Search

This study examined the spatiotemporal climate variability over the Ceyhan River basin in Southern Anatolia, Türkiye using historical rainfall and temperature observations recorded at 15 meteorology stations. Various statistical and geostatistical techniques were employed to determine the significance of trends for each climatic variable in the whole basin and its three sub-regions (northern, central, and southern regions). The results revealed that the recent years in the basin were generally warmer compared with previous years, with a temperature increase of approximately 4 °C. The standardized temperature index analysis indicated a shift towards hotter periods after 2005, while the coldest periods were observed in the early 1990s. The spatial distribution of temperature showed non-uniform patterns throughout the basin. The first decade of the study period (1975–1984) was characterized by relatively cold temperatures, followed by a transition period from cold to hot between 1985 and 2004, and a hotter period in the last decade (2005–2014). The rainfall analysis indicated a decreasing trend in annual rainfall, particularly in the northern and central regions of the basin. However, the southern region showed an increasing trend in annual rainfall during the study period. The spatial distribution of rainfall exhibited considerable variability across the basin, with different regions experiencing distinct patterns. The standardized precipitation index analysis revealed the occurrence of multiple drought events throughout the study period. The most severe and prolonged droughts were observed in the years 1992–1996 and 2007–2010. These drought events had significant impacts on water availability and agricultural productivity in the basin.

Floods can cause severe damage in urban environments. In regions lacking hydrological and hydraulic data, spatial urban flood modeling and mapping can enable city authorities to predict the intensity and spatial distribution of floods. These predictions can then be used to develop effective flood prevention and management plans. In this doctoral thesis, flood inventory data for Mazandaran, Iran were prepared based on historical and field survey data from the Sari and Amol municipalities and the regional water company. Flood risk maps were produced using several machine learning (ML) algorithms: GARP, QUEST, RF, j48DT, CART, LMT, ANN-SGW, SVM, MAXENT, BRT, MARS, GLM, GAM, Ensemble, MLPNN, and MultiB-MLPNN models. The flood influencing factors used in modeling were precipitation, slope, curve number, distance to river, distance to channel, depth to groundwater, land use, and elevation. Two equal sets of points were identified randomly for both categories of flooded and non-flooded areas. Therefore, 113 (for Sari city) and 118 (for Amol city) locations for each category were identified. Each set is divided into training (70%) and testing (30%) groups. The flood locations were assigned a value of 1, and non-flood locations were assigned a value of 0. Different conditioning factors, including urban density, quality of buildings, age of buildings, population density, and socio-economic conditions were considered to analyze urban flood vulnerability. Several confusion matrix criteria were applied to evaluate the accuracy of the ML algorithms. The results demonstrated that the ANN-SGW (as the optimized model), GARP (as the standalone model), Ensemble (BRT, MARS, GLM, and GAM), and MultiB-MLPNN models (as the hybridized model) had the highest performance accuracy, with area under the curve (AUC) values of 0.963, 0.935, 0.925, and 0.847 respectively. The results also indicated that distance to channel played a major role in flood hazard determination, whereas populat, Tiivistelmä Tulvat voivat aiheuttaa vakavia vahinkoja kaupunkiympäristössä. Alueilla, joista hydrologisia ja hydraulisia tietoja ei ole kattavasti saatavilla, kaupunkitulvien alueellinen mallinnus ja kartoitus avaavat mahdollisuuden viranomaisille arvioida tulvien alueellista jakautumista ja voimakkuutta. Mallinnus auttaa päätöksentekijöitä kehittämään toimivia tulvien ehkäisy- ja hallintasuunnitelmia. Tässä tutkimuksessa tulvainventointitiedot laadittiin Sarin ja Amolin kuntien sekä Iranin Mazandaranin vesiyhtiön historiallisten ja kenttätutkimusten tietojen perusteella. Tulvariskikarttoja tuotettiin useilla koneoppimisalgoritmeillä: GARP, QUEST, RF, j48DT, CART, LMT, ANN-SGW, SVM, MAXENT, BRT, MARS, GLM, GAM, Ensemble, MLPNN, ja MultiB-MLPNN mallit. Mallinnuksessa käytettyjä tulviin vaikuttavia tekijöitä olivat sadanta, maanpinnan kaltevuus, käyrän numero, etäisyys jokeen, etäisyys kanavaan, etäisyys pohjaveden pintaan, maankäyttö ja maanpinnan korkeus. Kaksi samanlaista pistejoukkoa tunnistettiin satunnaisesti sekä tulvivalla että tulvattomalla alueella ja siksi kullekin luokalle tunnistettiin 113 (Sarin kaupunki) ja 118 (Amolin kaupunki) sijaintia. Jokainen sarja on jaettu koulutusryhmiin (70 %) ja testausryhmiin (30 %). Tulvapaikoille määritettiin arvo 1 ja tulvattomille arvo 0. Kaupunkien tulvahaavoittuvuuden analysoinnissa arvioitiin erilaisia tekijöitä, kuten rakennustiheys, rakennusten laatu, rakennusten ikä, väestötiheys ja sosioekonomiset olosuhteet. ML-algoritmien tarkkuuden arvioimiseksi käytettiin useita sekaannusmatriisikriteerejä. Tulokset osoittivat, että ANN-SGW (optimoitu malli), GARP (erillisenä mallina), yhdistelmä-ensemble (BRT, MARS, GLM ja GAM) ja MultiB-MLPNN-mallit (hybridimallina) tuottivat muita paremman suorituksen tarkkuuden, AUC=0.963, AUC=0.935, AUC=0.925 ja AUC=0.847, edellä mainitussa järjestyksessä. Tulokset osoittivat myös, että etäisyys kanavaan oli tärkeässä asemassa tulvariskien määrittämisessä, kun taas väestötiheys oli haavoi

In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models., QC 20220308

Lake water level fluctuation is a function of hydro-meteorological components, namely input, and output to the system. The combination of these components from in-situ and remote sensing sources has been used in this study to define multiple scenarios, which are the major explanatory pathways to assess lake water levels. The goal is to analyze each scenario through the application of the water balance equation to simulate lake water levels. The largest lake in Iran, Lake Urmia, has been selected in this study as it needs a great deal of attention in terms of water management issues. We ran a monthly water balance simulation of nineteen scenarios for Lake Urmia from 2003 to 2007 by applying different combinations of data, including observed and remotely sensed water level, flow, evaporation, and rainfall. We used readily available water level data from Hydrosat, Hydroweb, and DAHITI platforms; evapotranspiration from MODIS and rainfall from TRMM. The analysis suggests that the consideration of field data in the algorithm as the initial water level can reproduce the fluctuation of Lake Urmia water level in the best way. The scenario that combines in-situ meteorological components is the closest match to the observed water level of Lake Urmia. Almost all scenarios showed good dynamics with the field water level, but we found that nine out of nineteen scenarios did not vary significantly in terms of dynamics. The results also reveal that, even without any field data, the proposed scenario, which consists entirely of remote sensing components, is capable of estimating water level fluctuation in a lake. The analysis also explains the necessity of using proper data sources to act on water regulations and managerial decisions to understand the temporal phenomenon not only for Lake Urmia but also for other lakes in semi-arid regions.

In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models.

River regulation is challenging when there is diverse upstream and downstream interest, leading to regional and international conflict. However, quantifying the upstream-downstream flow regime changes and their causes are given less consideration in the river basin. In this study, we presented three new ratios for downstream-upstream low flow contribution (DUL), downstream-upstream high flow contribution ratio (DUH), and meteorological-hydrological drought ratio (MHD), for an integrated assessment of flow regime alteration across the river basin. To test the methods, we compared flow regime alteration upstream and downstream in the Ceyhan basin in central Turkey, which was significantly modified by agriculture between 1984 and 2018 (the irrigated area increased 2.8-fold, rainfed farming decreased by 67.6%). Our analysis revealed a clear change in the contribution of low and high flow seasons to annual flow in the last station of the river at Misis after 1984, but no considerable change in upstream tributaries. In the last decade (2005–2014) and the second half (1995–2014) of the study, the frequency of hydrological droughts increased, while meteorological droughts followed a stationary pattern. Evaluation of the impact of anthropogenic activities on river regime (by comparing flow regime characteristics after 1984 with those from 1975 to 1984 as post- and pre-impact periods) revealed low to incipient impact upstream (Hanköy, Karaahmet, and Kadirli river headwaters), severe impact below the Aslantaş dam in the basin center, and moderate impact at the last station on the Ceyhan river. The new metrics provide supplementary information on the flow regime alteration in the basin and can be introduced as a novel quantitative measure to recognize the driving factor of droughts.

Accurate modeling and prediction of suspended sediment load (SSL) in rivers have an important role in environmental science and design of engineering structures and are vital for watershed management. Since different parameters such as rainfall, temperature, and discharge with the different lag times have significant effects on the SSL, quantifying and understanding nonlinear interactions of the sediment dynamics has always been a challenge. In this study, three soft computing models (multilayer perceptron (MLP), adaptive neuro-fuzzy system (ANFIS), and radial basis function neural network (RBFNN)) were used to predict daily SSL. Four optimization algorithms (sine–cosine algorithm (SCA), particle swarm optimization (PSO), firefly algorithm (FFA), and bat algorithm (BA)) were used to improve the capability of SSL prediction of the models. Data from gauging stations at the mouth of the Kasilian and Talar rivers in northern Iran were used in the analysis. The selection of input combinations for the models was based on principal component analysis (PCA). Uncertainty in sequential uncertainty fitting (SUFI-2) and performance indicators were used to assess the potential of models. Taylor diagrams were used to visualize the match between model output and observed values. Assessment of daily SSL predictions for Talar station revealed that ANFIS-SCA yielded the best results (RMSE (root mean square error): 934.2 ton/day, MAE (mean absolute error): 912.2 ton/day, NSE (Nash–Sutcliffe efficiency): 0.93, PBIAS: 0.12). ANFIS-SCA also yielded the best results for Kasilian station (RMSE: 1412.10 ton/day, MAE: 1403.4 ton/day, NSE: 0.92, PBIAS: 0.14). The Taylor diagram confirmed that ANFIS-SCA achieved the best match between observed and predicted values for various hydraulic and hydrological parameters at both Talar and Kasilian stations. Further, the models were tested in Eagel Creek Basin, Indiana state, USA. The results indicated that the ANFIS-SCA model reduced RMSE by

Spatial information on flood risk and flood-related crop losses is important in flood mitigation and risk management in agricultural watersheds. In this study, loss of water bound in agricultural products following damage by flooding was calculated using water footprint and agricultural statistics, using the Talar watershed, northern Iran, as a case. The main conditioning factors on flood risk (flow accumulation, slope, land use, rainfall intensity, geology, and elevation) were rated and combined in GIS, and a flood risk map classified into five risk classes (very low to very high) was created. Using average crop yield per hectare, the amount of rice and wheat products under flood risk was calculated for the watershed. Finally, the spatial relationships between agricultural land uses (rice and wheat) and flood risk areas were evaluated using geographically weighted regression (GWR) in terms of local R² at sub-watershed scale. The results showed that elevation was the most critical factor for flood risk. GWR results indicated that local R² between rice farms and flood risk decreased gradually from north to south in the watershed, while no pattern was detected for wheat farms. Potential production of rice and wheat in very high flood risk zones was estimated to be 7972 and 18,860 tons, on an area of 822 ha and 7218 ha, respectively. Loss of these crops to flooding meant that approximately 34.04 and 12.10 million m³ water used for production of wheat and rice, respectively, were lost. These findings can help managers, policymakers, and watershed stakeholders achieve better crop management and flood damage reduction.

In regions with lack of hydrological and hydraulic data, a spatial flood modeling and mapping is an opportunity for the urban authorities to predict the spatial distribution and the intensity of the flooding. It helps decision-makers to develop effective flood prevention and management plans. In this study, flood inventory data were prepared based on the historical and field surveys data by Sari municipality and regional water company of Mazandaran, Iran. The collected flood data accompanied with different variables (digital elevation model and slope have been considered as topographic variables, land use/land cover, precipitation, curve number, distance to river, distance to channel and depth to groundwater as environmental variables) were applied to novel hybridized model based on neural network and swarm intelligence-grey wolf algorithm (NN-SGW) to map flood-inundation. Several confusion matrix criteria were used for accuracy evaluation by cutoff-dependent and independent metrics (e.g., efficiency (E), positive predictive value (PPV), negative predictive value (NPV), area under the receiver operating characteristic curve (AUC)). The accuracy of the flood inundation map produced by the NN-SGW model was compared with that of maps produced by four state-of-the-art benchmark models: random forest (RF), logistic model tree (LMT), classification and regression trees (CART), and J48 decision tree (J48DT). The NN-SGW model outperformed all benchmark models in both training (E = 90.5%, PPV = 93.7%, NPV = 87.3%, AUC = 96.3%) and validation (E = 79.4%, PPV = 85.3%, NPV = 73.5%, AUC = 88.2%). As the NN-SGW model produced the most accurate flood-inundation map, it can be employed for robust flood contingency planning. Based on the obtained results from NN-SGW model, distance from channel, distance from river, and depth to groundwater were identified as the most important variables for spatial prediction of urban flood inundation. This work can serve as a basis for future stud

QC 20210127

Export Date: 3 January 2021; Article; CODEN: JCROE; Correspondence Address: Tien Bui, D.; Institute of Research and Development, Duy Tan UniversityViet Nam; email: buitiendieu@duytan.edu.vn

Land degradation (LD) is a complex process affected by both anthropogenic and natural driving variables, and its prevention has become an essential task globally. The aim of the present study was to develop a new quantitative LD mapping approach using machine learning techniques, benchmark models, and human-induced and socio-environmental variables. We employed four machine learning algorithms [Support Vector Machine (SVM), Multivariate Adaptive Regression Splines (MARS), Generalized Linear Model (GLM), and Dragonfly Algorithm (DA)] for LD risk mapping, based on topographic (n = 7), human-induced (n = 5), and geo-environmental (n = 6) variables, and field measurements of degradation in the Pole-Doab watershed, Iran. We assessed the performance of different algorithms using receiver operating characteristic, Kappa index, and Taylor diagram. The results revealed that the main topographic, geoenvironmental, and human-induced variable was slope, geology, and land use change, respectively. Assessments of model performance indicated that DA had the highest accuracy and efficiency, with the greatest learning and prediction power in LD risk mapping. In LD risk maps produced using SVM, GLM, MARS, and DA, 19.16%, 19.29%, 21.76%, and 22.40%, respectively, of total area in the Pole-Doab watershed had a very high degradation risk. The results of this study demonstrate that in LD risk mapping for a region, topographic, and geological factors (static conditions) and human activities (dynamic conditions, e.g., residential and industrial area expansion) should be considered together, for best protection at watershed scale. These findings can help policymakers prioritize land and water conservation efforts.

Machine learning models have attracted much research attention for groundwater potential mapping. However, the accuracy of models for groundwater potential mapping is significantly influenced by sample size and this is still a challenge. This study evaluates the influence of sample size on the accuracy of different individual and hybrid models, adaptive neuro-fuzzy inference system (ANFIS), ANFIS-imperial competitive algorithm (ANFIS-ICA), alternating decision tree (ADT), and random forest (RF) to model groundwater potential, considering the number of springs from 177 to 714. A well-documented inventory of springs, as a natural representative of groundwater potential, was used to designate four sample data sets: 100% (D₁), 75% (D₂), 50% (D₃), and 25% (D₄) of the entire springs inventory. Each data set was randomly split into two groups of 30% (for training) and 70% (for validation). Fifteen diverse geo-environmental factors were employed as independent variables. The area under the operating receiver characteristic curve (AUROC) and the true skill statistic (TSS) as two cutoff-independent and cutoff-dependent performance metrics were used to assess the performance of models. Results showed that the sample size influenced the performance of four machine learning algorithms, but RF had a lower sensitivity to the reduction of sample size. In addition, validation results revealed that RF (AUROC = 90.74–96.32%, TSS = 0.79–0.85) had the best performance based on all four sample data sets, followed by ANFIS-ICA (AUROC = 81.23–91.55%, TSS = 0.74–0.81), ADT (AUROC = 79.29–88.46%, TSS = 0.59–0.74), and ANFIS (AUROC = 73.11–88.43%, TSS = 0.59–0.74). Further, the relative slope position, lithology, and distance from faults were the main spring-affecting factors contributing to groundwater potential modelling. This study can provide useful guidelines and a valuable reference for selecting machine learning models when a complete spring inventory in a watershed is unavail

Floods in urban environments often result in loss of life and destruction of property, with many negative socio-economic effects. However, the application of most flood prediction models still remains challenging due to data scarcity. This creates a need to develop novel hybridized models based on historical urban flood events, using, e.g., metaheuristic optimization algorithms and wavelet analysis. The hybridized models examined in this study (Wavelet-SVR-Bat and Wavelet-SVR-GWO), designed as intelligent systems, consist of a support vector regression (SVR), integrated with a combination of wavelet transform and metaheuristic optimization algorithms, including the grey wolf optimizer (GWO), and the bat optimizer (Bat). The efficiency of the novel hybridized and standalone SVR models for spatial modeling of urban flood inundation was evaluated using different cutoff-dependent and cutoff-independent evaluation criteria, including area under the receiver operating characteristic curve (AUC), Accuracy (A), Matthews Correlation Coefficient (MCC), Misclassification Rate (MR), and F-score. The results demonstrated that both hybridized models had very high performance (Wavelet-SVR-GWO: AUC = 0.981, A = 0.92, MCC = 0.86, MR = 0.07; Wavelet-SVR-Bat: AUC = 0.972, A = 0.88, MCC = 0.76, MR = 0.11) compared with the standalone SVR (AUC = 0.917, A = 0.85, MCC = 0.7, MR = 0.15). Therefore, these hybridized models are a promising, cost-effective method for spatial modeling of urban flood susceptibility and for providing in-depth insights to guide flood preparedness and emergency response services.

In an effort to improve tools for effective flood risk assessment, we applied machine learning algorithms to predict flood-prone areas in Amol city (Iran), a site with recent floods (2017–2018). An ensemble approach was then implemented to predict hazard probabilities using the best machine learning algorithms (boosted regression tree, multivariate adaptive regression spline, generalized linear model, and generalized additive model) based on a receiver operator characteristic-area under the curve assessment. The algorithms were all trained and tested on 92 randomly selected points, information from a flood inundation survey, and geospatial predictor variables (precipitation, land use, elevation, slope percent, curve number, distance to river, distance to channel, and depth to groundwater). The ensemble model had 0.925 and 0.892 accuracy for training and testing data, respectively. We then created a vulnerability map from data on building density, building age, population density, and socio-economic conditions and assessed risk as a product of hazard and vulnerability. The results indicated that distance to channel, land use, and runoff generation were the most important factors associated with flood hazard, while population density and building density were the most important factors determining vulnerability. Areas of highest and lowest flood risks were identified, leading to recommendations on where to implement flood risk reduction measures to guide flood governance in Amol city.

In separate analyses of the impacts of land use change and climate change, a scenario-based approach using remote sensing and hydro-climatological data was developed to assess changes in hydrological indices. The data comprised three Landsat TM images (1988, 1998, 2008) and meteorological and hydrological data (1983–2012) for the Aligudarz and Doroud stations in the Marboreh watershed, Iran. The QUAC module and supervised classification maximum likelihood (ML) algorithm in ENVI 5.1 were used for remote sensing, the SWAT model for hydrological modelling and the Mann-Kendall and t test methods for statistical analysis. To create scenarios, the study period was divided into three decades (1983–1992, 1993–2002, 2003–2012) with clearly different land use/land cover (LULC). After hydrological modelling, 10 hydrological indices related to high and low flow indices (HDI and LDI) were analysed for seven scenarios developed by combining pre-defined climate periods and LULC maps. The major changes in land use were degradation of natural rangeland (−18.49%) and increasing raid-fed farm area (+16.70%) and residential area (+0.80%). The Mann-Kendall test results showed a statistically significant (p < 0.05) decreasing trend in rainfall and flow during 1983–2012. In the scenarios evaluated, hydrological index trends were more sensitive to climate change than to LULC changes in the study area. Low flow indices were more affected than high flow indices in both land use and climate change scenarios. The results show little impact of land use change and indicate that climate change is the main driver of hydrological variations in the catchment. This is useful information in outlining future strategies for sustainable water resources management and policy decision-making in the Marboreh watershed.

Managed aquifer recharge (MAR) structure is widely used to expand groundwater resources. In arid regions with flash flooding, MAR can also be used as a flood control structure to decrease peak discharge of rivers. In this paper, we present a method for quantifying the role of MAR in head water systems and assess its impact on the total water balance in a river basin. The method is based on rainfall-runoff modeling, reservoir flood routing, recharge analysis and river flow analysis. For the case selected, Kamal Abad MAR in Lake Maharlou basin in southern Iran, we analyzed changes in the downstream river regime using two scenarios (with MAR and without MAR) with different return periods. The results revealed a significant impact of MAR on river flow in terms of changes in flow timing, magnitude and variability. With MAR, the ephemeral river studied became disconnected from the main stream, albeit, whereas the case without MAR, floods with return period higher than 10 years would be connected to the downstream. Even though, MAR structures are useful in arid and semi-arid climates for irrigation water supply, their placing and designing need more attention. The developed method can be used to assess the impacts of MAR on river flow and find the best location for it to make the connection of the ephemeral river and downstream river, an issue which has not received much attention in hydrological research.

In northern Iran’s Haraz River basin between 1975 and 2010, hydrological sensitivity, double mass curve, and Soil and Water Assessment Tool (SWAT) methods were applied to monitoring and analysing changes in stream flow brought on by climatic variability and human activities. Applied to analyse trends in annual and seasonal runoff over this period, the sequential MK test showed a sudden change point in stream flow in 1994. The study period was, therefore, divided into two sub-periods: 1975–1994 and 1995–2010. The SWAT model showed obvious changes in water resource components between the two periods: in comparison to the period of 1975–1994, sub-watershed-scale stream flow and soil moisture decreased during 1995–2010. Changes in evapotranspiration were negligible compared to those in stream flow and soil moisture. The hydrological sensitivity method indicated that climatic variability and human activities contributed to 29.86% and 70.14%, respectively, of changes in annual stream flow, while the SWAT model placed these contributions at 34.78% and 65.21%, respectively. The double mass curve method indicated the contribution of climatic variability to stream flow changes to be 57.5% for the wet season and 22.87% for the dry season, while human activities contributed 42.5% and 77.13%, respectively. Accordingly, in the face of climatic variability, measures should be developed and implemented to mitigate its impacts and maintain eco-environmental integrity and water supplies.

Floods are the most common natural disaster globally and lead to severe damage, especially in urban environments. This study evaluated the efficiency of a self-organizing map neural network (SOMN) algorithm for urban flood hazard mapping in the case of Amol city, Iran. First, a flood inventory database was prepared using field survey data covering 118 flooded points. A 70:30 data ratio was applied for training and validation purposes. Six factors (elevation, slope percent, distance from river, distance from channel, curve number, and precipitation) were selected as predictor variables. After building the model, the odds ratio skill score (ORSS), efficiency (E), true skill statistic (TSS), and the area under the receiver operating characteristic curve (AUC-ROC) were used as evaluation metrics to scrutinize the goodness-of-fit and predictive performance of the model. The results indicated that the SOMN model performed excellently in modeling flood hazard in both the training (AUC = 0.946, E = 0.849, TSS = 0.716, ORSS = 0.954) and validation (AUC = 0.924, E = 0.857, TSS = 0.714, ORSS = 0.945) steps. The model identified around 23% of the Amol city area as being in high or very high flood risk classes that need to be carefully managed. Overall, the results demonstrate that the SOMN model can be used for flood hazard mapping in urban environments and can provide valuable insights about flood risk management.

© 2018 Elsevier B.V. Flood risk mapping and modeling is important to prevent urban flood damage. In this study, a flood risk map was produced with limited hydrological and hydraulic data using two state-of-the-art machine learning models: Genetic Algorithm Rule-Set Production (GARP) and Quick Unbiased Efficient Statistical Tree (QUEST). The flood conditioning factors used in modeling were: precipitation, slope, curve number, distance to river, distance to channel, depth to groundwater, land use, and elevation. Based on available reports and field surveys for Sari city (Iran), 113 points were identified as flooded areas (with each flooded zone assigned a value of 1). Different conditioning factors, including urban density, quality of buildings, age of buildings, population density, and socio-economic conditions, were taken into account to analyze flood vulnerability. In addition, the weight of these conditioning factors was determined based on expert knowledge and Fuzzy Analytical Network Process (FANP). An urban flood risk map was then produced using flood hazard and flood vulnerability maps. The area under the receiver-operator characteristic curve (AUC-ROC) and Kappa statistic were applied to evaluate model performance. The results demonstrated that the GARP model (AUC-ROC = 93.5%, Kappa = 0.86) had higher performance accuracy than the QUEST model (AUC-ROC = 89.2%, Kappa = 0.79). The results also indicated that distance to channel, land use, and elevation played major roles in flood hazard determination, whereas population density, quality of buildings, and urban density were the most important factors in terms of vulnerability. These findings demonstrate that machine learning models can help in flood risk mapping, especially in areas where detailed hydraulic and hydrological data are not available.

This corrects the article DOI: 10.1038/ncomms5999.

Flood risk mapping and modeling is important to prevent urban flood damage. In this study, a flood risk map was produced with limited hydrological and hydraulic data using two state-of-the-art machine learning models: Genetic Algorithm Rule-Set Production (GARP) and Quick Unbiased Efficient Statistical Tree (QUEST). The flood conditioning factors used in modeling were: precipitation, slope, curve number, distance to river, distance to channel, depth to groundwater, land use, and elevation. Based on available reports and field surveys for Sari city (Iran), 113 points were identified as flooded areas (with each flooded zone assigned a value of 1). Different conditioning factors, including urban density, quality of buildings, age of buildings, population density, and socio-economic conditions, were taken into account to analyze flood vulnerability. In addition, the weight of these conditioning factors was determined based on expert knowledge and Fuzzy Analytical Network Process (FANP). An urban flood risk map was then produced using flood hazard and flood vulnerability maps. The area under the receiver-operator characteristic curve (AUC-ROC) and Kappa statistic were applied to evaluate model performance. The results demonstrated that the GARP model (AUC-ROC = 93.5%, Kappa = 0.86) had higher performance accuracy than the QUEST model (AUC-ROC = 89.2%, Kappa = 0.79). The results also indicated that distance to channel, land use, and elevation played major roles in flood hazard determination, whereas population density, quality of buildings, and urban density were the most important factors in terms of vulnerability. These findings demonstrate that machine learning models can help in flood risk mapping, especially in areas where detailed hydraulic and hydrological data are not available.

Common variation on 14q24.1, close to RAD51B, has been associated with breast cancer: rs999737 and rs2588809 with the risk of female breast cancer and rs1314913 with the risk of male breast cancer. The aim of this study was to investigate the role of RAD51B variants in breast cancer predisposition, particularly in the context of familial breast cancer in Finland. We sequenced the coding region of RAD51B in 168 Finnish breast cancer patients from the Helsinki region for identification of possible recurrent founder mutations. In addition, we studied the known rs999737, rs2588809, and rs1314913 SNPs and RAD51B haplotypes in 44,791 breast cancer cases and 43,583 controls from 40 studies participating in the Breast Cancer Association Consortium (BCAC) that were genotyped on a custom chip (iCOGS). We identified one putatively pathogenic missense mutation c.541C>T among the Finnish cancer patients and subsequently genotyped the mutation in additional breast cancer cases (n = 5259) and population controls (n = 3586) from Finland and Belarus. No significant association with breast cancer risk was seen in the meta-analysis of the Finnish datasets or in the large BCAC dataset. The association with previously identified risk variants rs999737, rs2588809, and rs1314913 was replicated among all breast cancer cases and also among familial cases in the BCAC dataset. The most significant association was observed for the haplotype carrying the risk-alleles of all the three SNPs both among all cases (odds ratio (OR): 1.15, 95% confidence interval (CI): 1.11-1.19, P = 8.88 x 10-16) and among familial cases (OR: 1.24, 95% CI: 1.16-1.32, P = 6.19 x 10-11), compared to the haplotype with the respective protective alleles. Our results suggest that loss-of-function mutations in RAD51B are rare, but common variation at the RAD51B region is significantly associated with familial breast cancer risk.

__Background:__ There is increasing evidence that elevated body mass index (BMI) is associated with reduced survival for women with breast cancer. However, the underlying reasons remain unclear. We conducted a Mendelian randomization analysis to investigate a possible causal role of BMI in survival from breast cancer. __Methods:__ We used individual-level data from six large breast cancer case-cohorts including a total of 36 210 individuals (2475 events) of European ancestry. We created a BMI genetic risk score (GRS) based on genotypes at 94 known BMI-associated genetic variants. Association between the BMI genetic score and breast cancer survival was analysed by Cox regression for each study separately. Study-specific hazard ratios were pooled using fixed-effect meta-analysis. __Results:__