Mohsen Soltanpour

Bio: Mohsen Soltanpour is an academic researcher from K.N.Toosi University of Technology. The author has contributed to research in topics: Wave height & Wave shoaling. The author has an hindex of 9, co-authored 59 publications receiving 285 citations.

Prediction of peak ground acceleration of Iran’s tectonic regions using a hybrid soft computing technique

Abstract: A new model is derived to predict the peak ground acceleration (PGA) utilizing a hybrid method coupling artificial neural network (ANN) and simulated annealing (SA), called SA-ANN. The proposed model relates PGA to earthquake source to site distance, earthquake magnitude, average shear-wave velocity, faulting mechanisms, and focal depth. A database of strong ground-motion recordings of 36 earthquakes, which happened in Iran’s tectonic regions, is used to establish the model. For more validity verification, the SA-ANN model is employed to predict the PGA of a part of the database beyond the training data domain. The proposed SA-ANN model is compared with the simple ANN in addition to 10 well-known models proposed in the literature. The proposed model performance is superior to the single ANN and other existing attenuation models. The SA-ANN model is highly correlated to the actual records (R ¼ 0.835 and r ¼ 0.0908) and it is subsequently converted into a tractable design equation.

A comparative study on the rheology and wave dissipation of kaolinite and natural Hendijan Coast mud, the Persian Gulf

Abstract: The objective of this paper is to investigate the rheological behavior of kaolinite and Hendijan mud, located at the northwest part of the Persian Gulf, and the dissipative role of this muddy bed on surface water waves. A series of laboratory rheological tests was conducted to investigate the rheological response of mud to rotary and cyclic shear rates. While a viscoplastic Bingham model can successfully be applied for continuous controlled shear-stress tests, the rheology of fluid mud displays complex viscoelastic behavior in time-periodic motion. The comparisons of the behavior of natural Hendijan mud with commercial kaolinite show rheological similarities. A large number of laboratory wave-flume experiments were carried out with a focus on the dissipative role of the fluid mud. Assuming four rheological models of viscous, Kelvin-Voigt viscoelastic, Bingham viscoplastic, and viscoelastic-plastic for fluid mud layer, a numerical multi-layered model was applied to analyze the effects of different parameters of surface wave and muddy bed on wave attenuation. The predicted results based on different rheological models generally agree with the obtained wave-flume data implying that the adopted rheological model does not play an important role in the accuracy of prediction.

Cyclone Gonu: The Most Intense Tropical Cyclone on Record in the Arabian Sea

Abstract: The Oman Sea and its neighboring countries’ (Iran and Oman) coastlines are subject to tropical cyclone influence on an infrequent basis; however, these cyclones can generate extremely large sea states. In general, cyclones generated in the Arabian Sea tend to travel either due west toward Oman or recurve north to strike Pakistan or India. They rarely enter the Oman Sea. Recently, in early June 2007, cyclone Gonu entered the Oman Sea and large waves were experienced along the Iranian and Omani coastlines. This cyclone had an unusual path, traveling much further west and north than the typical cyclone. Significant wave heights in excess of 4 m were measured at Chabahar located on the south coast of Iran bordering the Oman Sea.

Cross-Shore Mud Transport and Beach Deformation Model

Abstract: The present study aims to simulate the various features of wave-mud interaction on fine-grained shore profiles including wave height attenuation, wave-induced mud mass transport, gravity-driven flow of fluid mud and the reconfiguration of profile shape. A two-dimensional mud beach deformation model is presented considering the transport of fluid mud under continued wave action and downward gravity force. The wave height transformation is computed from the energy flux conservation law combining the effects of mud bed, shoaling and wave breaking. The rheological constitutive equations of visco-elastic-plastic model (Shibayama et al., 1990) are selected for numerical simulation. Wave flume experiments are carried out and the results are utilized for the verification of numerical model. The results of the numerical model are also compared with the laboratory data of Nakano (1994). It is concluded that the model is capable to predict the observed phenomena.

Physically-based Assessment of Hurricane Surge Threat under Climate Change

Abstract: United States. National Oceanic and Atmospheric Administration (Postdoctoral Fellowship Program)

Estimation of monthly evaporative loss using relevance vector machine, extreme learning machine and multivariate adaptive regression spline models

Abstract: The forecasting of evaporative loss (E) is vital for water resource management and understanding of hydrological process for farming practices, ecosystem management and hydrologic engineering. This study has developed three machine learning algorithms, namely the relevance vector machine (RVM), extreme learning machine (ELM) and multivariate adaptive regression spline (MARS) for the prediction of E using five predictor variables, incident solar radiation (S), maximum temperature (T max), minimum temperature (T min), atmospheric vapor pressure (VP) and precipitation (P). The RVM model is based on the Bayesian formulation of a linear model with appropriate prior that results in sparse representations. The ELM model is computationally efficient algorithm based on Single Layer Feedforward Neural Network with hidden neurons that randomly choose input weights and the MARS model is built on flexible regression algorithm that generally divides solution space into intervals of predictor variables and fits splines (basis functions) to each interval. By utilizing random sampling process, the predictor data were partitioned into the training phase (70 % of data) and testing phase (remainder 30 %). The equations for the prediction of monthly E were formulated. The RVM model was devised using the radial basis function, while the ELM model comprised of 5 inputs and 10 hidden neurons and used the radial basis activation function, and the MARS model utilized 15 basis functions. The decomposition of variance among the predictor dataset of the MARS model yielded the largest magnitude of the Generalized Cross Validation statistic (≈0.03) when the T max was used as an input, followed by the relatively lower value (≈0.028, 0.019) for inputs defined by the S and VP. This confirmed that the prediction of E utilized the largest contributions of the predictive features from the T max, verified emphatically by sensitivity analysis test. The model performance statistics yielded correlation coefficients of 0.979 (RVM), 0.977 (ELM) and 0.974 (MARS), Root-Mean-Square-Errors of 9.306, 9.714 and 10.457 and Mean-Absolute-Error of 0.034, 0.035 and 0.038. Despite the small differences in the overall prediction skill, the RVM model appeared to be more accurate in prediction of E. It is therefore advocated that the RVM model can be employed as a promising machine learning tool for the prediction of evaporative loss.