Cours d'economie politique

Prediction of chemical bioactivity and physical properties has been one of the most important applications of statistical and more recently, machine learning and artificial intelligence methods in chemical sciences. This field of research, broadly known as quantitative structure–activity relationships (QSAR) modeling, has developed many important algorithms and has found a broad range of applications in physical organic and medicinal chemistry in the past 55+ years. This Perspective summarizes recent technological advances in QSAR modeling but it also highlights the applicability of algorithms, modeling methods, and validation practices developed in QSAR to a wide range of research areas outside of traditional QSAR boundaries including synthesis planning, nanotechnology, materials science, biomaterials, and clinical informatics. As modern research methods generate rapidly increasing amounts of data, the knowledge of robust data-driven modelling methods professed within the QSAR field can become essential for scientists working both within and outside of chemical research. We hope that this contribution highlighting the generalizable components of QSAR modeling will serve to address this challenge.

QSAR without borders

Twenty-three of the more recent and commonly used equilibrium local scour equations for cohesionless sediments were evaluated using compiled laboratory and field databases. This investigation assembled 569 laboratory and 928 field data. A method for assessing the quality of the data was developed and applied to the data set. This procedure reduced the laboratory and field data to 441 and 791 values, respectively. Because the maturity of the scour hole at the time of measurement for the field data was unknown, they were only used to evaluate underprediction by the equations. A preliminary quality control screening of the equilibrium scour methods/equations reduced the number of equations from the initial 23 to 17. For this screening procedure the equations were used to compute scour depths for a wide, but practical, range of structure, flow, and sediment parameters. Those methods/equations yielding unreasonable (negative or extremely large) scour depths were eliminated from further consideration. The remaining 17 methods/equations were then analyzed using both laboratory and field data. Plots of underprediction error versus total error for the laboratory data and underprediction error for field data versus total error for laboratory data along with error statistics calculations assisted in the ranking of the equations. Equations from previous publications were melded and slightly modified to provide the best performing equation in that it yields the least total error and close to the least under-prediction error of those tested. The new equation is termed the Sheppard/Melville (S/M) equation in this paper.

Evaluation of Existing Equations for Local Scour at Bridge Piers

The Water Quality Index (WQI) is the most common indicator to characterize surface water quality. This study introduces a new ensemble machine learning model called Extra Tree Regression (ETR) for predicting monthly WQI values at the Lam Tsuen River in Hong Kong. The ETR model performance is compared with that of the classic standalone models, Support Vector Regression (SVR) and Decision Tree Regression (DTR). The monthly input water quality data including Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Dissolved Oxygen (DO), Electrical Conductivity (EC), Nitrate-Nitrogen ( NO 3 -N), Nitrite-Nitrogen ( NO 2 -N), Phosphate ( P O 4 3 - ), potential for Hydrogen (pH), Temperature (T) and Turbidity (TUR) are used for building the prediction models. Various input data combinations are investigated and assessed in terms of prediction performance, using numerical indices and graphical comparisons. The analysis shows that the ETR model generally produces more accurate WQI predictions for both training and testing phases. Although including all the ten input variables achieves the highest prediction performance ( R 2 t e s t = 0.98 , R M S E t e s t = 2.99 ), a combination of input parameters including only BOD, Turbidity and Phosphate concentration provides the second highest prediction accuracy ( R 2 t e s t = 0.97 , R M S E t e s t = 3.74 ). The uncertainty analysis relative to model structure and input parameters highlights a higher sensitivity of the prediction results to the former. In general, the ETR model represents an improvement on previous approaches for WQI prediction, in terms of prediction performance and reduction in the number of input parameters.

River water quality index prediction and uncertainty analysis: A comparative study of machine learning models

Particle swarm optimization (PSO) is an evolutionary computation approach to solve nonlinear global optimization problems. The PSO idea was made based on simulation of a simplified social system, the graceful but unpredictable choreography of birds flock. This system is initialized with a population of random solutions that are updated during iterations. Over the last few years, PSO has been extensively applied in various geotechnical engineering aspects such as slope stability analysis, pile and foundation engineering, rock and soil mechanics, and tunneling and underground space design. A review on the literature shows that PSO has utilized more widely in geotechnical engineering compared with other civil engineering disciplines. This is due to comprehensive uncertainty and complexity of problems in geotechnical engineering which can be solved by using the PSO abilities in solving the complex and multi-dimensional problems. This paper provides a comprehensive review on the applicability, advantages and limitation of PSO in different disciplines of geotechnical engineering to provide an insight to an alternative and superior optimization method compared with the conventional optimization techniques for geotechnical engineers.

Applications of Particle Swarm Optimization in Geotechnical Engineering: A Comprehensive Review

During the past decades, several investigations were conducted to assess the adequacy of countermeasures against local scour at bridge piers. The countermeasures can be broadly classified into two categories: (1) flow-altering and (2) bed-armouring countermeasures. Flow-altering countermeasures, as treated herein, can be classified into four main groups based on their shapes and performances. A comprehensive review of the up-to-date studies on various types of flow-altering countermeasures is presented, placing special emphasis on recently proposed methods while also revisiting studies of former methods. Experimental conditions of different studies under which the tests were performed are critically examined. A preliminary evaluation of the previously conducted experiments indicates that the results of several tests were influenced by side-wall, sediment size, flow shallowness and temporal effects. Experimental results on the combinations of different countermeasures, including their limitations and difficulties in field applications, are also discussed. Finally, suggestions are presented for further research on selected countermeasures.

Flow-altering countermeasures against scour at bridge piers: a review

In the present research, neuro-fuzzy-based group method of data handling (NF-GMDH) has been applied to evaluate the longitudinal dispersion coefficient in rivers. The NF-GMDH model has been improved through particle swarm optimization algorithms (PSO). Effective parameters on the longitudinal dispersion coefficient including flow depth, channel width, cross-sectional average velocity, and bed shear velocity were selected to characterize a correlation between input and output variables. Field and experimental data sets have been collected from different studies. The efficiency of the proposed NF-GMDH-PSO model for both training and testing stages has been investigated. The performance of the NF-GMDH-PSO model were compared with those obtained from the differential evolutionary (DE), model tree (MT), genetic algorithm (GA), artificial neural network (ANN), and traditional empirical equations. Results analysis showed that among the artificial intelligence approach-based equations, DE and GA methods performed better than the other methodologies. The most accurate empirical equations were also introduced. NF-GMDH-PSO network also predicted the longitudinal dispersion coefficient properly and can be considered as an alternative to the aforementioned successful formulas.

Evaluation of neuro-fuzzy GMDH-based particle swarm optimization to predict longitudinal dispersion coefficient in rivers

In this study, six different types of flow-altering countermeasures against pier scour were evaluated experimentally. The selected countermeasures were submerged vanes, bed sill, transverse sacrificial piles, collar, threading, and pier slot. Laboratory tests were performed in clear-water conditions with flow intensity slightly below the threshold of sediment motion. Tests were designed on the basis of the best configurations recommended in previous studies by different authors to obtain the maximum efficiency in terms of scour depth reduction. Results showed that some countermeasures, which were recommended as highly efficient in the literature, do not perform well under other test conditions; in particular, literature tests carried out with low flow intensity or short duration or in narrow-channel conditions are criticized. The efficiency of bed sill, submerged vanes, and threading was found to be less than 20%, whereas collar, pier slot, and transverse sacrificial piles reduced the maximum scour depth ...

Evaluation of Flow-Altering Countermeasures against Bridge Pier Scour

This study presents the results of clear-water tests on the following five combined flow-altering countermeasures against bridge pier scour: (1) submerged vanes and a bed sill, (2) slot and sacrificial piles, (3) a collar and sacrificial piles, (4) a slot and a collar, and (5) a bed sill and a collar. Each countermeasure was designed on the basis of the best configuration recommended in the literature. The results clarify that an improper combination of two countermeasures may be less effective than each individual countermeasure; combinations (1), (2), and (3) do not reduce the scour depth significantly with respect to the single countermeasures; combination (3) increases the scour rate during the first few hours with respect to a single collar; combination (4) may also prevent scour intrusion beneath a collar; and combination (5) in the best configuration reduces the scour depth significantly around the collar with respect to maximum scour depth of the unprotected pier, preventing also the scour hole re...

Combined flow-altering countermeasures against bridge pier scour

An experimental campaign of 21 long-duration tests on scouring at complex piers of different configurations was performed to investigate the effect of pile cap thickness on the temporal evolution of the maximum scour depth and the development of equilibrium conditions. Two test series were performed with two significantly different pile cap thicknesses over a wide range of pile cap elevations with respect to the expected scour hole and the approach flow depth. In addition, the accuracy of existing methods to calculate the maximum scour depth was evaluated and discussed. The results show that, in general, the thicker the pile cap, the deeper the corresponding scour hole. The increase in scour depth that is attributable to the pile cap thickness depends on the distance between the pile cap and the original bed level. The observed maximum scour depth was greater with the thicker pile cap (with respect to the thinner pile cap) when it was entirely immerged into the flow, partially buried, or totally buried at a small depth from the initial bed level. Depending on the distance between the pile cap and initial bed level, the pile cap thickness may also influence the temporal evolution of the maximum scour depth by increasing or reducing the scouring rate. DOI: 10.1061/(ASCE)HY.1943-7900.0000704. © 2013 American Society of Civil Engineers.

Ali Tafarojnoruz

Papers

Flow-altering countermeasures against scour at bridge piers: a review

Evaluation of neuro-fuzzy GMDH-based particle swarm optimization to predict longitudinal dispersion coefficient in rivers

Evaluation of Flow-Altering Countermeasures against Bridge Pier Scour

Combined flow-altering countermeasures against bridge pier scour

Effects of Pile Cap Thickness on the Maximum Scour Depth at a Complex Pier