Most of river engineering problems are complicated and need to be analyzed by three dimensional models of flow and sediment transport. Considering the fact that computers and numerical methods with great ability of flow and sediment transport simulation are developing quickly, using numerical modeling by engineers is inevitable. Nevertheless, before application, numerical models need to be veri...

This study examines the capability of the Relevance Vector Machine (RVM) and Multivariate Adaptive Regression Spline (MARS) for prediction of ultimate capacity of driven piles and drilled shafts. RVM is a sparse method for training generalized linear models, while MARS technique is basically an adaptive piece-wise regression approach. In this paper, pile capacity prediction models are developed...

Numerical models can be valuable tools in the prediction of seepage. The results can often be misleading if proper variational analysis is not performed. Measurement of the soil-water characteristic curve (SWCC) or saturated and unsaturated hydraulic conductivity information is often neglected or minimized. The modeller is therefore forced to develop a seepage model based on estimated soil prop...

Time series and their methods of analysis are important subjects in statistics. Most of time series have a linear behavior and can be modelled by linear ARIMA models. However, some of realized time series have a nonlinear behavior and for modelling them one needs nonlinear models. For this, many good parametric nonlinear models such as bilinear model, exponential autoregressive model, threshold...

Decay prediction models are frequently used to estimate the service life of wooden components. These models require knowledge of how the material climate, i.e. moisture content and material temperature, varies over time. Therefore, a reliable material climate prediction model is crucial in situations when measurements are not viable. The aim of this paper is to test and evaluate the performance...

Latent factor models and decision tree based models are widely used in tasks of prediction, ranking and recommendation. Latent factor models have the advantage of interpreting categorical features by a low-dimensional representation, while such an interpretation does not naturally fit numerical features. In contrast, decision tree based models enjoy the advantage of capturing the nonlinear inte...

The sub-grid-scale parameterization of clouds is one of the weakest aspects of weather and climate modeling today, and the explicit simulation of clouds will be one of the next major achievements in numerical weather prediction. Research cloud models have been in development over the last 45 years and they continue to be an important tool for investigating clouds, cloud-systems, and other small...