Flash flood susceptibility mapping using a novel deep learning model based on deep belief network,back propagation and genetic algorithm

Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA) based on Deep Belief Network(DBN) with Back Propagation(BP) algorithm optimized by the Genetic Algorithm(GA).For this task, a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE) technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy, root mean square error(RMSE), and area under the receiver operatic characteristic curve(AUC) were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC = 0.989) and prediction accuracy(AUC = 0.985), and based on the validation dataset it outperforms benchmark models including LR(0.885), LMT(0.934), BLR(0.936), ADT(0.976), NBT(0.974), REPTree(0.811), ANFIS-BAT(0.944), ANFIS-CA(0.921), ANFIS-IWO(0.939), ANFIS-ICA(0.947), and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods.     

Interactive effect of nitrogen fertilizer and hydrocarbon pollution on soil biological indicators

The investigation of the impact of different forms of nitrogen fertilizer (NO₃-N and NH₄-N) on microbial parameters, enzyme activities and phytotoxicity in a petroleum-contaminated soil was evaluated by an incubation study. The tested enzymes, microbial activity and seed germination index showed different patterns in response to both petroleum and nitrogen fertilizer addition and time of incubation. The results apparently showed that the contamination of soil with petroleum has a negative effect on soil ecosystem. Nitrogen fertilizer could improve inhibition of petroleum hydrocarbons in soil. Nevertheless, nitrogen fertilizer had no significant effect on urease activity in the petroleum-contaminated soil. As compared to NO₃-N, the addition of NH₄-N to the soil resulted in a greater impact on soil performance as attested by the recovery of the soil germination capability and higher values of the respiration. The application of nitrogen fertilizer may be suggested as a good strategy for restoring soils in regions affected by the same problem.     

Assessment of mesoscale convective systems using IR brightness temperature in the southwest of Iran

In this research, the spatial and temporal distribution of Mesoscale Convective Systems was assessed in the southwest of Iran using Global merged satellite IR brightness temperature (acquired from Meteosat, GOES, and GMS geostationary satellites) and synoptic station data. Event days were selected using a set of storm reports and precipitation criteria. The following criteria are used to determine the days with occurrence of convective systems: (1) at least one station reported 6-h precipitation exceeding 10 mm and (2) at least three stations reported phenomena related to convection (thunderstorm, lightning, and shower). MCSs were detected based on brightness temperature, maximum areal extent, and duration thresholds (228 K, 10,000 km², and 3 h, respectively). An MCS occurrence classification system is developed based on mean sea level, 850 and 500 hPa pressure patterns.

The results indicated that the highest frequency of MCSs occurred in December and April. Assessment of MCSs spatial frequency showed that MCS occurrence is strongly correlated with topography in April and May unlike the cold months. In other words, the role of Zagros Mountains in developing MCSs varies based on the season so that its impact increases with enhancement of mean monthly temperature. In addition, the occurrence of MCSs depends closely on the configuration of the Sudan Low in the southwest of Iran.

     

Spatial distribution of soil shear-wave velocity and the fundamental period of vibration – a case study of the Saguenay region,Canada

The spatial distribution of soil shear-wave velocity and the fundamental period of vibration were selected as input parameters for the determination of potential seismic site effects in the Saguenay region, Canada. The methodology used in this study involved three clear steps. First, a 3D geological model of the surficial deposits was built taking into consideration the type, spatial distribution and thickness of the deposits. Second, representative average V_s values were determined for each of the major soil units. Finally, the average shear-wave velocity from the ground surface to bedrock (V_sav), the shear-wave velocity of the upper 30 m (V_s30) and the fundamental site resonance period (T₀) were calculated over a regular grid for the study area. The results include the spatial distribution of the fundamental site resonance period, the average shear-wave velocity in the first 30 m of the ground and the spatial distribution of National Building Code of Canada seismic soil classes for the Saguenay region.     

Measuring the relationships between landscape aesthetics suitability and spatial patterns of urbanized lands: an informed modelling framework for developing urban growth scenarios

This study develops an informed modelling approach that follows a bottom-up planning strategy to define plausible urban growth scenarios. In this case, landscape aesthetics suitability of the area was first generated using multi-criteria evaluation method. Then, a buffer zone of 1 km was considered to extract the average values of aesthetics suitability scores surrounding urban patches with medium physical size (10–30 hectares). The averaged values were considered as the dependent variable. In the next step, landscape metrics of these urban patches, as explanatory variables, were also computed to measure compositional and configuration-based attributes of urban clusters. Bivariate associations (Pearson correlation analysis) and statistical relationships (linear regression algorithm) between landscape metrics and their associated aesthetics values were measured and modelled. According to the results, both composition and configuration values are significantly correlated to the dependent variable in which configuration-based attributes depicted a stronger explanatory power.     

Application of the WEPP model to determine sources of run‐off and sediment in a forested watershed

This study investigates critical run‐off and sediment production sources in a forested Kasilian watershed located in northern Iran. The Water Erosion Prediction Project (WEPP) watershed model was set up to simulate the run‐off and sediment yields. WEPP was calibrated and validated against measured rainfall–run‐off–sediment data. Results showed that simulated run‐off and sediment yields of the watershed were in agreement with the measured data for the calibration and validation periods. While low and medium values of run‐off and sediment yields were adequately simulated by the WEPP model, high run‐off and sediment yield values were underestimated. Performance of the model was evaluated as very good and satisfactory during the calibration and validation stages, respectively. Total soil erosion and sediment load of the study watershed during the study period were determined to be 10 108 t yr^?1 and 8735 t yr^?1, respectively. The northern areas of the watershed with dry farming were identified as the critical erosion prone zones. To prioritize the subwatersheds based on their contribution to the run‐off and sediment production at the watershed's main outlet, unit response approach (URA) was applied. In this regard, subwatersheds close to the main outlet were found to have the highest contribution to sediment yield of the whole watershed. Results indicated that depending on the objective of land and water conservation practices, particularly, for controlling sediment yield at the main outlet, critical areas for implementing the best management practices may be identified through conjunctive application of WEPP and URA. Copyright © 2014 John Wiley & Sons, Ltd.     

Understanding the impact of temporal scale on human movement analytics

Journal of Geographical Systems - Movement is manifested through a series of patterns at multiple spatial and temporal scales. Movement data today are becoming available at increasingly...     

A modi?ed failure criterion for transversely isotropic rocks

A modified failure criterion is proposed to determine the strength of transversely isotropic rocks. Me-chanical properties of some metamorphic and sedimentary rocks including gneiss, slate, marble, schist, shale, sandstone and limestone, which show transversely isotropic behavior, were taken into consider-ation. Afterward, introduced triaxial rock strength criterion was modified for transversely isotropic rocks. Through modification process an index was obtained that can be considered as a strength reduction parameter due to rock strength anisotropy. Comparison of the parameter with previous anisotropy in-dexes in literature showed reasonable results for the studied rock samples. The modified criterion was compared to modified Hoek-Brown and Ramamurthy criteria for different transversely isotropic rocks. It can be concluded that the modified failure criterion proposed in this study can be used for predicting the strength of transversely isotropic rocks.     

Development of a New Index to Assess the Rock Mass Drillability

Knowledge of drillability of rock masses in engineering projects is very important in determining drilling costs. In drilling operations, so many parameters such as the properties of rock and the drilling equipment affect the drilling performance. In this study, after discussing the rock mass drillability process and identifying all the effective parameters, interaction matrixes based on the rock engineering systems, that analyze the interrelationship between the parameters affecting rock engineering activities, is introduced to study the rock mass drillability tribosystem. Given that interaction matrix codes are not unique numbers, and then possible interactive intensities are calculated for each matrix and a group decision-making method, Fuzzy–Delphi–AHP technique has been used to obtain appropriate weights. As a result, rock mass drillability index (RMDI) is presented to classify the rock mass drillability. The results indicate the ability of this method to analyze rock mass drillability procedure. Drilling data along with laboratory rock properties from Sungun copper mine were collected and were ranked according to the new classification system. Fifteen zones at the mine site were ranked based upon the new index RMDI and a reasonable correlation was obtained between measured drilling rate at the zones and RMDI data.     

Effects of cations and anions on iron and manganese sorption and desorption capacity in calcareous soils from Iran

This study investigated the effect of cations and anions on the sorption and desorption of iron (Fe) and manganese (Mn) in six surface calcareous soil samples from Western Iran. Six 10 mM electrolyte background solutions were used in the study, i.e., KCl, KNO₃, KH₂PO₄, Ca(NO₃)₂, NaNO₃, and NH₄NO₃. NH₄NO₃ and NaNO₃ increased the soil retention of Fe and Mn, whereas Ca(NO₃)₂ decreased the soil retention of Fe and Mn. Iron and Mn sorption was decreased by NO₃ ^? compared with H₂PO₄ ^? or Cl^?. The Freundlich equation adequately described Fe and Mn adsorption, with all background electrolytes. The Freundlich distribution coefficient (K _F) decreased in the order H₂PO₄ ^? > Cl^? > NO₃ ^? for Mn and H₂PO₄ ^? > NO₃ ^? > Cl^? for Fe. The highest sorption reversibility was for Fe and Mn in competition with a Ca²⁺ background, indicating the high mobility of these two cations. A MINTEQ speciation solubility model showed that Fe and Mn speciation was considerably affected by the electrolyte background used. Saturation indices indicated that all ion background solutions were saturated with respect to siderite and vivianite at low and high Fe concentrations. All ion background solutions were saturated with respect to MnCO_3(am), MnHPO₄, and rhodochrosite at low and high Mn concentrations. The hysteresis indices (HI) obtained for the different ion backgrounds were regressed on soil properties indicating that silt, clay, sand, and electrical conductivity (EC) were the most important soil properties influencing Fe adsorption, while cation exchange capacity (CEC), organic matter (OM), and Mn-DTPA affected Mn adsorption in these soils.