Prevention Of Natural Hazards Research Articles

Agent-based modeling methodology and temporal simulation for Natech events in chemical clusters

In chemical clusters, technological accidents triggered by natural events (Natech events) can lead to the failure of large number of units and cause catastrophic consequences. Previous studies on Natech events give primary concerns on the static analysis at small-scale region with few thoughts the impact of various safety barriers. From the perspective of the large-scale region and temporal characteristics, an agent-based modeling methodology is proposed to present the dynamic evolution process. All the units associated with the evolution are divided into natural hazard agent, hazard-affected facility agent, safety barrier agent, and escalation factor agent to reduce the computational complexity. The time-dependent state transition mechanism of each agent is analyzed to represent the evolution process, simultaneously, the temporal effect of natural hazards, safety barrier and multi escalation factors is considered by utilization of time steps. Moreover, Monte Carlo simulation is adopted to quantify the uncertainties accompanying an accident evolution. The proposed methodology is demonstrated on a complex chemical system in the large-scale region. The results of simulation show that the number of failed hazard-affected facilities in the Natech events scenario will cyclically increase and keep constant, with strong temporal characteristic. The intensity of natural hazards and the probability of failure of safety barriers make a big impact on the temporal characteristic. The results are valuable to support natural hazard prevention in chemical cluster.

For a Sustainable Future: A Survey about the 2030 Agenda among the Italian Geosciences Community

The combined annual Congress of the Italian Geological Society (Società Geologica Italiana, SGI) and the Italian Mineralogical and Petrological Society (Società Italiana di Mineralogia e Petrologia, SIMP), dedicated to Geosciences for a sustainable future, took place in Turin in September 2022. This was an opportunity to critically reflect on the role of geosciences for our society and planet, and the role that geoscientists have to play in the education of citizens, for the prevention of natural hazards and the conservation of cultural and natural heritage. In continuity with our previous work on the awareness of the Sustainable Development Goals among young geoscientists in Italy, the present study attempts to expand the investigated sample to include the entire Italian community of geoscientists. The aim is to highlight: (1) the most widespread opinions on the link between Earth Sciences and the Sustainable Development Goals of the UN 2030 Agenda; (2) what steps have been taken by Italian Earth Sciences departments for sustainability education and what could be the best strategies to develop sustainability related to geoscience topics. According to 229 answers to a questionnaire sent to congress participants (corresponding to 20% of the total amount), the results highlight that the Italian geocommunity (at least its younger members) has a high awareness of the implications of its work and research with sustainability issues, and, in particular, their responsibility to the environment; notwithstanding this awareness, the level of average familiarity with the 2030 Agenda and its goals is still low. In order to bridge this gap, it is recognized that there is an urgent need for sustainability education efforts in departments and the use of inter- and trans-disciplinary teaching approaches that can educate both students and practitioners to be capable of addressing the challenging issues of today.

Towards Digital Twinning on the Web: Heterogeneous 3D Data Fusion Based on Open-Source Structure

Recent advances in Computer Science and the spread of internet connection have allowed specialists to virtualize complex environments on the web and offer further information with realistic exploration experiences. At the same time, the fruition of complex geospatial datasets (point clouds, Building Information Modelling (BIM) models, 2D and 3D models) on the web is still a challenge, because usually it involves the usage of different proprietary software solutions, and the input data need further simplification for computational effort reduction. Moreover, integrating geospatial datasets acquired in different ways with various sensors remains a challenge. An interesting question, in that respect, is how to integrate 3D information in a 3D GIS (Geographic Information System) environment and manage different scales of information in the same application. Integrating a multiscale level of information is currently the first step when it comes to digital twinning. It is needed to properly manage complex urban datasets in digital twins related to the management of the buildings (cadastral management, prevention of natural and anthropogenic hazards, structure monitoring, etc.). Therefore, the current research shows the development of a freely accessible 3D Web navigation model based on open-source technology that allows the visualization of heterogeneous complex geospatial datasets in the same virtual environment. This solution employs JavaScript libraries based on WebGL technology. The model is accessible through web browsers and does not need software installation from the user side. The case study is the new building of the University of Twente—Faculty of Geo-Information (ITC), located in Enschede (the Netherlands). The developed solution allows switching between heterogeneous datasets (point clouds, BIM, 2D and 3D models) at different scales and visualization (indoor first-person navigation, outdoor navigation, urban navigation). This solution could be employed by governmental stakeholders or the private sector to remotely visualize complex datasets on the web in a unique visualization, and take decisions only based on open-source solutions. Furthermore, this system can incorporate underground data or real-time sensor data from the IoT (Internet of Things) for digital twinning tasks.

MurGame: Protect your village from debris flows!

Past debris flow events, like in Bondo (2017) and Brienz (2005) in Switzerland have been heavily covered in the (Swiss) media, illustrating how destructive such events can get. Protection measures play an important role in dealing with natural hazards. Debris flows are considered to be very rare, complex and multidimensional processes. Imagining and foreseeing the course and progression of a debris flow as well as estimating the potential damage and the influence of protection measures is a difficult task. Serious games offer a possibility to simulate these kinds of situations. With the MurGame, we have developed an application for natural hazard prevention. In the three-dimensional, interactive game, a village is created by selecting different objects, such as residential buildings or schools. Debris flow simulations show, which buildings would be destroyed and what damage would occur in the event of a debris flow. Different protection measures can be implemented to protect the village and their effectiveness can be monitored during the simulations. After the event, it is necessary to evaluate which measures offer the desired protection, what they may cost and how the needs of the population are met. The MurGame can be played online at www.murgame.ch.

Assessment of Landslide Susceptibility Using Different Machine Learning Methods in Longnan City, China

In recent decades, with the increase in extreme climate duration and the continuous development of urbanization in China, the threat of landslide disasters has become increasingly serious. More and more scholars pay attention to the problem of the prevention of landslide disasters. Therefore, the landslide susceptibility prediction is generated, which can play an important role in the design of land development and urban development schemes in mountainous areas. In this paper, the frequency ratio (FR) model is used to quantitatively analyze the relationship between each factor and the occurrence of landslide (elevation, slope, aspect, plan curvature, profile curvature, distance to faults, rainfall, distance to rivers, soil types, land cover, Normalized Difference Vegetation Index (NDVI) and distance to roads). Based on the analysis of landslide distribution, 12 influencing factors were selected to establish the landslide susceptibility evaluation index system. Historical landslide points were randomly divided into training (70% of the total) and validation (30%) sets. Thereafter, decision tree (DT), logistic regression (LR), and random forest (RF) models were used to generate the landslide susceptibility mapping (LSM), and the predictive performance of the three models was evaluated using receiver operating characteristic (ROC) curves. The FR model results showed that landslides mostly occurred at slopes of 0–15°, elevations of <1000 m, distance to rivers of 0–500 m, rainfall of 750–840 mm, NDVI of 0.8–0.9, distance to roads of 0–500 m, distance to faults of 1500–2000 m and transportation land. Our results also showed that the RF model showed a great capability of identifying areas highly susceptible to landslide, and this model had the greatest reliability. High and very high landslide susceptibility was detected for 29.73% of the land area of Longnan City, Gansu Province, mainly in the eastern, northeastern, and southern regions. The importance ranking of the RF model also revealed that elevation, NDVI, distance to roads, and rainfall dominated the spatial distribution of landslides. Our results could help government agencies and decision-makers make wise decisions for future natural hazard prevention in Longnan City.

Spatial-Temporal Variations of Extreme Precipitation Characteristics and Its Correlation with El Niño-Southern Oscillation during 1960–2019 in Hubei Province, China

Extreme precipitation could result in many disasters, such as floods, drought, and soil erosion, further bringing severe economic loss. Based on the daily precipitation records during 1960–2019 of 26 stations obtained from the National Meteorological Science Data Center of China, 10 extreme precipitation indices (EPIs: annual total precipitation (PRCPTOT), max-1-day precipitation amount (RX1day), max-5-day precipitation amount (RX5day), number of heavy rain days (R10), number of very heavy rain days (R10), simple daily intensity index (SDII), consecutive dry days (CDD), continued wet days (CWD), very wet days (R95p) and extremely wet days (R99p)) were chosen and used to analyze the spatial-temporal variation of extreme precipitation within Hubei province, China, which is an important industrial and agricultural base in China. Finally, the correlation between El Niño-Southern Oscillation and EPIs was analyzed by cross-wavelet analysis. Results showed that the annual EPIs varied obviously during 1960–2019, and CWD decreased significantly (p < 0.05). The chosen EPIs were higher in eastern and southwestern Hubei compared to other regions, and RX1day, RX5day, R95p, and R99p were increased in most regions. The spatial-temporal variations of spring and summer EPIs were more obvious than those on an annual scale. In summer, all EPIs except CDD should increase in the near future. More attention should be paid to Wuhan, Enshi, and Macheng, where the RX1day, RX5day, R95p, and R99p will increase in these regions. Finally, the RX1day and R10 were positively correlated with MEI (p < 0.05), while the RX5day, CDD, CWD, and R99p were negatively correlated with MEI (p < 0.05). The extreme precipitation events within Hubei were affected by the El Niño-Southern Oscillation. The results could provide a possible driving factor for precipitation prediction and natural hazard prevention within Hubei province, China.

Open Spaces in the European Alps—GIS-Based Analysis and Implications for Spatial Planning from a Transnational Perspective

This article presents an open space concept of areas that are kept permanently free from buildings, technical infrastructure, and soil sealing. In the European Alps, space is scarce because of the topography; conflicts often arise between competing land uses such as permanent settlements and commercial activity. However, the presence of open spaces is important for carbon sequestration and the prevention of natural hazards, especially given climate change. A GIS-based analysis was conducted to identify an alpine-wide inventory of large-scale near-natural areas, or simply stated, open spaces. The method used identified the degree of infrastructure development for natural landscape units. Within the Alpine Convention perimeter, near-natural areas (with a degree of infrastructural development of up to 20%) account for a share of 51.5%. Only 14.5% of those areas are highly protected and are mostly located in high altitudes of over 1500 m or 2000 m above sea level. We advocate that the remaining Alpine open spaces must be preserved through the delimitation of more effective protection mechanisms, and green corridors should be safeguarded through spatial planning. To enhance the ecological connectivity of open spaces, there is the need for tailored spatial and sectoral planning strategies to prevent further landscape fragmentation and to coordinate new forms of land use for renewable energy production.

Evolution of vulnerability to marine inundation in Caribbean islands of Saint-Martin and Saint-Barthélemy

The islands of Saint-Martin and Saint-Barthélemy in the French West Indies are regularly affected by hurricanes and marine inundations. In this study, we investigated the influence of economic, demographic, and urban planning strategies on the construction of buildings located in areas exposed to coastal flooding, using a quantitative analysis based on satellite images and aerial photos from 1954 to 2017. Our results indicated that the number of buildings in coastal flooding areas is higher in Saint-Martin than in Saint-Barthélemy. The number of buildings constructed in marine inundation risk areas have increased during the last decades, owing to the tax reduction policies implemented for investment in French overseas territories that favor the development of new constructions in these islands and promote demographic growth. Inheritance of economic policy during the 1980–2010 period is responsible for the present state of vulnerability to marine inundation. A recent decrease (by 45%) in the constructions per year in the marine inundation risk areas observed in Saint-Martin from 2011 to 2017 could have been influenced by (1) the approval of the Natural Hazards Prevention Plan in 2011 and (2) population stagnation since 2007. Prevention plan was implemented late, after many buildings had already been built in marine inundation areas. The reduced prevention plan efficiency is due to the difficulty to conciliate risk mitigation, economic interests and political agenda.

Comparative Study of Convolutional Neural Network and Conventional Machine Learning Methods for Landslide Susceptibility Mapping

Landslide susceptibility mapping (LSM) is a useful tool to estimate the probability of landslide occurrence, providing a scientific basis for natural hazards prevention, land use planning, and economic development in landslide-prone areas. To date, a large number of machine learning methods have been applied to LSM, and recently the advanced convolutional neural network (CNN) has been gradually adopted to enhance the prediction accuracy of LSM. The objective of this study is to introduce a CNN-based model in LSM and systematically compare its overall performance with the conventional machine learning models of random forest, logistic regression, and support vector machine. Herein, we selected Zhangzha Town in Sichuan Province, China, and Lantau Island in Hong Kong, China, as the study areas. Each landslide inventory and corresponding predisposing factors were stacked to form spatial datasets for LSM. The receiver operating characteristic analysis, area under the curve (AUC), and several statistical metrics, such as accuracy, root mean square error, Kappa coefficient, sensitivity, and specificity, were used to evaluate the performance of the models. Finally, the trained models were calculated, and the landslide susceptibility zones were mapped. Results suggest that both CNN and conventional machine learning-based models have a satisfactory performance. The CNN-based model exhibits an excellent prediction capability and achieves the highest performance but also significantly reduces the salt-of-pepper effect, which indicates its great potential for application to LSM.

The ‘Rocket Framework’: A Novel Framework to Define Key Performance Indicators for Nature-based Solutions Against Shallow Landslides and Erosion

The idea of nature providing solutions to societal challenges is relatively easy to understand by the layperson. Nature-based solutions (NBS) against landslides and erosion mostly comprise plant-based interventions in which the reinforcement of slopes provided by vegetation plays a crucial role in natural hazard prevention and mitigation, and in the provision of multiple socio-ecological benefits. However, the full potential of NBS against landslides and erosion is not realised yet because a strong evidence base on their multi-functional performance is lacking, hindering the operational rigour of NBS practice and science. This knowledge gap can be addressed through the definition of repositories of key performance indicators (KPIs) and metrics, which should stem from holistic frameworks facilitating the multi-functional assessment of NBS. Herein, we propose the ‘rocket framework’ to promote the uptake of NBS against landslides and erosion through the provision of a comprehensive set of indicators which, through their appropriate selection and measurement, can contribute to build a robust evidence base on NBS performance. The ‘rocket framework’ is holistic, reproducible, dynamic, versatile, and flexible in helping define metrics for NBS actions against landslides and erosion along the NBS project timeline. The framework, resultant from an iterative research approach applied in a real-world environment, follows a hierarchical approach to deal with multiple scales and environmental contexts, and to integrate environmental, eco-engineering, and socio-ecological domains, thus establishing a balance between monitoring the engineering performance of NBS actions against landslides and erosion, and the wider provision of ecosystem functions and services. Using a case study, and following the principles of credibility, salience, legitimacy, and feasibility, we illustrate herein how the ‘rocket framework’ can be effectively employed to define a repository with over 40 performance indicators for monitoring NBS against landslides and erosion, and with over 60 metrics for establishing the context and baseline upon which the NBS are built and encourage their reproduction and upscaling.

"The Moral Economy of Rukai Society: Social Organization, Traditional Agriculture, and Natural Hazards Prevention"

"The Moral Economy of Rukai Society: Social Organization, Traditional Agriculture, and Natural Hazards Prevention"

UAV-BASED LIDAR HIGH-RESOLUTION SNOW DEPTH MAPPING IN THE SWISS ALPS: COMPARING FLAT AND STEEP FORESTS

Abstract. Snow depth mapping in Alpine forests is of high importance for hydrogeology, ecology, tourism, and natural hazards prevention. Different remote sensing approaches have been employed for the precise mapping of snow depth within forests. However, optical sensors cannot provide below-canopy information. While Airborne Laser Scanning (ALS) systems have been used successfully in this context and allow obtaining data below canopies, the costs of acquisitions are very high, not allowing frequent data acquisitions. UAV-based Lidar technology potentially can provide the critical below-canopy information at lower cost and allows for frequent acquisitions.First attempts to employ a UAV-based Lidar system in forests have proven promising, but they are limited to flat forests and to grid-level snow depth calculations. In this study, we present UAV-based Lidar data of both flat and steep forests. Different Lidar processing workflows are analyzed and compared, and snow depth algorithms are used both at the point and the grid level. Whereas the UAV-Lidar system proved capable of mapping snow in both environments, the steep forests' data processing comes with greater challenges, especially for the 3D registration, ground classification, and point-to-point snow depth calculations.

A Numerical Study of the Critical Threshold for Landslide Dam Formation Considering Landslide and River Dynamics

Landslide dam formation can be influenced by the erosive capacity of river flow and the dynamic characteristics of the landslide. When the deposition rate of a landslide that reaches a river is higher than the erosion rate of river flow, the landslide can form a dam by blocking the channel. Hence, in this paper, a dimensionless discharge threshold for landslide dam formation considering landslide and river dynamics is established and studied numerically. A two-layer depth-averaged model coupled with an erosion term is presented to simulate river and landslide movements and their interactions. Several numerical cases are simulated to study the influence of landslide and river dynamics on the critical threshold for dam formation by considering some key factors, such as landslide velocity and the angle between the river and landslide transport directions. Through the simulations, three types of landslide intrusion into river can be reflected: a dam forms quickly, a dam forms or does not form close to a critical state, and no dam forms. The results show that these factors together affect the process of dam formation if the difference between the landslide and river discharges is relatively small. All results are helpful to further clarify the formation of such dams for natural hazard prevention under future climate change conditions.

Effect of Congestion on Flow Field of Vented Natural Gas Explosion in a Kitchen

The process of gas explosion venting in a typical Chinese civil kitchen was investigated using computational fluid dynamics technology, focusing on the impact of the scale and cross-sectional characteristics of congestion, such as common furniture and electrical appliances, on the explosion flow-field parameters. An asymmetrical distribution of congestion will cause the uneven combustion of explosion flames in the kitchen. The flame will initially spread on one side of the room and then accelerate toward the surrounding areas, thereby increasing the risk of indoor gas explosion. The typical indoor overpressure change process can be divided into five stages, among which Stage V is found to be related to pseudoclosed combustion. Large-scale congestion has an obstructive effect on the explosion flow field, but it changes under certain conditions, while small-scale congestion only acts as a promoter. The flat congestion cross section helps maintain the stability of the flame structure, whereas the continuous and abrupt change of the congestion cross section can induce strong turbulent combustion. The research results provide a theoretical basis for the prevention and control of natural gas explosion hazards in civil kitchens from the perspective of congestion scale and cross-sectional mutation.

Image-Data-Driven Slope Stability Analysis for Preventing Landslides Using Deep Learning

Landslides account for approximately 5% of natural disasters resulting in significant socio-economic impacts. As a major infrastructure issue, slope stability has been traditionally analyzed with multiple deterministic and probabilistic methods to evaluate the stability of slopes or the probability of landslides. Geotechnical engineers tend to visit the sites of slopes, measure the geometry and soil properties, and use those traditional methods to analyze the slope stability and provide a factor of safety evaluation and recommendation. The fast-growing new technologies such as the internet of things and big data analytics provide new directions for natural hazard prevention. This study is the first to use deep learning as a new method for slope stability analysis for landslide prevention. A convolutional neural network was used to establish the model via transfer learning for processing simulated slope images. After training, our model can accurately predict the factor of safety of slopes for new slope images. Our proposed method was validated by comparing it with a classic limit equilibrium method, i.e., the simplified Bishop method, which is widely used in commercial programs for slope stability analysis. The comparison results showed that our proposed deep learning method outperformed the traditional method by decreasing the computation time by orders of magnitude without sacrificing accuracy. The results demonstrated the possibility and advantages of using deep learning as a new type of slope stability analysis method, including its ability to analyze raw image data directly, high level of automation, satisfactory accuracy, and short computing time, which will enable onsite evaluation for slope stability analysis. Thus, it facilitates fast in-situ decision-making for geotechnical applications and ensures the feasibility of using the internet of things and big data analytics for natural hazard prevention.

Summary of the general Local Plan of Dropull Municipality

The inhabitants of Dropull have historically recognized themselves as a community, kept together by the common traditions, culture and territory. But it was during the recent years that the territory was comprised in one municipality. The establishing of the new administrative unit created the opportunity for developing a new General Local Plan. POLIS University offered to the newly formed municipality the possibility of drafting the plan in a participated process that would profoundly and comprehensively involve the community. The plan is one of the most important instruments for governing the territory and for managing the future opportunities. In this sense the plan is structured in a series of consecutive documents, organized in three groups. The initial and primary document is the analysis of the territory, its culture and its economy. Out of this analysis a series of treats and opportunities emerge. The second document builds on the strengths of the municipality and tries to translate the opportunities into a vision. Dropulli’s vision foresees the municipality as a linear development corridor of settlements, and as rural development pole between the regional centers of Gjirokastra and Ioannina, from one side and the southern mountain ranges of Albania and the Ionian coast on the other. A territory with a strong historical and cultural character and identity, a model of coexistence between different nationalities, an important gateway to the cross-border area and a bridge between Albania and Greece. The municipality can turn into a center focused on the development of tourism, agriculture, livestock, and processing industry that utilizes local products to create a complete production cycle. The territory can welcome and provides space for research and for the establishment of start-ups based on tourism and bioproducts. In this way it can become a cross-border pole that uses sustainably the potential of a consolidated local economy and a favorable atmosphere for the return of population and for the attraction of investments. In order to achieve this vision, in the third and implementation part of the plan, four strategic objectives are proposed. The firs one fosters the higher accessibility to the territory and its integration to the larger infrastructural networks. This topic represents one of the most important challenges to the new municipality which is heavily influenced by the geographic position and by the rough terrain. The second strategic objective is the strengthening of the regional and cross border economic position through the development and diversification of the local economic activities. In this case, the geographic position of the municipality can be further exploited in order to become part of larger exchanges networks. The fourth strategic objective is the protection of the rural character of the settlements and the improvement of the quality of life. This objective is one of the most complex to achieve because it requires the creation of a balanced and sustainable development model which gives value to the historical settlements, without altering them but at the same time avoiding the freezing of every development initiative. The fourth and final strategic objective foresees the protection of the environment and the prevention of natural hazards. The strategic objectives are then turned into an operative form through the proposal of programs and projects which are consequently represented in the land use plan and in a budget.

Earth Observation and GIS-Based Analysis for Landslide Susceptibility and Risk Assessment

Landslides can cause severe problems to the social and economic well-being. In order to effectively mitigate landslide hazards, the development of detailed susceptibility maps is required, towards implementing targeted risk management plans. This study aims to create detailed landslide susceptibility (LS) and landslide risk (LR) maps of the Sperchios River basin by applying an expert semi-quantitative approach that integrates the Geographic Information Systems (GIS)-based multicriteria analysis and Earth Observation (EO) data. Adopting the analytic hierarchy process (AHP) for a weighted linear combination (WLC) approach, eleven evaluation parameters were selected. The results were validated using a historic landslide database, enriched with new landslide locations mapped by satellite and aerial imagery interpretation and field surveys. Moreover, the landslide risk map of the area was also developed, based on the LS delineation, considering additionally the anthropogenic exposure and overall vulnerability of the area. The results showed that the most susceptible areas are located at the west and south-west regions of the basin. The synergistic use of GIS-based analysis and EO data can provide a useful tool for the design of natural hazards prevention policy at highly susceptible to risk landslide risk areas.

GIS-based landslide susceptibility assessment using optimized hybrid machine learning methods

Globally, but especially in China, landslides are considered to be one of the most severe and significant natural hazards. In this study, bivariate statistical-based kernel logistic regression (KLR) models with different kernel functions (Polynomial, PUK, and Radial Basis Function), named the PLKLR, PUKLR, and RBFKLR models, were proposed for landslide susceptibility evaluation in Zichang City, China. Meanwhile, the present study aims to build landslide susceptibility maps based on bivariate statistical correlation analysis, optimization of different kernel functions, comparison of three landslide susceptibility maps and systematic analysis of spatial patterns. The steps of this article are organized as follows: Firstly, a landslide inventory containing 263 historical landslide locations was constructed. For the purpose of training and validation of models, 263 landslide locations were randomly divided into two parts with a ratio of 70/30. Secondly, 14 landslide conditioning factors were extracted from the spatial database. Subsequently, correlation analysis between the conditioning factors and the occurrence of landslides was conducted using frequency ratios. Then, the conditioning factors with normalized frequency ratios values were used as inputs to build the landslide susceptibility maps using the three models. A multicollinearity analysis was performed using collinearity statistics. Finally, the area under the receiver operating characteristic curve (AUC) was used for comparison and validation of models for recognizing the prediction capability. By further quantitative comparing mapped susceptibility values on a pixel-by-pixel basis, which can acquire underestimations and overestimations of factors (distance to river and slope) and susceptibility area. The results indicated that the PUKLR model had superior performance in landslide susceptibility assessment, with the highest AUC values of 0.884 and 0.766 for training and validation datasets, respectively. This model was followed by the RBFKLR model and the PLKLR model for the training datasets (AUC values of 0.879 and 0.797, respectively), and the PLKLR model and the RBFKLR model for the validation datasets (AUC values of 0.758 and 0.752, respectively). The landslide susceptibility map could help government agencies and decision-makers make wise decisions for future natural hazards prevention in Zichang region.

Analysis of geophysical and meteorological parameters influencing 222Rn activity concentration in Mladeč caves (Czech Republic) and in soils of Phlegrean Fields caldera (Italy)

The present work concerns a detailed analysis of Radon time series to differentiate endogenous from exogenous phenomena which provide anomalous signals. Two-year data from two sites in Czech Republic and in Italy are analyzed in order to contribute to the prevention of natural hazards. A new hybrid forecasting method is implemented and tuned for the identification of Radon anomalies in the time series. It is based on the combination of Multiple Linear Regressions, Empirical Mode Decomposition and Support Vector Regression methods that decompose the signal and analyze the components to distinguish the variations due to Radon originated in depths from those due to environmental parameters. The possible correlations with fumarolic tremors in the Italian site and the faults microdisplacements in the Czech site have been studied, as well as with the earthquakes that have influence on two studied areas. Results show that: (i) the used method is very effective considering the calculated statistical uncertainties; (ii) the outer temperature is the main influencing Radon driving force; (iii) the extracted Radon anomalies due to endogenous phenomena are well correlated with fault displacements, fumarolic tremors, and with earthquakes under a characteristic delay time for each area; (iv) significant correlations among earthquake magnitude and depth with fault displacement and fumarolic tremor are found.

Prediction of convective clouds formation using evolutionary neural computation techniques

The prediction of convective clouds formation is a very important problem in different areas such as agriculture, natural hazards prevention or transport-related facilities. In this paper, we evaluate the capacity of different types of evolutionary artificial neural networks to predict the formation of convective clouds, tackling the problem as a classification task. We use data from Madrid-Barajas airport, including variables and indices derived from the Madrid-Barajas airport radiosonde station. As objective variable, we use the cloud information contained in the METAR and SPECI meteorological reports from the same airport and we consider a prediction time horizon of 12 h. The performance of different types of evolutionary artificial neural networks has been discussed and analysed, including three types of basis functions (sigmoidal unit, product unit and radial basis function) and two types of models, a mono-objective evolutionary algorithm with two objective functions and a multi-objective evolutionary algorithm optimised by the two objective functions simultaneously. We show that some of the developed neuro-evolutionary models obtain high quality solutions to this problem, due to its high unbalance characteristic.