Vulnerability Map Research Articles

Novel integrated modelling based on multiplicative long short-term memory (mLSTM) deep learning model and ensemble multi-criteria decision making (MCDM) models for mapping flood risk

Flood risk assessment is a key step in flood management and mitigation, and flood risk maps provide a quantitative measure of flood risk. Therefore, integration of deep learning – an updated version of machine learning techniques – and multi-criteria decision making (MCDM) models can generate high-resolution flood risk maps. In this study, a novel integrated approach has been developed based on multiplicative long short-term memory (mLSTM) deep learning models and an MCDM ensemble model to map flood risk in the Minab-Shamil plain, southern Iran. A flood hazard map generated by the mLSTM model is based on nine critical features selected by GrootCV (distance to the river, vegetation cover, variables extracted from DEM (digital elevation model) and river density) and a flood inventory map (70% and 30% data were randomly selected as training and test datasets, respectively). The values of all criteria used to assess model accuracy performance (except Cohens kappa for train dataset = 86, and for test dataset = 84) achieved values greater than 90, which indicates that the mLSTM model performed very well for the generation of a spatial flood hazard map. According to the spatial flood hazard map produced by mLSTM, the very low, low, moderate, high and very high classes cover 26%, 35.3%, 20.5%, 11.2% and 7% of the total area, respectively. Flood vulnerability maps were produced by the combinative distance-based assessment (CODAS), the evaluation based on distance from average solution (EDAS), and the multi-objective optimization on the basis of simple ratio analysis (MOOSRA), and then validated by Spearman's rank correlation coefficients (SRC). Based on the SRC, the three models CODAS, EDAS, and MOOSRA showed high-ranking correlations with each other, and all three models were then used in the ensemble process. According to the CODAS-EDAS-MOOSRA ensemble model, 21.5%, 34.2%, 23.7%, 13%, and 7.6% of the total area were classified as having a very low to very high flood vulnerability, respectively. Finally, a flood risk map was generated by the combination of flood hazard and vulnerability maps produced by the mLSTM and MCDM ensemble model. According to the flood risk map, 27.4%, 34.3%, 14.8%, 15.7%, and 7.8% of the total area were classified as having a very low, low, moderate, high, and very high flood risk, respectively. Overall, the integration of mLSTM and the MCDM ensemble is a promising tool for generating precise flood risk maps and provides a useful reference for flood risk management.

High vulnerability of coastal wetlands in Chile at multiple scales derived from climate change, urbanization, and exotic forest plantations

Coastal wetlands are considered one of the most vulnerable ecosystems worldwide; the ecosystem services they provide and the conservation of their biodiversity are threatened. Despite the high ecological and socioenvironmental value of coastal wetlands, regional and national vulnerability assessments are scarce. In this study we aimed to assess the vulnerability of coastal wetlands in Chile from 18°S to 42°S (n = 757) under a multiscale approach that included drivers associated with climate change and land cover change. We assessed multiple drivers of vulnerability at three spatial scales (10 m, 100 m, and 500 m) by analyzing multiple remote sensing data (16 variables) on land cover change, wildfires, climatic variables, vegetation functional properties, water surface and importance for biodiversity. We constructed a multifactorial vulnerability index based on the variables analyzed, which provided a map of coastal wetland vulnerability. Then we explored the main drivers associated with the vulnerability of each coastal wetland by performing a Principal Components Analysis with Agglomerative Hierarchical Clustering, which allowed us to group coastal wetlands according to the drivers analyzed. We found that 42.6 ± 9.2 % of the coastal wetlands evaluated have high or very high vulnerability, with higher vulnerability at the 500 m scale (51.4 %). We identified four groups of coastal wetlands: two located in central Chile, mainly affected by climate change-associated drivers (41.9 ± 2.1 %), and one in central Chile which is affected by land cover change (52.8 ± 6.2 %); the latter has a lower vulnerability level. The most vulnerable coastal wetlands were located in central Chile. Our results present novel findings about the current vulnerability of coastal wetlands, which could be validated by governmental institutions in field campaigns. Finally, we believe that our methodological approach could be useful to generate similar assessments in other world zones.

Geospatial assessment and hydrogeochemical characterization of groundwater resources of Manipur Valley, India.

Spatio-temporal hydrogeochemical assessments of groundwater resources were carried out for the valley region of Manipur in India to investigate its quality status and suitability criteria for irrigational and potable uses. The assessment was carried out for 140 spatially distributed groundwater samples collected during 2018-2021 for pre- and post-monsoon seasons. To assess and comprehend the hydrogeochemical behavior of underlying aquifers and controlling factors for groundwater quality in the region, groundwater quality indices and statistical tools were used. Assessment of in situ parameters such as pH, TDS, salinity, and EC under field conditions reveal that the values exceed concentration in many locations. Most of the samples fall in the category of hard to very hard water. Moreover, observation of both positive and negative oxidation-reduction potential (ORP) and low dissolved oxygen (DO) concentration in groundwater samples indicates aquifers are of recent unstable geologic formations. Similarly, elevated concentrations of F-, Cl-, HCO3-, and Fe3+ greater than the prescribed standards of the World Health Organization in many samples indicate the unsuitability of the groundwater sources for potable uses. The geochemical interactions were found to be dominated and controlled by the rock-weathering geochemical process that contributes to HCO3--Ca2+-type water, followed by HCO3--Na+, Cl--Ca2+, and mixed-type water in both seasons. Spatio-temporal geospatial vulnerable groundwater zone mapping using interpolation techniques carried out in the ArcGIS platform identifies the aquifers based on the water quality and pollution indices. The study's significant findings can provide baseline information that can supplement the government's planning and management initiatives to deal with the current water security challenges in the region as groundwater uses are increasing due to various hydroclimatic phenomena in the state.

A new approach for assessing the assembled vulnerability of coastal aquifers based on optimization models

Developing Assembled Vulnerability (AV) maps is essential for preventing environmental issues corresponding to the groundwater conditions in aquifers that are exposed to multiple contaminants from multiple origins. There is a research gap in the application of multiple models to produce the AV map of aquifers with two or more origins of contaminant. This study fills this knowledge gap by considering two objectives using the non-dominated sorting genetic algorithm-II (NSGA-II) multi-objective optimization approach to evaluate the vulnerability of coastal urban aquifers to wastewater and seawater intrusion contamination for the first time in the literature. For this purpose, the DRASTICA-GA and GALDIT-GA groundwater vulnerability models as individual models have been combined using NSGA-II to produce the AV maps as multiple models. In this step, two states are considered to produce the AV map: (1) The NSGA-II multi-objective optimization model aims to maximize the correlation coefficients between nitrate (NO3) and AV as well as total dissolved solids (TDS) and AV, and (2) A qualitative index obtained by data fusion (DF) is used in the NSGA-II model to produce the AV map. Finally, to prove the efficiency and applicability of the proposed framework, it is applied to an important aquifer in Oman, the Al Khoudh aquifer, which shows that the north of the Al Khoudh aquifer is more vulnerable than other parts exposed to wastewater and seawater intrusion contamination. In addition, results indicate that the presented methodology can accurately define the AV indices to identify the vulnerable areas corresponding to the different contamination origins. Moreover, the ROC/AUC criteria for the AV-NSGA-II-DF are more than the AV-NSGA-II, which are 0.962 and 0.956, respectively.

Identifying flood vulnerable and risk areas using the integration of analytical hierarchy process (AHP), GIS, and remote sensing: A case study of southern Oromia region

Many people have died, and economies have been devastated by flooding, which is one of the world's most prevalent and catastrophic natural catastrophes. As a result of human activity on the land, the flooding patterns have changed. Inadequate drainage infrastructures, as well as various activities such as deforestation, are exacerbating the flood. In Ethiopia, southern Oromia is one of the regions affected by flooding, with the West Guji and Guji zones being the most frequently flooded places. People are exploiting natural vegetation for various purposes as a result of rapid population growth, resulting in deforestation and susceptibility to natural disasters such as floods. As a result, identifying flood-prone locations in great detail is essential for effective issue-solving. Thus, the study aims to locate and map flood-prone and flood-risk regions in southern Oromia utilizing Remote Sensing, analytical hierarchy Process (AHP), and Geographic Information system (GIS). Eight flood-causing factors, such as drainage density, rainfall, elevation, slope, Topographic wetness index (TWI), soil type, distance from the river, and LULC were developed in the GIS environment, and ERDAS Imagine software was employed to make land coverage and land usage data. The weighted overlay Multi-criteria evaluation (MCE) approach was then used to construct a flood-sensitive map based on the AHP pairwise comparison of eigenvector value. To determine flood risk, population density, a vulnerable flood map, and land usage/land coverage layer were overlaid, having equal weightage. The flooding vulnerability outcome in southern Oromia indicates that 0.3% (20.53km2), 31.4% (24,986.4km2), 62% (49,310.6km2), 6.39% (5081.98km2), and 0.19% (148.866) is, very high, high, moderate, low, and very low flooding vulnerable region correspondingly. From the flood risk map, it was estimated that 2% (1587.3km2), 19.3% (15,384.4km2), 75.5% (60,071.7km2), and 3.15% (2505.3km2) of the area were endangered to very high, high, moderate, and low, flood risk levels correspondingly. As a result, the study will assist the relevant authorities in formulating development policies based on the area's existing flood danger and risk.

Analyzing spatial vulnerability in cities by combining the analytic hierarchy process and geographic information systems: The case of Vitoria-Gasteiz, Spain

ABSTRACT Vulnerability in urban areas has been on the rise following the global political and economic restructuring processes that have taken place since the 1980s. This increase in vulnerability has sparked a growing awareness of the need to understand the impact of these processes on the most vulnerable neighborhoods and areas of cities so as to develop effective policy responses. Although this vulnerability has become more evident in larger cities, this casuistry can also be seen in medium-sized cities. This paper examines the level of vulnerability of different neighborhoods in the medium-sized European city of Vitoria-Gasteiz (Basque Country, Spain), using a methodological approach which combines the analytic hierarchy process and geographic information systems, based on a number of indicators for different economic, demographic and migratory status-related dimensions. The results reveal a synthetic map of the vulnerability of neighborhoods in Vitoria-Gasteiz that shows an uneven impact of structural processes and policy initiatives implemented over decades. The paper concludes that synthetic maps of vulnerability make it possible to show the different realities in the urban framework and can contribute to defining public interventions tailored to these specific problems.

Analysis of the Socio-Economic vulnerability of coastal area of Leupung District, Aceh Besar

The purpose of this study is to assess the status of socio-economic vulnerability in the coastal area of Leupung sub-district, Aceh Besar district. The assessment was carried out by applying six indicators of vulnerability, namely income per capital, asset ownership, green belt area, population density, education level, and local wisdom using the SEVI (Social Economic Vulnerability Index) method. These indicators were then analyzed and described in the form of vulnerability maps using GIS applications to get a clear picture of the socio-economic conditions of communities in the form of thematic maps. The results of the study indicate that the green belt in several villages in the Leupung area has a high vulnerability status, then asset ownership, population density, and income per capita are included in the vulnerable category. Meanwhile, the local wisdom and education level of the community is generally in low to moderate vulnerability status. The results also indicate that the status of vulnerability in the sub-district of Leupung tends to lead to high vulnerability if coastal management does not anticipate these possibilities.

Multi-Criteria Analysis Method for Aquifer Vulnerability Investigation Using Godt Method at Idi-Ayunre, Ibadan, Southwestern Nigeria

Geophysical investigation involving Vertical Electrical Sounding (VES) Schlumberger array was carried out across Idi-Ayunre, Ibadan, a typical basement complex area having a rock composition of migmatite-gneiss, quartzite, and biotite-hornblende. A total of forty (40) vertical electrical sounding data were acquired with maximum current electrode separation of 100m using resistivity meter and its accessories. The aim of the study was to evaluate the aquifer vulnerability of the study area to contamination. The VES results were both qualitatively and quantitatively interpreted using partial curve matching and were further subjected to computer iteration using WINRESIST. The longitudinal conductance, thickness of layer overlying aquifer and hydraulic conductivity were generated and synthesized to produce the vulnerability map. A GODT multi-criteria model which is an acronym of Groundwater occurrence, Overburden thickness, Depth and Topography developed from the hydrogeologic parameters were evaluated alongside the longitudinal conductance values to determine the aquifer vulnerability of the area and to classify the study area accordingly. The curve type obtained are H and HA. The interpretation revealed three to four geoelectric layers: the topsoil (18.9-178.9Ωm), clayey (9.0-70.6Ωm), fractured basement (31.9-43.1Ωm) and fresh basement (1131-2916Ωm). The longitudinal unit conductance ranges from 0.032-0.93mhos. And from the GODT model derivations, the study area shows 92.5% of high vulnerability rating, 2.5% of low-moderate and 5% of moderate rating; areas with high rating are prone to contamination than areas with low-moderate and moderate rating. Hence, zones of high vulnerability may be not be encouraged for groundwater exploitation and, if need be, constant water quality assessment should be carried out before consumption.

APPORT DE LA GEOMATIQUE ALA DELIMITATION DES PERIMETRES DE PROTECTION AUTOUR DE LA PRISE DEAUPOUR LALIMENTATION EN EAU POTABLE SUR LA RIVIERE ME A KONGOFON (SUD EST DE LA COTE DIVOIRE)

The quality of the Me Rivers water is threatened by sources of pollution generated in the region without any measures being taken to protect this resource.So, to reduce the risk of pollution of this water resource, this study aims to delimit the protection perimeters around the water intake on the river.The methodological approach consisted firstly in assessing the vulnerability of the resource through the weighting and combination of five selected parameters, and then in determining the protection perimeters on the basis of the pre-established vulnerability map and data from previous studies.The pollution vulnerability map obtained reveals five classes of vulnerability around the water intake, with a dominance of the high class estimated at 29.44% of the watershed. Three protection perimeters have been defined. The immediate protection perimeter has a 200 m radius around the water intake and covers areas with a strong influence on the rivers vulnerability to pollution over a surface area of 1.97 km2.The close protection perimeter, covering a 1000 m radius, was delimited from the immediate protection perimeter. It covers an area of 43.7 km2 and takes into account the rivers low, medium and very high vulnerability classes, following the direction of water flow in the Me watershed.The remote protection perimeter covers a large part of the watershed, with an area of 1,480 Km2. It covers the rest of the catchments highly vulnerable areas and adjoins the close protection perimeter.The defined protection perimeters can serve as a guide for sustainable management and protection of river quality.

Zoning of Social Vulnerability for Tidal Flood Disaster in Medan Belawan District, Medan City Based on Remote Sensing and Geographic Information Systems

This study aims to 1) identify the social vulnerability of tidal floods in Medan Belawan District and 2) produce a zoning map of social vulnerability to tidal floods in Medan Belawan District descriptive quantitative type research. The variable used refers to Regulation of the Head of BNPB No. 2 of 2012 with changes covering population density, sex ratio, ratio of persons with disabilities, land use, and existing tidal flooding. The social vulnerability variable is then classified using a scoring technique. Data collection techniques in this study were document studies of secondary data obtained from various agencies. The results showed that five urban villages (83%) in Medan Belawan District had high tidal flood social vulnerability, and only one urban town (17%) was classified as having moderate social vulnerability. The urban villages with high tidal flood social vulnerability are Bagan Deli urban village, Belawan Bahagia urban village, Belawan Bahari urban village, Belawan I urban village, and Belawan II urban village. Meanwhile, the urban village with a moderate level of social vulnerability to tidal floods is the Belawan Sicanang Village. Belawan I Village occupies the highest tidal flood social vulnerability class, and the lowest tidal flood social vulnerability class is populated by Belawan Sicanang urban village.Keywords: Social Vulnerability, Tidal Flood, Disaster 

Analysis of Ground Subsidence Vulnerability in Urban Areas Using Spatial Regression Analysis

The main cause of ground subsidence accidents in urban areas is cavities formed by damage to underground utilities. For this reason, the attribute information of underground utilities should be used to prepare against ground subsidence accidents. In this study, attribute information (pipe age, diameter, burial depth, and density) of six types of underground utilities (water, sewer, gas, power, heating, and communication) and history information of ground subsidence were collected. A correlation analysis was conducted using the collected data, and a prediction model of vulnerability to ground subsidence was developed through the ordinary least squares (OLS) method and spatial regression analysis (spatial lag model (SLM) and spatial error model (SEM)). To do this, the target area was divided into a grid of 100 m × 100 m. Datasets were constructed using the attribute information of underground utilities included in the divided grid and the number of ground subsidence occurrences. To analyze the OLS of the constructed data, the variance inflation factor (VIF) of the attribute information of underground utilities was studied. An OLS analysis was conducted using the appropriate factors, and the results show that the spatial data were autocorrelated. Subsequently, SEM and SLM analyses, which were spatial regression analyses, were conducted. As a result, the model using SLM was selected as suitable for analyzing the vulnerability of ground subsidence, and the density of six types of underground utilities was found to be the highest influencing factor. In addition, a vulnerability map of ground subsidence in the target area was prepared using the model. The vulnerability map demonstrates that regions with frequent ground subsidence can be predicted to be highly vulnerable.

Nutritional composition of least-cost staple food sources of nutrients in Eastern Uganda

Food cost and seasonal availability are important determinants of food choice and ultimately nutrient intake. This study aimed at establishing the nutritional composition of least-cost staple food sources of nutrients in Kamuli, Buyende and Pallisa districts in eastern Uganda across the cropping seasons. The World Food Programme (WFP) Vulnerability Analysis and Mapping (VAM) Market Analysis Tool guidelines were used to conduct a mini-survey to determine seasonal prices and availability of foods. Retailers (n= 268) from six markets in Kamuli, three in Buyende and six in Pallisa were interviewed. The least-cost sources of energy, protein, iron and zinc were determined using nutrient-cost values. The nutrient composition of the least-cost foods were determined using standard methods. For the first dry season, the least cost sources of energy, protein, iron and zinc were maize (0.052 $/1000kcal), soybeans (0.016 $/10g), maize (0.070 $/10mg) and maize (0.086 $/10mg), respectively. For the second dry season, the least cost sources of energy, protein, iron and zinc were maize (0.052 $/1000kcal), soybeans (0.015 $/10g), maize (0.070 $/10mg) and maize (0.086 $/10mg). For the first rainy season, the least cost source of energy was sorghum (0.074 $/1000kcal), protein was groundnuts (0.019 $/10g), iron was sesame (0.100 $/10mg) and zinc was sweet potatoes (0.123 $/10mg), respectively. For the second rainy season, the least cost sources of energy, protein, iron and zinc were sorghum (0.049 $/1000kcal), groundnuts (0.016 $/10g), sesame (0.067 $/10mg) and sweet potatoes (0.082 $/10mg), respectively. The richest sources of energy, sugars and starch, protein, fat, fibre and iron were sesame (797.2 ± 116.84 Kcal/100g), sweet potatoes (11.5 ± 1.22 and 86.8 ± 10.75 g/100g), soybeans (40.7 ± 4.58 g/100g), sesame (52.9 ± 3.82 g/100g), soybeans (7.0 ± 0.32 g/100g), groundnuts (7.0 ± 0.82 mg/g). The nutrition composition of least-cost foods in the dry seasons and rainy seasons indicates that they can be used to formulate low-cost nutrient-dense mixtures for the respective seasons. Key words: Uganda, cropping seasons, least-cost, energy, protein, iron, zinc

FLOOD RISK OF GRASSLANDS IN THE MOUNTAIN AREA OF WESTERN ROMANIA

Floods, some of the most destructive natural phenomena, are occurring with increasing frequency, against the backdrop of climate change in recent years. Floods affect both built spaces and natural areas, implicitly the lands used as grasslands. In the context outlined above, the purpose of this study is to identify grasslands susceptible to being affected by floods and to group and map them according to the intensity of the manifestation of the flood risk. For the flood risk assessment, both for the entire analyzed area and for the grassland areas, in the GIS environment, seven factors (spatialized in raster format) determining the occurrence of floods were taken into account: land use, altitude, slope, drainage density, rainfall, distance to rivers and distance to roads. The flood vulnerability map of the analyzed territory, implicitly of the grassland areas, obtained by summing up and the weighted participation of the seven variables, was reclassified into five risk classes/areas: no risk or very low risk, low risk, medium risk, high risk and very high risk. It has been shown that the most vulnerable are the surfaces located on land with low slopes, located at low altitudes and in the proximity of water courses. Regarding the areas of grasslands, 50% fall into the classes without flood risk, with very low and low risk, 28% in the moderate risk class, 16% present a high risk and 6% of the grasslands are classified in the risk class very high to floods. From the point of view of practical applicability, it is important to identify and map the grasslands at risk of flooding, so that measures can be taken to mitigate the destructive effects.

A novel approach for assessing flood risk with machine learning and multi-criteria decision-making methods

Hazardous flooding occurs across most climate zones. Owing to the lack of appropriate infrastructures and applicable predictive methods, flooding in arid and semi-arid regions may be especially damaging. Based on a study of Abarkuh County, Iran, we introduce an integrated approach for identifying high-priority flood risk areas using machine learning (ML) and multi-criteria decision-making (MCDM) methods, which is transferable to other (semi)arid regions. Results indicate that among the ML models we examined—including classification and regression tree (CART), mixture discriminant analysis (MDA), and support vector machine (SVM)—the SVM model performs best. We estimate that 75% of the study area is subject to high or very flood hazard. Our application of the Jackknife technique identifies precipitation, vegetation, and drainage density as the most important conditional factors for regional flood hazards. Our analytical network process (ANP)-decision making trial and evaluation laboratory (DEMATEL) results reveal that population density and agricultural area density have the greatest influence on flood vulnerability. Results integrating SVM and ANP-DEMATEL flood hazard and vulnerability maps indicate that 6% of the study area is at high or very high flood risk. Application of this approach can assist local authorities in identifying priority areas for flood management interventions.

Mapping spatial morbidity patterns for bronchiolitis related to socioeconomic estimators: A spatial epidemiology approach to identify health disparities in Puerto Madryn, Argentina.

To describe the frequency of hospitalizations of infants under 1 year of age with bronchiolitis in Puerto Madryn, Argentina, and to study the spatial distribution of cases throughout the city in relation to socioeconomic indicators. To visualize and better understand the underlying processes behind the local manifestation of the disease by creating a vulnerability map of the city. We performed a cross-sectional study of all patients discharged for bronchiolitis from the local public Hospital in 2017, considering length of hospital stay, readmission rate, patient age, home address and socioeconomic indicators (household overcrowding). To understand the local spatial distribution of the disease and its relationship to overcrowding, we used GIS and Moran's global and local spatial autocorrelation indices. The spatial distribution of bronchiolitis cases was not random, but significantly aggregated. Of the 120 hospitalized children, 100 infants (83.33%) live in areas identified as having at least one unsatisfied basic need (UBN). We found a positive and statistically significant relationship between frequency of cases and percentage of overcrowded housing by census radius. A clear association was found between bronchiolitis and neighborhoods with UBNs, and overcrowding is likely to be a particularly important explanatory factor in this association. By combining GIS tools, spatial statistics, geo-referenced epidemiological data, and population-level information, vulnerability maps can be created to facilitate visualization of priority areas for development and implementation of more effective health interventions. Incorporating the spatial and syndemic perspective into health studies makes important contributions to the understanding of local health-disease processes.

Groundwater vulnerability assessment of typical covered karst areas in northern China based on an improved COPK method

Karst in China is characterized by a wide distribution, diverse forms, well-developed features, and excellent preservation, making it a representative example on a global scale. The semi-arid karst in northern China, widely distributed in many provinces, has unique hydrogeological features, including covered karst, weak karst development, thick aquifers, highly interconnected fissure network, and numerous karst springs, making it difficult to directly apply the COP method which is widely used in karst groundwater vulnerability assessment in this area. Additionally, the quality of the karst groundwater in many northern China cities is facing a threat in recent years, making it urgent to evaluate the vulnerability of the karst groundwater. This study aims to develop an improved COPK method for the covered karst groundwater vulnerability assessment modified from the widely used COP method, and to use it in the Baotu Spring basin in Jinan City, as a typical representative of the covered karst area in northern China. The assessment result by the improved COPK method shows that most of the study area exhibits moderate to low karst groundwater vulnerability, and the area with very high to high vulnerability is situated in the Middle Ordovician-Upper Cambrian Chaomidian Formation limestone exposed area. The above results by the improved COPK method are more consistent with the hydrogeological conditions than those by the original COP method. A comparison of nitrate contamination map to the groundwater vulnerability map reveals the more efficient performance of the improved COPK method compared to the original COP method in vulnerability assessment of the typical covered karst areas in northern China. This paper can provide a reference for karst groundwater vulnerability assessment of covered karst areas in northern China, as well as other countries and regions with similar hydrogeological conditions, which can provide valuable support for groundwater pollution control efforts.

Groundwater vulnerability assessment to pollution using GIS-based DRASTIC and GOD methods in Araihazar upazila of Narayanganj district, Bangladesh

A groundwater vulnerability map is a preliminary way to assess the risk of groundwater pollution from a variety of sources and across a range of geological and hydrological contexts. With rapid urbanization and industrialization, the possibility of groundwater contamination has greatly increased in Bangladesh. The focus of this study is on an industrialized peri-urban area in Bangladesh, where the regional aquifer has already been depressurized owing to pumping to fulfill the ascending municipal and industrial water demand of the Dhaka megacity and adjacent areas. Two vulnerability index maps were created utilizing a Geographic Information System (GIS) and the contamination risk indices DRASTIC (Depth to water table (D), Net recharge (R), Aquifer media (A), Soil media (S), Topography (T), Impact of vadose zone (I) and hydraulic Conductivity of the aquifer (C)) and GOD (Groundwater or hydraulic confinement in the aquifer under consideration (G), Overlying strata in terms of lithological characters that determine the pollutant attenuation capacity (O) and Depth to groundwater (D)). Vulnerabilities varied greatly over the study area. The DRASTIC analysis identified three vulnerability classes: one-fifth of the area exhibited high vulnerability, more than half of the study area showed moderate vulnerability and rest of the area is low in vulnerability. In contrast, GOD analysis was somewhat conservative, showed two classes where vulnerability was negligible in 58% of the study area and low in the rest of the area. The study also generated hot-spot maps of potential surface contamination for each vulnerability map by overlapping the potentially hazardous activity layer which corresponds to areas with higher industrial clusters. Human activities that commonly cause groundwater pollution need to be constrained by utilizing groundwater protection strategies in the identified vulnerable areas to ensure sustainable development.

Evaluating the ecological vulnerability of Chongqing using deep learning.

This study used deep learning to evaluate the ecological vulnerability of Chongqing, China, discuss the deep learning evaluations of ecological vulnerability, and generate vulnerability maps that support local ecological environment protection and governance decisions and provide reference for future studies. The information gain ratio was used to screen the influencing factors, selecting 16 factors that influence ecological vulnerability. Deep neural network (DNN) and convolutional neural network (CNN) methods were used for modeling, and two ecological vulnerability maps of the study area were generated. The results showed that the mean absolute error and root mean square error of the DNN and CNN models were relatively small, and the fitting accuracy was high. The area under the receiver operating characteristic curve of the CNN model was 0.926, which was better than that of the DNN model (0.888). Random forest was applied to calculate the importance of the influencing factors in the two models. Because the main factor was geological features, the relative ecological vulnerability was mainly affected by karst topography. Through the analysis of the ecological vulnerability map, the areas with higher vulnerability are the karst mountains of Dabashan, Wushan, and Qiyaoshan in the northeast and southeast, as well as the valley between mountains and cities in the center and west of the study area. According to the investigation of these areas, the primary ecological problems are low forest quality, structural irregularities caused by self-geological factors, severe desertification, and soil erosion. Human activity is also an important factor that causes ecological vulnerability in the study area. In conclusion, deep learning, particularly CNN models, can be used for ecological vulnerability assessments. The ecological vulnerability maps conformed to the basic cognition of field surveys and can provide references for other deep learning vulnerability studies. While the overall vulnerability of the study area is not high, ecological problems that lead to its vulnerability should be addressed by future ecological protection and management measures.

Modeling assessment of groundwater vulnerability to contamination risk in a typical basement terrain using TOPSIS-entropy developed vulnerability data mining technique

This study involved a comparative analysis in the groundwater vulnerability domain, which is a crucial component of groundwater management decision support systems (DSS). This was achieved by creating models that covered the range of algorithms from the subjective to the data-driven. The study was conducted in a basement complex area. Databases of climatic, remote sensing, and geophysical datasets were created using varieties of data acquisition techniques. The datasets included in this assessment were: rainfall (R), land use (LU), bedrock topography (BT), recharge rate (Re), and slope (S). The slope and rainfall were determined to have the highest (0.78) and lowest (0.01) weighted factors, respectively, using the entropy method. For the development of the TOPSIS-Entropy model algorithm, the weights results were combined with the TOPSIS outranking method. To generate the Groundwater Vulnerability Model map of the study area, the hybrid model was applied to griddled raster layers of the factors. Also, the TOPSIS and Entropy-WLA model algorithms were also explored and used to generate groundwater vulnerability maps. The TOPSIS-Entropy algorithms produced an accuracy of 70%, while TOPSIS and Entropy-WLA produced accuracy of 50 and 47%, respectively. The resulting model maps were validated by using correlation technique on the produced map and the longitudinal conductance map of the study area. The TOPSIS-Entropy, which followed an object-oriented model pattern, demonstrates greater accuracy and has the potential to provide appropriate insights and alternatives to decision-making in the field of groundwater hydrology in the study area and other regions of the world with comparable geology.

Flood Vulnerability Mapping and Risk Assessment Using Hydraulic Modeling and GIS in the Tamanrasset Valley Watershed, Algeria

Flood Vulnerability Mapping and Risk Assessment Using Hydraulic Modeling and GIS in the Tamanrasset Valley Watershed, Algeria