Evaluation of four supervised learning methods for groundwater spring potential mapping in Khalkhal region (Iran) using GIS-based features

One important tool for water resources management in arid and semi-arid areas is groundwater potential mapping. In this study, four data-mining models including K-nearest neighbor (KNN), linear discriminant analysis (LDA), multivariate adaptive regression splines (MARS), and quadric discriminant analysis (QDA) were used for groundwater potential mapping to get better and more accurate groundwater potential maps (GPMs). For this purpose, 14 groundwater influence factors were considered, such as altitude, slope angle, slope aspect, plan curvature, profile curvature, slope length, topographic wetness index (TWI), stream power index, distance from rivers, river density, distance from faults, fault density, land use, and lithology. From 842 springs in the study area, in the Khalkhal region of Iran, 70 % (589 springs) were considered for training and 30 % (253 springs) were used as a validation dataset. Then, KNN, LDA, MARS, and QDA models were applied in the R statistical software and the results were mapped as GPMs. Finally, the receiver operating characteristics (ROC) curve was implemented to evaluate the performance of the models. According to the results, the area under the curve of ROCs were calculated as 81.4, 80.5, 79.6, and 79.2 % for MARS, QDA, KNN, and LDA, respectively. So, it can be concluded that the performances of KNN and LDA were acceptable and the performances of MARS and QDA were excellent. Also, the results depicted high contribution of altitude, TWI, slope angle, and fault density, while plan curvature and land use were seen to be the least important factors.     

Assessment of H<Subscript>2</Subscript>S emission hazards into tunnels: the Nosoud tunnel case study from Iran

The presence of a gassy ground condition is an important problem in tunneling. In this study, the effects of groundwater H₂S and CH₄ emissions are investigated and characterized together with the factors that created these conditions in Nosoud tunnel in Iran. Through the geological investigations, the presence of these gasses was not detected prior to the construction of the tunnel. Groundwater sampling indicated that about 1 L of H₂S is released per 100 L of the water inflow into the Nosoud tunnel under normal conditions. However, the volume of the released gas was varying with the changes in the groundwater discharge rate. Thus, estimation of groundwater inflow into the tunnel is necessary for predicting the volume of gas emission. Based on the experience of the Nosoud tunnel excavations, there are several geological and hydrogeological factors that must be considered as the indicators of gas emissions during tunneling. Considering the importance of ground water gas emission into the tunnels located in gassy conditions, the present work was conducted to predict the H₂S seepage before the excavation using geological and hydrogeological indicators.     

Support vector machines and feed-forward neural networks for spatial modeling of groundwater qualitative parameters

The present study attempts to model the spatial variability of three groundwater qualitative parameters in Guilan Province, northern Iran, using artificial neural networks (ANNs) and support vector machines (SVMs). Data collected from 140 observation wells for the years 2002–2014 were used. Five variables, X and Y coordinates of the observation well, distance of the observation well from the shoreline, areal average 6-month rainfall depth, and groundwater level at the day of water quality sampling, were considered as primary input variables. In addition, nine qualitative variables were also considered as auxiliary input variables. Electrical conductivity (EC), sodium concentration (Na⁺), and sulfate concentration (SO₄ ^2?) of the groundwater in the region were estimated using ANNs and SVMs with different input combinations. The results showed that both ANNs and SVMs work well when the only primary input variable is the well location. The ANN yielded an RMSE of 1.03 mEq/l for SO₄ ^2?, 1.05 mEq/l for Na⁺, and 203.17 μS/cm for EC, using the X and Y coordinates of the observation wells in the study area. In the case of SVM, these values were, respectively, 0.87, 0.87, and 176.68. Considering the auxiliary input variables (pH, EC, and the concentrations of Na⁺, K⁺, Ca²⁺, Mg²⁺, Cl^?, SO₄ ^2?, and HCO₃ ^?) resulted in a significant decrease in the RMSE of both ANNs (0.22, 0.30, and 33.04) and SVMs (0.26, 0.34, and 36.23). Comparing these RMSE values with those of cokriging interpolation technique (0.59, 0.98, and 177.59) indicated that ANNs and SVMs produced more accurate estimates of the three qualitative parameters. The relative importance of auxiliary input variables was also determined using Gamma test. The output uncertainty of ANNs and SVMs were determined using p-factor and d-factor. The results showed that SVMs have less uncertainty than ANNs.     

A new look at the phenomenon of offshore pile plugging

Abstract

Open‐pipe piles are widely used for offshore structures. During the initial stage of installation, soil enters the pile at a rate equal to the pile penetration. As penetration continues, the inner soil cylinder may develop sufficient frictional resistance to prevent further soil intrusion, causing the pile to become plugged. The open‐ended pile then assumes the penetration characteristics of a closed‐ended pile. The mode of pile penetration significantly alters the soil‐pile interaction during and after installation. This affects the ultimate static bearing capacity (mainly in granular materials), the time‐dependent pile capacity (in clays), and the dynamic behavior and analysis of the piles.

Following a summary demonstrating the effects of pile plugging, a review of the common view of offshore pile plugging is undertaken. The interpretation of plugging by referring to the average plug length has led to the erroneous conclusion that in most piles significant plugging action does not occur.

Establishment of an analogy between soil samplers and open‐ended piles enabled correct identification of plugging by referring to the incremental changes in plug length. Examination of case histories of plugging of offshore piles revealed that beyond a certain penetration depth‐to‐diameter ratio, most piles are plugged.     

Woody species diversity and forest structure from lowland to montane forest in Hyrcanian forest ecoregion

Alborz Mountains host Caspian Hyrcanian forest ecoregion along the northern slopes and forest steppe ecoregion in highlands. Hyrcanian forest covers the southeastern part of Caucasus biodiversity hotspot and is of great biogeographic importance. Altitudinal pattern and correlation between woody species biodiversity (DIV), forest structure ((stem density (DEN), mean basal area (MBA) and mean height class (MHC)) and disturbance (DIS) were explored along 2,400 m altitudinal gradient in Hyrcanian relict forest, Central Alborz Mountains. Vegetation changes from lowland forest (LoF) to mid- altitude forest (MiF) and montane forest (MoF) in this area. The altitudinal gradient was divided into twelve 200 m elevational belts. Point centered quarter method (PCQM) with 96 sampling points and 83 vegetation samples by plot method (PM) were used to record field data. Shannon-Wiener index and Pearson coefficient were used for diversity and correlation analysis. The results showed that DEN decreased linearly, MBA and MHC showed relatively hump shaped and DIS showed a reverse hump shaped pattern of change along altitudinal gradient. Woody species diversity decreased non-steadily from LoF to MoF. Transitional vegetations of Carpinus-Fagus and Fagus-Quercus represented higher diversity of woody taxa compared to adjacent homogenous communities. Significant correlation was observed between altitude and all parameters: DEN with MBA, DIS and DIV; MBA with DIS; MHC with DIS along with DIV; and DIS with DIV at the study area scale. Surprisingly,correlation between studied parameters differed within each vegetation type. Altitude probably acts as a proxy for human and environmental driving forces in this area. Stability of warm and wet condition, season length, soil depth along with forest accessibility probably influences the altitudinal pattern of the studied parameters. Disturbance affects forest structure and consequently diversity; especially in lowlands. The obtained results recommend using both forest biodiversity and mensuration data in management process of forest ecosystems.     

Dead Sea Basin Imaged by Ambient Seismic Noise Tomography

In the framework of the Dead Sea Integrated Research project (DESIRE), 59 seismological stations were deployed in the region of the Dead Sea Basin. Twenty of these stations recorded data of sufficiently high quality between May and September 2007 to be used for ambient seismic noise analysis. Empirical Green’s functions are extracted from cross-correlations of long term recordings. These functions are dominated by Rayleigh waves, whose group velocities can be measured in the frequency range from 0.1 to 0.5 Hz. Analysis of positive and negative correlation lags of the Green’s functions makes it possible to identify the direction of the source of the incoming energy. Signals with frequencies higher than 0.2 Hz originate from the Mediterranean Sea, while low frequencies arrive from the direction of the Red Sea. Travel times of the extracted Rayleigh waves were measured between station pairs for different frequencies, and tomographically inverted to provide independent velocity models. Four such 2D models were computed for a set of frequencies, all corresponding to different sampling depths, and thus together giving an indication of the velocity variations in 3D extending to a depth of 10 km. The results show low velocities in the Dead Sea Basin, consistent with previous studies suggesting up to 8 km of recent sedimentary infill in the Basin. The complex structure of the western margin of the Basin is also observed, with sedimentary infill present to depths not exceeding 5 km west of the southern part of the Dead Sea. The high velocities associated with the Lisan salt diapir are also observed down to a depth of ~5 km. The reliability of the results is confirmed by checkerboard recovery tests.     

Comparison of two intelligent models to estimate the instantaneous global solar radiation in semi-arid climate conditions: Application in Iran

Solar radiation incident on the earth’s surface is a fundamental input for many aspects of climatology, hydrology, biology, and architecture. In addition, it is an important parameter in solar energy applications. Due to the high cost of the measuring instruments of solar radiation, many researchers have suggested different empirical methods to estimate this essential parameter. In this study, with the help of fuzzy systems and neural networks, two models have been designed to estimate the instantaneous global solar radiation in Rafsanjan city which has a typical climatic conditions of semi-arid region of middle eastern countries. In fuzzy and neural network model, the inputs are the number of the given day in the year, time, ambient temperature and cloudiness, The comparison between the results of the models and the measurements, shows that the estimated global radiation is similar to the measurement; for fuzzy model, statistical indicators RMSE, MBE and t-test are 103.4367 \((\hbox {w/m}^{2})\), 4.1169 \((\hbox {w/m}^{2})\) and 9.1318, respectively and for ANN, they are 85.46 \((\hbox {w/m}^{2})\), 3.08 \((\hbox {w/m}^{2})\) and 5.41, respectively. As the results indicate, both models are able to estimate the amount of radiation well, while the neural network has a higher accuracy. The output of the modes for six other cities of Iran, with similar climate conditions, also proves the ability of the proposed models.     

The Effects of Hydrophilic Polymer and Soil Salinity on Corn Growth in Sandy and Loamy Soils

The interaction effects of different applied ratios of a hydrophilic polymer (Superab A200) (0, 0.2, 0.6% w/w) under various soil salinity levels (initial salinity, 4 and 8 ms/cm) were evaluated on available water content (AWC), biomass, and water use efficiency for corn grown in loamy sand and sandy clay loam soils. The results showed that the highest AWC was measured at the lowest soil salinity. The application of 0.6% w/w of the polymer at the lowest salinity level increased the AWC by 2.2 and 1.2 times greater than those of control in the loamy sand and sandy clay loam soils, respectively. The analysis of variance of data showed that the effect of salinity was significant on biomass and water use efficiency of corn in the loamy sand and sandy clay loam soils. The highest amounts of these traits were measured in soils with the lowest salinity level. Application of polymer at the rate of 0.6% in the loamy sand soil and at the rate of 0.2% in the sandy clay loam soil resulted in the highest aerial and root biomass and water use efficiency for corn. At these polymer rates the amounts of water use efficiency for corn were 2.6 and 1.7 times greater than those of control in the loamy sand and sandy clay loam soils, respectively. Thus, the use of hydrophilic polymer in soils especially in the sandy soils increases soil water holding capacity, yield, and water use efficiency of plant. On the other hand, decreases the negative effect of soil salinity on plant and helps for irrigation projects to succeed in arid and semi‐arid areas.