Estimating the bearing capacity of piles is an essential point when seeking for safe and economic geotechnical structures. However, the traditional methods employed in this estimation are time-consuming and costly. The current study aims at elaborating a new alternative model for predicting the pile-bearing capacity based on eleven new advanced machine-learning methods in order to overcome these limitations. The modeling phase used a database of 100 samples collected from different countries. Additionally, eight relevant factors were selected in the input layer based on the literature recommendations. The optimal inputs were modeled using the machine-learning methods and their performance was assessed through six performance measures using a K-fold cross-validation approach. The comparative study proved the effectiveness of the DNN model, which displayed a higher performance in predicting the pile-bearing capacity. This elaborated model provided the optimal prediction, i.e., the closest to the experimental values, compared to the other models and formulae proposed by previous studies. Finally, a reliable and easy-to-use graphical interface was generated, namely “BeaCa2021”. This will be very helpful for researchers and civil engineers when estimating the pile-bearing capacity, with the advantage of saving time and money.

The compression index is one of the important geotechnical parameters, essential for the structural design. Since the determination of the compression index based on oedometer tests is relatively expensive and time-consuming, different authors have proposed for its estimation models using regression analysis and artificial neuron networks. However, they have ignored several parameters that could have increased the predictive capability of models. Other studies have concluded that genetic programming could have yielded better results. Unfortunately, no compression index models or effective comparisons of different methods have been published. The aim of this study is to propose a novel approach for estimating the compression index more accurately. To test the approach, a comparison study using K-fold cross-validation technique was conducted utilizing several models of multilayer neural networks, genetic programming, and multiple regression analysis. These models have been applied to 373 oedometer test samples to predict the compression index from soil physical parameters. The results indicate that the neural network with two hidden layers (7-14-4-1) provides the most appropriate prediction, compared with other models and the formulae suggested by previous studies. Based on these findings, this study‏ proposed a MATLAB script for efficiently estimating the compression index in the future studies.

Climatic spatial maps are essential for understanding the thermal conditions of cities and estimate their cooling and heating energy needs. Climate maps allow building designers and city planners to get adequately informed without accessing, analyzing or interpreting dense textual information. In this study, a representative residential benchmark model was simulated in seventy-four cities of Algeria. The simulation results were interpolated using geographic information systems to generate six high-resolution maps that spatially estimate and visualize the discomfort hours and cooling/heating energy needs. The unique methodology relies on a reliable weather dataset (2004–2018) and combines the power of building performance simulation and geographic information systems. The results of these analyses provide easy to understand and web-based atlas that can be used to explore regional and local climate and quantify the discomfort hours, the heating/cooling energy needs and energy use intensity. The spatial maps are not a static product, but rather data-rich content, which can be expanded to include the most important cities of Algeria. The capabilities of the tool allow architects and urban planners to understand the climate better and propose practical design guidance.

Several attempts have been made for estimating the vital swelling index parameter conducted by the expensive and time-consuming Oedometer test. However, they have only focused on the neuron network neglecting other advanced methods that could have increased the predictive capability of models. In order to overcome this limitation, the current study aims to elaborate an alternative model for estimating the swelling index from geotechnical physical parameters. The reliability of the approach is tested through several advanced machine learning methods like Extreme Learning Machine, Deep Neural Network, Support Vector Regression, Random Forest, LASSO regression, Partial Least Square Regression, Ridge Regression, Kernel Ridge, Stepwise Regression, Least Square Regression, and genetic Programing. These methods have been applied for modeling samples consisting of 875 Oedometer tests. Firstly, principal component analysis, Gamma test, and forward selection are utilized to reduce the input variable numbers. Afterward, the advanced techniques have been applied for modeling the proposed optimal inputs, and their accuracy models were evaluated through six statistical indicators and using K-fold cross validation approach. The comparative study shows the efficiency of FS-RF model. This elaborated model provided the most appropriate prediction, closest to the experimental values compared with other models and formulae proposed by the previous studies.