Coastal Wave Height Prediction using Recurrent Neural Networks (RNNs) in the South Caspian Sea

The prediction of wave parameters has a great significance in the coastal and offshore engineering. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, soft computing, and numerical based approaches. Recently, soft computing techniques such as recurrent neural networks (RNN) have been used to develop sea wave prediction models. In this study, the RNN for wave prediction based on the data gathered and the measurement of the sea waves in the Caspian Sea, in the north of Iran is used for this study. The efficiency of RNNs for 3, 6, and 12 hourly and diurnal wave prediction using correlation coefficients is calculated to be 0.96, 0.90, 0.87, and 0.73, respectively. This indicates that wave prediction by using RNNs yields better results than the previous neural network approaches.     

Neuro-fuzzy modelling in mining geochemistry: Identification of geochemical anomalies

Local and mine scale exploration models for anomaly recognition within known ore fields are discussed. Traditional geochemical exploration methods are based on multivariate statistical analysis, metallometry, vertical geochemical zonality and criteria of natural field geochemical associations, which suffer several shortcomings, including lack of a geostatistical generalised approach for separating anomalies from background. These shortcomings make the interpretation process time consuming and costly. Fuzzy set theory, fuzzy logic and neural network techniques seem very well suited for typical mining geochemistry applications. The results, obtained from applying the proposed technique to a real scenario, reveals significant improvements, comparing the results obtained from applying multivariate statistical analysis. Computationally, the introduced technique makes possible, without exploration drilling, the distinction between blind mineralisation and zone of dispersed ore mineralisation. The methodology developed in this research study has been verified by testing it on various real-world mining geochemical projects.     

A new developed approach for the prediction of ground vibration using a hybrid PSO-optimized ANFIS-based model

Ground vibration is one of the common environmental effects of blasting operation in mining industry, and it may cause damage to the nearby structures and the surrounding residents. So, precise estimation of blast-produced ground vibration is necessary to identify blast-safety area and also to minimize environmental effects. In this research, a hybrid of adaptive neuro-fuzzy inference system (ANFIS) optimized by particle swarm optimization (PSO) was proposed to predict blast-produced ground vibration in Pengerang granite quarry, Malaysia. For this goal, 81 blasting were investigated, and the values of peak particle velocity, distance from the blast-face and maximum charge per delay were precisely measured. To demonstrate the performance of the hybrid PSO–ANFIS, ANFIS, and United States Bureau of Mines empirical models were also developed. Comparison of the predictive models was demonstrated that the PSO–ANFIS model [with root-mean-square error (RMSE) 0.48 and coefficient of determination (R ²) of 0.984] performed better than the ANFIS with RMSE of?1.61 and R ² of 0.965. The mentioned results prove the superiority of the newly developed PSO–ANFIS model in estimating blast-produced ground vibrations.     

Interannual variations in length of day with respect to El Niño - Southern Oscillation’s impact (1962–2015)

The objective of research done in this study is to examine the variability of the length of day (LOD) and to investigate its correlation with ENSO (El Niño-Southern oscillation) episodes. For this purpose, the LOD time series (1962–2015), from the International Earth Rotation and Reference Systems Service (IERS), is investigated using the Singular Spectrum Analysis (SSA) technique. The results show that the LOD time series is very complex and is composed of several components: the long-term trend explains 95.97% of the original series, the annual harmonic 1.76% and the semi-annual 1.35%. Considering sea surface temperature anomalies (SSTA) index over the Niño3, Niño4 and Niño3.4 regions, Southern Oscillation Index (SOI) and Multivariate ENSO Index (MEI), the residuals signal, that represents only 0.92% of the initial LOD series, indicate a significant correlation with ENSO occurred during 1965–66, 1972–73, 1982–83 and 1997–98 El Niño events and 1970–71, 1973–74, 1988–89, 2007–08, 2010–11 La Niña ones. This is a pertinent result that suggests that LOD variability is at least partly related to ENSO phenomena.     

Evaluating the impact of management scenarios and land use changes on annual surface runoff and sediment yield using the GeoWEPP: a case study from the Lighvanchai watershed,Iran

This study was undertaken to evaluate land use change impact and management scenarios on annual average surface runoff (SR) and sediment yield (SY) using the GeoWEPP tool in the Lighvanchai watershed (located in northwestern Iran). Following a sensitivity analysis, the WEPP model was calibrated (2005–2007) and validated (2008–2010) against monthly observed SY and SR. The coefficient of determination (R ²), Nash–Sutcliffe efficiency (NSE), mean bias error (MBE), and root-mean-square error (RMSE) were applied to quantitatively evaluate the WEPP model. The results indicate a satisfactory model performance with R ² > 0.80 and NSE > 0.60. Therefore, the model for current land use (scenario 1) was run for a 30-year time period (1982–2011). The annual average of SR and sediment load were predicted as 93,584 m³/year and 4340 ton/year, respectively. To reduce the annual average surface runoff and sediment yield at the watershed scale, the second scenario (alfalfa cultivation with suitable tillage) and the third scenario (grassland development) as two management scenarios of land use changes were defined by identifying the critical hillslopes. The rate of SR and sediment load in the second scenario were 42,096 m³/year and 429 ton/year, respectively. For the third scenario, the model predictions were 30,239 m³/year and 226 ton/year, respectively. Compared to the first scenario, the reduction rates in annual average of sediment load were about 90 and 94%, respectively. Moreover, for the second and third management scenarios, the reduction rates in annual average of SR were about 55 and 67%, respectively.     

A change-detection application on the evolution of Kahak playa (South Khorasan province, Iran)

Kahak salt playa in South Khorasan province of Iran, have special geomorphological characteristics by the presence of ephemeral saline lakes, wetlands, salt crusts, surface accumulations of salt and zones of patterned ground. Salt crusts in the soil surface are unique in the region and have laminated horizons in the playa soil. Soil-surface salt accumulations are dominated by NaCl and gypsum. It has been found that distribution of chemical soluble is not uniform across the playa landscape, and this result influences on the variety form of patterned ground. In this study, the percent changes in some of the chemical elements such as NaCl, gypsum and also brine extent have been calculated in the playa. Indicating changes in Kahak salt playa is the main aim of this study by using remote sensing and GIS techniques. In this paper, techniques such as spectral un-mixing, maximum likelihood classification, band rationing, fuzzy classification and correlation relationships are discussed. This contribution presents modeling of temporal and spatial changes of salinity and playa developing using combined approaches that incorporate different data-fusion and data-integration techniques for two periods of date. Furthermore, percent changes in the surface-patterned ground of the playa have been calculated using texture and pattern analysis of the PCA1. Results have revealed that, in the playa developing, chemical materials such as sodium, NaCl, gypsum and also brine extent are positively correlated with each other and the most increased changes are related to gypsum and the most decreased changes are related to the NaCl. Also changes in the amount of agricultural area in the playa-lakes margin, show low effects in the desertification process.     

Pairing geotechnics and fluvial hydraulics for the prediction of the hazard zones of an exceptional flooding

The direct consequences of exceptional floods are usually considered to be limited to the maximum flooding zone created downstream. However, considering the magnitude of the flows, the morphology of the flooded zone could undergo deep changes. To predict the hazard zone on a river undergoing exceptional flooding, numerical simulations are widely used. In this article, the simulation of the evolution of river reaches resulting from such catastrophic events is performed by coupling the hydraulic and sediment transport numerical model GSTARS with a developed slope stability model based on the Bishop’s simplified method. This is a novel methodology for the delimitation of hazard zones along riverbanks by taking into consideration not only the flood risks but also the possible induced landslides. Indeed, each section of the river reach is subject to changes caused by the river hydraulics and the associated erosion or sediment deposition and also undergoes profile changes caused by possible landslides. The initial hydraulic and geotechnical characteristics are first defined and then used to test the stability of several slopes of representative sections of the river reaches before the dam break. Validation tests are performed on specific reaches of the Outaouais River (Quebec) undergoing a dam break flood.     

Global morphology of ionospheric sporadic E layer from the FormoSat-3/COSMIC GPS radio occultation experiment

Ionospheric sporadic-E (Es) activity and global morphology were studied using the 50 Hz signal-to-noise ratio amplitude and excess phase measurements from the FormoSat-3/Constellation Observing System for Meteorology, Ionosphere and Climate (FS3/COSMIC) GPS radio occultation (RO) observations. The results are presented for data collected during the last sunspot cycle from mid-2006 to the end of 2017. The FS3/COSMIC generally performed more than 1000 complete E-region GPS RO observations per day, which were used to retrieve normalized L1-band amplitude standard deviation (SDL1) and relative electron density (N_e) profiles successfully. More or less 31% of those observations were identified as Es events based on SDL1 and peak SDL1 altitude criteria. We found that the peak Es-event i values are approximately proportional to the logarithms of the corresponding peak N_e differences. Five major geographical zones were identified, in which the seasonal and diurnal Es occurrence patterns are markedly different. These five zones include the geomagnetic equatorial zone (??5°?<?magnetic latitude (ML)?<?5°), two extended geomagnetic mid-latitude zones (15°?<?ML?<?55°, and ??55°?<?ML < ??15°), and two auroral zones (70°?<?ML, and ML < ??70°). The Es climatology, namely its variations with each identified zone, altitude, season, and local time has been documented.     

Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses.In this study,we applied two novel deep learning algorithms,the recurrent neural network(RNN)and convolutional neural network(CNN),for national-scale landslide susceptibility mapping of Iran.We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors(altitude,slope degree,profile curvature,distance to river,aspect,plan curvature,distance to road,distance to fault,rainfall,geology and land-sue)to construct a geospatial database and divided the data into the training and the testing dataset.We then developed RNN and CNN algorithms to generate landslide susceptibility maps of Iran using the training dataset.We calculated the receiver operating characteristic(ROC)curve and used the area under the curve(AUC)for the quantitative evaluation of the landslide susceptibility maps using the testing dataset.Better performance in both the training and testing phases was provided by the RNN algorithm(AUC=0.88)than by the CNN algorithm(AUC=0.85).Finally,we calculated areas of susceptibility for each province and found that 6%and 14%of the land area of Iran is very highly and highly susceptible to future landslide events,respectively,with the highest susceptibility in Chaharmahal and Bakhtiari Province(33.8%).About 31%of cities of Iran are located in areas with high and very high landslide susceptibility.The results of the present study will be useful for the development of landslide hazard mitigation strategies.