land mass and its further expansion to eastern and southern regions. During strong heat wave conditions surface temperatures reaching maximum of 46 ͦ C at northwest regions, 41 ͦ C at eastern regions and 40 ͦ C at southern regions. The corresponding mixing ratio values at 950 hPa diminishes to 2–4 g/kg for northwest regions and 4–6 g/kg at eastern and southern regions. The study also gives hints to locate signals of heat waves regarding their origin, possible expanding directions, and geographical extent from the satellite-derived mixing ratio. The observations from the analysis give scope for further enhancing the study in the future to devise efficient forecasting methodologies to predict heat wave conditions using satellite derived mixing ratio profiles.

Teorija i praksa prevencije od poplava - studija slučaja teritorije grada Kraljeva

Increasingly frequent floods, caused by altered climatic conditions, result significant material damage and loss of human life. The floods of May 2014 were the largest recorded in Serbia, affecting the territory of the city of Kraljevo, particularly the settlement of Grdica and the industrial zone of Šeovac. The damages from the floods impacted residential buildings, infrastructure, agriculture, business entities, and public facilities. Similar flood events, in terms of precipitation volumes and river water levels, also affected the Kraljevo area in 2023. Due to the frequent natural disasters impacting various parts of the territory, along with the extensive network of watercourses and intense climate changes, the city of Kraljevo has adopted an integrated approach to disaster risk reduction. The flood risk reduction system is governed by several legal regulations, primarily the Water Law and the Law on Disaster Risk Reduction and Emergency Management. In compliance with these legal obligations, the city has adopted necessary planning documents, established institutional mechanisms, and properly equipped civil protection units. Additionally, continuous investments have been made in constructing new and reconstructing the existing infrastructure. A significant advancement in the city's risk reduction system is the establishment of a civil protection system and inter-municipal cooperation among cities and municipalities in the West Morava River basin. It is important to measure the impact of investments in flood prevention to assess the justification and effectiveness of the resources used. The activities and measures implemented to reduce flood risk from 2014 to 2023 have shown positive results. This paper presents a comparative analysis of the effects of preventive activities and investments in the disaster risk reduction and emergency management system in the Kraljevo area during the specified period. The concluding considerations indicate that preventive investments in the flood risk reduction system and the construction of resilient and necessary protective infrastructure, lead to reduced damages and losses from floods.

Two-dimensional flooding model using IBER software case Study: Saidia City North east of Morocco

In the last two decades, Morocco has suffered a lot from catastrophic flooding, resulting in enormous damage to materials and loss of human life. The Sadia City (northeast Morocco), in our case of this study, is the most urbanized area with a high concentration of socio-economic activities in the region. Sadia is located downstream of the Moulouya watershed known for its low topography, and high vulnerability to fluvial and torrential flooding. The study aims to simulate the flood hazard index in the city of Saidia and consists of developing a two-dimensional (2D) flooding model using IBER software, and then producing maps of water flow and water velocity based on a 1-meter DTM. Then, we use GIS to map the hazard index of the areas with a high risk of flooding over a return period of 50 years. These hydraulic models were used to elucidate the risk of the Moulouya River overflowing its catchment area and to assist the stakeholders in decision-making about adequate measures to protect human life in Saidia City.

Arabic Text Detection on Traffic Panels in Natural Scenes

Identifying and acknowledging Traffic Panels (TP) and the text they display constitute significant use cases for Advanced Driver Assistance Systems (ADAS). In recent years, particularly in the context of the Arabic language, extracting textual information from TP and signs has emerged as a challenging problem in the field of computer vision. Furthermore, the significant rise in road traffic accidents within Arabic-speaking countries has resulted in substantial financial losses and loss of human lives. This is largely attributed to the limited number of diverse datasets for traffic signs and the absence of a reliable system for TP detection. Implementing warning and guidance systems for drivers on the road not only addresses this issue but also paves the way for the integration of intelligent components into future vehicles, offering decision support for transitioning to semi-automatic or fully automatic driving based on the driver’s health condition. These tasks present us with two main challenges. First, it involves developing a new Arabic dataset called the Syphax Traffic Panels dataset (STP) tailored to the diverse conditions of natural scenes gathered from “Sfax,” a city in Tunisia. This dataset aims to provide high-quality images of Arabic TP. Secondly, we suggest a deep learning method for detecting Arabic text on TP by evaluating the performance of the state-of-the-art algorithms in this context. In our study, we enhance the architecture of the most successful result achieved. The experiments conducted reveal promising results, affirming the significant contribution of our dataset to this research area, and even more encouraging results stemming from the enhancements made to the proposed method. The dataset we possess is accessible to the general public on IEEE DataPort https://dx.doi.org/10.21227/5zd9-pe55

Mogućnost primene pravila međunarodnog humanitarnog prava na sajber rat

Cyber warfare represents a new form of conflict in today's world. Unlike earlier traditional armed conflicts, cyber warfare is different in terms of means, methods, techniques, and actors. Cyber warfare takes place in virtual space through the use of information and communication technologies. The actors may be states, but also individuals who can inflict significant damage on their opponents. The consequences of cyber attacks may not be immediately apparent, but can manifest much later. Similarly, the outcome of a cyber attack can be material damage or the loss of human life. Since cyber operations can take place not only during conflicts but also in peacetime, the concept of cyber aggression is often present. States are aware of the new cyber threats and are developing their defensive and offensive capabilities, adopting strategies and doctrines addressing these issues. However, there is no international agreement that regulates the open issues related to cyber warfare, as there is no consensus among states on how to regulate it. There are attempts to apply the rules of international humanitarian law that govern armed conflicts to the realm of cyber warfare. Consensus within the international community has not been reached, leaving this area unregulated. The paper aims to examine the possibility of applying the rules of international humanitarian law, specifically the rules governing the right to use force in international relations (jus ad bellum) and the rules governing the conduct of parties in conflict (jus in bello), to cyber warfare.

Dynamical features and FE modelling of a multi-span historical masonry arch bridge

The Italian road infrastructural asset includes a large number of historical masonry arch bridges. Many of these structures are today still in service, despite their ancientness and the frequent lack of maintenance and upgrading interventions. Given the strategic role they often play in the road network, their protection and conservation are an urgent priority to avoid connection issues, as well as losses of human lives. The structural assessment of these structures may be far from trivial since original design documents are generally missing. Thus, they must be subjected to articulate knowledge processes, which include geometrical surveys (both externally and internally), tests on material and, if possible, characterization of the overall dynamic behavior. Based on this premise, in the present paper the case study of a five-span masonry arch bridge in Mignano Monte Lungo (Caserta province, Italy) is addressed. A preliminary historical reconnaissance was performed together with a survey of the external geometry of the bridge. The collected data were enriched by means of a dynamical characterization of the entire structure, which allowed for realizing a preliminary finite element model in Abaqus software.

ECONOMIC DEVELOPMENT AND CLIMATE CHANGE IN INDIA: A REVIEW STUDY

Global warming has become a reality in present times posing a serious threat to existence of human lives on this earth. Increasing instances of natural calamities have caused huge loss of precious human lives and property in recent past and such casualties have become more frequent in recent times than ever before. Achieving higher rate of economic growth has now become a compulsion for every nation and commands a central place in framing of various state policies in their quest for alleviation of poverty and bringing improvement in standard of living of people residing in that country especially poor and downtrodden sections of society. Economic growth entails using various natural resources in production of goods and services but when it takes the form of race causing over-exploitation of natural resources then it results in inflicting severe damage to natural environment due to excessive emission of greenhouse gases. Developed countries are far ahead in this race of achieving economic growth and so they are now being followed by developing and under-developed countries. Gradually, the world community has started realizing the huge cost that humanity is paying for environmental damage and so there is daunting challenge before every country to cut down carbon emission and release of greenhouse gases but none wants to compromise on their growth agenda. Developing countries object to the pressure mounted by developed world arguing that since developed countries are main contributors to this menace and so they should compensate by way of extending financial support to them to help them adapt to green technologies in years to come. It is to be noted that economic development is the cause as well as remedy for protecting against climate change and so there needs to a judicious development policy which incorporates climate change perspective without compromising on achieving high rate of economic growth. Different countries around the world have started revisiting their erstwhile models of economic growth and so it is highly needed that India too to conform to modern global practices to minimize damage to natural environment.

Performance-Based Design Assessment of Temperature Tenability Condition in a Hotel Atrium

Fire safety risk assessment to prevent loss of human life and property is necessary for complex structures where the traditional prescriptive designs are inapplicable. Maintaining tenable temperature conditions is essential for the safe evacuation of building occupants. This study considered British Standards (BS) 7974 and the Code of Practice for Fire Precautions in Buildings to analyze the temperature tenability conditions in the hotel atrium through a performance-based design approach. Further, the Computational Fluid Dynamics (CFD) code, Pyrosim, a Graphical User Interface (GUI) of the Fire Dynamics Simulator (FDS), was utilized to simulate a constant Heat Release Rate (HRR) steady state design fire of 5 Megawatts (MW) igniting from the hotel brasserie (ground floor) within the atrium. The researcher used the big design fire of 5MW to generalize the results to similar fires in similar structures. The objective was to conduct a fire safety risk assessment to prevent loss of property and fatalities by activating a smoke management control system with a ‘what if’ condition when the fire suppression system failed to start. Temperature data was collected through the statistical steady state profile, smoke layer temperatures, thermocouples, and 2-dimensional slice temperature recordings. The ground floor, the fire source, was found to have untenable conditions for human survival with temperatures above 2250C, as confirmed by thermocouple and steady-state temperature profile readings. Other floors demonstrated tenable conditions for human survival with temperatures below 400C due to the effect of natural vents and mechanical extractors, which extracted the hot smoke at a rate of 15m/s. The temperature recordings from this study compared well with those from Chew and Liew’s (2000) Computational Fluid Dynamics results, which had fire igniting within the atrium, without sprinklers, and had mechanical extraction fans and a constant Heat Release Rate of 5 Megawatts (MW). The results indicated that the smoke control management system maintained tenable temperature conditions within the hotel atrium, even without the fire suppression system through sprinklers. Considering the design fire size was 5 MW, which was significantly big, the results could be generalized for other hotels or structures with similar designs.

Enhancing landslide hazards survey and management to reduce the loss of human lives and properties

Enhancing landslide hazards survey and management to reduce the loss of human lives and properties

Smart heart disease prediction and amalgamation tracking system

In this modern world, cardiovascular disease stands as the leading cause of global mortality. To combat this alarming trend and prevent the devastating loss of lives, an innovative solution that focus on reliability, accuracy, scalability, and cost-effectiveness. This work proposes a system that utilizes an artificial intelligence processor (LSAI48266X) and an IoT device to transfer data from sensors such as the Mach30100 and DS18B20. The system aims to track, visualize, and forecast heart disease. Random Forest is a machine learning algorithm that predicts cardiac illness based on numerous parameters such as SpO2, heartbeat, temperature, and blood pressure. Web application is developed using PHP that displays hospital details and integrated with a Telegram chatbot for communication during emergency conditions. Compared to earlier methods, our proposed system distinguishes itself with an impressive accuracy rate of 95.6% and automation system to prevent loss of human life by incorporating the Random Forest Algorithm and tracking system.

Probabilistic Convective Initiation Nowcasting Using Himawari-8 AHI with Explainable Deep Learning Models

Abstract Convective initiation (CI) nowcasting is crucial for reducing loss of human life and property caused by severe convective weather. A novel deep learning method based on the U-Net model (named as CIUnet) was developed for forecasting CI during the warm season with eight interest fields of Himawari-8 Advanced Himawari Imager (AHI) and terrain height. The results showed that the CIUnet model produced probability forecasts of CI occurrence location and time with probability of detection (POD) at 93.3% ± 0.3% and false alarm ratio (FAR) at 18.3% ± 0.4% at a lead time of 30 min. Sensitivity and permutation importance experiments on the input fields of the CIUnet model revealed that the differences in brightness temperature for spectral channels were more critical for CI nowcasts than the original infrared channel brightness temperatures. The brightness temperature difference between band 10 (7.3 μm) and band 13 (10.4 μm), which represents the cloud-top height relative to the lower troposphere, is identified as the most important input fields for CI nowcasting. The tri-spectral brightness temperature difference (TTD), which represents cloud-top glaciation, is ranked the second and it significantly reduced the FAR of the CI forecast. Using terrain heights as an extra input feature improved the POD, but slightly overestimated CI over complex terrain. In addition, a layer-wise relevance propagation (LRP) analyses was performed, and confirmed that the CIUnet model can effectively identify the crucial regions and features of the input fields for accurate CI prediction. Therefore, both permutation importance experiments and LPR analyses are useful for improving the CIUnet model and advancing the understanding of CI mechanisms.

Participatory communication as the key to successful disaster management in Pangandaran district

Background: Pangandaran, situated within the province of West Java, is considered a region susceptible to natural disasters, leading to significant material damages and, unfortunately, loss of human life. This particular calamity has attracted the attention of various stakeholders, encompassing the local government, affiliated organizations, social communities, volunteers, and numerous others. The circumstances mentioned above have led to the development of participatory communication initiatives to promote cooperation in disaster management. Purpose: This study aims to ascertain the factors contributing to heteroglossia, discourse, polyphony, and collaboration among communities and volunteers. Methods: The research method utilized in this study is a descriptive study, incorporating a range of data collection techniques, including in-depth interviews, observation, and literature analysis. Furthermore, to conduct comprehensive data analysis, this study involves data reduction, data display, conclusion derivation, and verification. Moreover, the technique employed for data source identification involves systematically classifying stakeholders, including individuals affiliated with institutions and community members/volunteers who actively participate in collaborative efforts to address disaster-related issues in the Pangandaran Regency. Additionally, the study involved a cohort of five key informants deliberately chosen to represent the community under the study. Results: The study results indicate that, despite differences in tasks, responsibilities, roles, and level of expertise within the community or volunteers, they are willing to exchange knowledge, drawing on their viewpoints openly. Furthermore, the dialogue process that unfolds among the community/volunteers takes the form of a democratic discussion to attain consensus in their respective roles. Conclusion: Communities/volunteers have established collaborative efforts grounded in their understanding, awareness and commitment to assisting individuals affected by adverse circumstances. Moreover, shared norms and beliefs have guided their robust, extensive relationships and networks.

Insights for Improving Road Safety：Focusing on Vehicle Accidents in Daegu Metropolitan City

Road accidents not only caused loss of human lives but also costed 3% of gross domestic product in most of the countries. The road accidents pose significant challenges to public safety and urban transportation management. There is a need to identify the high-risk area of accidents along with the critical day of week and vulnerable time period in order to implement effective preventive measures and optimizing the resource allocation. We collected 5,012 accident data from 대구교통종합정보. This study identified the high-risk locations, days of week, and time periods for accidents in Daegu and estimated the conditional probabilities of accidents occurring based on combinations of location, day of the week, and time period. The result is visualized in the form of dashboard in Tableau. This study holds substantial practical significance for urban planners, transportation authorities, and policymakers in Daegu to strategically allocate resources for traffic management, law enforcement, and targeted safety campaigns.

IDENTIFYING THE POTENTIAL OF UNMANNED AERIAL VEHICLE ROUTING FOR BLOOD DISTRIBUTION IN EMERGENCY REQUESTS

This study is focusing on identifying the potential of Unmanned Aerial Vehicle (UAV) routing for blood distribution in emergency requests in Sri Lanka compared to existing transportation modes. Capacitated Unmanned Aerial Vehicle Routing Problem was used as the methodology to find the optimal distribution plan between blood banks directing emergency requests. The developed UAV routing model was tested for different instances to compare the results. Finally, the proposed distribution process via UAVs was compared with the current distribution process for the objective function set up in the model and other Key Performance Indicators (KPIs) including energy consumption savings and operational cost savings. The average percentage of distribution time re-duction, energy consumption cost reduction, and operational cost per day reduction utilizing UAVs were determined to be 58.57%, 96.35%, and 61.20%, respectively, for the instances tested using the model highlighting the potential of UAVs. Therefore, the deficiencies in Sri Lanka's present blood delivery system can be addressed using UAVs' potential for time, cost, and energy savings. The ability to save time through the deployment of UAVs to the fleet during emergency situations plays a crucial role in preventing the loss of human lives.

ECOWAS Protocol on Migration, Porous Borders and Dynamics of Armed Banditry in Nigeria

The dialectics that have led to an explosion of free movement of persons within ECOWAS borders largely constitute a new dimension of security threats in the region. The security threats emanating from incessant human migration within the region have predictably distorted the security architecture of Nigeria, thereby posing colossal pressures on the Nigerian armed forces, as well as leading to the loss of human lives, properties, and financial resources. The study investigated how ECOWAS protocol on free movement of persons and porous borders in the West African region orchestrate armed banditry in Nigeria. The work was anchored on the Qualitative-Descriptive method of analysis, and ‘inelastic political will’ was adopted as an analytical construct that explains the inability of ECOWAS member governments as well as the Nigerian government to employ sustainable strategies in tackling the ever-changing security threat dimensions within the region. It was revealed that chaotic and explosive cross-border migration of persons in West Africa has a relationship with the new dimension of armed banditry in Nigeria. The study recommended that the ECOWAS framework that promotes the free movement of people be reviewed and amended to address current security crises in the region. Also, there is a need for the Nigerian government to reinforce viable and strong diplomatic ties with the neighboring countries such as Benin, Chat, Niger, and Cameroon regarding border infrastructure development and security enhancement mechanisms to cover ungoverned spaces in the Chad Basin Region.

The Lviv Archaeological Milieu During World War

The article deals with the scientific and museological activities of Lviv archaeologists during World War I. The focus is on the fate of archaeologists who were forced to serve in the army (Y. Pasternak, V. Hrebeniak); the state of scientific institutions of Lviv, and the living and working conditions of professors and teaching staff of the University of Lviv, as well as museum workers of the city, were analyzed. In addition, it is about stocking and inventorying the museum collections with archaeological finds, and attempts to restore the activities of museum institutions regardless of conditions (National Museum of Jan III Sobieski, Dzieduszycki Museum). The issue of the loss of human lives is not the least. During these years, Lviv archaeology lost a Polish professor of archaeology Karol Hadaczek and his student, the talented Ukrainian archaeologist Volodymyr Hrebeniak. It was found that the War stopped the development of archaeological science in Lviv and pushed it back for some time. Only in the post-War years, was it possible to restore field research, and publishing activities, replenish museum collections, and educate new personnel.

Assessing psychological well-being among medical officers during COVID-19 pandemic: An approach toward sustainable development

The COVID-19 pandemic has resulted in a significant loss of human life and affected healthcare infrastructure globally. The present study aimed to study the presence of anxiety and stress symptoms among medical officers in the Indian army and the impact of anxiety and stress on psychological well-being during COVID. The data was collected from February 2021 to April 2021 using a standardized questionnaire to measure anxiety, stress, and psychological well-being. Data collected from 319 respondents were analyzed using SPSS by Chi-square tool, bivariate correlation, H-test, and U-test. The presence of anxiety and stressed symptoms were 11.9% and 37.3% among medical officers in the Indian army. Medical officers of the AMC unit (doctors) were more impacted by anxiety compared with MNS and ADC medical officers. The risk factors having significant association with stress symptoms were age (maximum in 31-40 and 51-60 years), rank (initial service ranks and senior ranks both), and unit (AMC and MNS are more prone to stress symptoms as compared to ADC unit). Anxiety (-0.543) at p&lt;0.01 has more negative impact on psychological well-being among medical officers of armed forces as compared to stress at work (-0.243) at P&lt;0.01. In this present study, results showed the high presence of anxiety and stress symptoms among medical officers during COVID-19. Results also demonstrated that there is a difference in anxiety level at different times of COVID. Differences in psychological well-being also exist and are impacted due to the presence of stress and anxiety. By prioritizing well-being, focus will be shifted to sustainable development of medical officers.

A comparative study of Machine Learning and Deep Learning methods for flood forecasting in the Far-North region, Cameroon

Flood crises are the consequence of climate change and global warming, which lead to an increase in the frequency and intensity of heavy rainfall. Floods are, and remain, natural disasters that result in huge loss of lives and material damage. Flood risks threaten all countries of the globe in general. The Far-North region of Cameroon has suffered of flood crises on several occasions, resulting in significant loss of human lives, infrastructural and socio-economic damage, with the destruction of homes, crops and grazing areas, and the halting of economic activities. The models used for flood forecasting in this region are generally physical-based, and produce unsatisfactory results. The use of artificial intelligence based methods for flood forecasting in order to limit its consequences is a way to be explored in the Far-North region of Cameroon. The aims of the present research work is to design and compare the performance of Machine Learning and Deep Learning based models such as one dimensional Convolutional Neural Network, Long and Short Term Memory and Multi Layer Perceptron for short-term and long-term flood forecasting in the Far-North region of Cameroon. The models designed take as input the temperature and rainfall time series recorded in this region. Performance criteria used for evaluating models are Nash–Sutcliffe Efficiency, Percent Bias, Coefficient of Determination and Root Mean Squared Error. As the results of the design and performance comparison of the models, the best model for short-term flood forecasting is the LSTM model , and the best model for long-term flood forecasting is still the LSTM model. The best models obtained from the comparisons have satisfactory performance and good generalization capabilities, as reflected by the performance criteria. The results of our research work can be used for implementation of floods warning systems and for definition of an effective and efficient flood risk management policies in order to make the Far-North region of Cameroon more resilient to flood crises.