A comprehensive comparison of different regression techniques and nature-inspired optimization algorithms to predict carbonation depth of recycled aggregate concrete

The utilization of recycled aggregates(RA)for concrete production has the potential to offer substantial environmental and economic advantages.However,RA concrete is plagued with considerable durability concerns,particularly carbonation.To advance the application of RA concrete,the establishment of a reliable model for predicting the carbonation is needed.On the one hand,concrete carbonation is a long and slow process and thus consumes a lot of time and energy to monitor.On the other hand,carbonation is influenced by many factors and is hard to predict.Regarding this,this paper proposes the use of machine learning techniques to establish accurate prediction models for the carbonation depth(CD)of RA concrete.Three types of regression techniques and meta-heuristic algorithms were employed to provide more alternative predictive tools.It was found that the best prediction performance was obtained from extreme gradient boosting-multi-universe optimizer(XGB-MVO)with R^(2) value of 0.9949 and 0.9398 for training and testing sets,respectively.XGB-MVO was used for evaluating physical laws of carbonation and it was found that the developed XGB-MVO model could provide reasonable predictions when new data were investigated.It also showed better generalization capabilities when compared with different models in the literature.Overall,this paper emphasizes the need for sustainable solutions in the construction industry to reduce its environmental impact and contribute to sustainable and low-carbon economies.

Research of Neural Network Based on Improved PSO Algorithm for Carbonation Depth Prediction of Concrete

Firstly,neural network based on improved particle swarm optimization (PSO)algorithm is introduced in this paper. Based on the data collected from projects in typical areas,the concrete carbonation depth is assessed with consideration of various factors such as unit cement consumption (C),unit water consumption (W),binder material content (B),water binder ratio (W/B ),concrete strength (MPa),rapid carbonization days (D),fly ash consumption of unit volume concrete(FA),fly ash percentage of total cementitious materials (FA%),expansion agent consumption of unit volume concrete(EA),expansion agent percentage of total cementitious materials (FA%).Gaining the data from project-experiment,a model is presented to calculate and forecast carbonation depth using neural network based on improved PSO algorithm. The calculation results indicate that this algorithm accord with the prediction carbonation depth of concrete accuracy requirements and has a better convergence and generalization,worth being popularized.

Durability Analysis and Carbonation Life Prediction of Shajiang River Bridge

The shajiang river bridge on the appearance test, concrete rebound detection, concrete cover depth detection, concrete carbonation depth detection, concrete chlorine ion content detection, and the detection results in statistics and analysis. Based on the bridge of the service the atmospheric environment parameters and testing data, the paper calculates and analyzes the main stress components the carbonation bridge reliability index and remaining life of carbide, assessing the bridge for the service life and reinforcement maintenance and offer the scientific basis.

Microfossils, carbonate lysocline and compensation depth in surface sediments of the northeastern South China Sea

Based on the quantitative analyses of abundance of planktonic foraminifera, benthic foraminifera, calcareous nannofossils, the ratios of calcareous to siliceous microfossils, and the determination of carbonate contents in the surface sediments of the northeastern South China Sea, it has been found that the carbonate contents, the abundance of planktonic foraminifera and calcareous nannoplankton, and the ratio of calcareous microfossils decrease rapidly while the ratio of the benthic foraminifera to the total foraminiferal fauna, specific value of siliceous microfossils, and the percentage of the agglutinated tests in the benthic foraminiferal fauna increase with the water depth. The results indicate that the microfossils abundance and ratio, and the carbonate content are closely related to the carbonate lysocline and carbonate compensation depth (CCD) in the study area. In addition, the carbonate lysocline and the CCD are different between the southern and northern parts of the South China Sea. Both the lysocline and the CCD are deeper in the south with 2 600 and 3 600 m than in the north with 2 200 and 3 400 m, respectively.

Auger Depth Profiling of Carbonized SiC/Si Samples

Silicon carbide (SiC) has been prepared by passing natural gas over (100) oriented hot Si substrate at different temperatures in the range 930~1000℃. Reaction times of 60 and 90 min are used.Depth profile, using Auger Electron Spectroscopy, shows the formation of SiC under a thin coating of carbon for the samples prepared at 930 and 950℃. Annealing, at 1050℃ for 12 h,results in a more pronounced formation of SiC. It is found that at the temperature of 1000℃and reaction times of 60 and 90 min, a hard diamond-like coating is formed.

Coupling between the Cenozoic west Pacific subduction initiation and decreases of atmospheric carbon dioxides

At the beginning of the Cenozoic,the atmospheric CO_(2)concentration increased rapidly from~2000 ppmv at 60 Ma to~4600 ppmv at 51 Ma,which is 5–10 times higher than the present value,and then continuous declined from~51 to 34 Ma.The cause of this phenomenon is still not well understood.In this study,we demonstrate that the initiation of Cenozoic west Pacific plate subduction,triggered by the hard collision in the Tibetan Plateau,occurred at approximately 51 Ma,coinciding with the tipping point.The water depths of the Pacific subduction zones are mostly below the carbonate compensation depths,while those of the Neo-Tethys were much shallower before the collision and caused far more carbonate subducting.Additionally,more volcanic ashes erupted from the west Pacific subduction zones,which consume CO_(2).The average annual west Pacific volvano eruption is 1.11 km~3,which is higher than previous estimations.The amount of annual CO_(2)absorbed by chemical weathering of additional west Pacific volcanic ashes could be comparable to the silicate weathering by the global river.We propose that the initiation of the western Pacific subduction controlled the long-term reduction of atmospheric CO_(2)concentration.

Unraveling the Cenozoic carbon cycle by reconstructing carbonate compensation depth(CCD)

The Carbonate Compensation Depth(CCD)refers to the depth within the ocean where the production and dissolution rates of carbonates reach equilibrium,widely likened to the oceanic calcareous‘snowline’.The reconstruction of deep-time CCD has significant implications for understanding ocean circulation,seawater chemical conditions,sediment distribution,and the surface carbon cycle.This paper critically reviews the methods for CCD reconstruction,summarizes the driving mechanisms of the Cenozoic CCD evolution and its association with the carbon cycle,and offers insights into future directions for CCD research.CCD reconstruction has evolved over the past half century from early qualitative to quantitative methods.These methodological improvements have markedly improved the accuracy and resolution of CCD.Existing studies have indicated a general trend of the CCD deepening across major ocean basins since the Cenozoic,interspersed with a minor shallowing phase during the mid-Miocene.The variations in the CCD are primarily influenced by factors such as ocean productivity,weathering,and shelf-basin partitioning.During climate events such as the Paleocene-Eocene Thermal Maximum,the CCD exhibits pulselike fluctuations.Future research should focus on precision and quantification while integrating model simulations to further explore the correlations and response mechanisms between the CCD and the paleoclimate as well as the carbon cycle.

Pedotransfer Functions for Estimating Soil Bulk Density:A Case Study in the Three-River Headwater Region of Qinghai Province,China

Bulk density(BD) is an important soil physical property and has significant effect on soil water conservation function. Indirect methods, which are called pedotransfer functions(PTFs), have replaced direct measurement and can acquire the missing data of BD during routine soil surveys. In this study, multiple linear regression(MLR) and artificial neuron network(ANN) methods were used to develop PTFs for predicting BD from soil organic carbon(OC), texture and depth in the Three-River Headwater region of Qinghai Province, China. The performances of the developed PTFs were compared with 14 published PTFs using four indexes, the mean error(ME), standard deviation error(SDE), root mean squared error(RMSE) and coefficient of determination(R^2). Results showed that the performances of published PTFs developed using exponential regression were better than those developed using linear regression from OC. Alexander(1980)-B, Alexander(1980)-A and Manrique and Jones(1991)-B PTFs, which had good predictions, could be applied for the soils in the study area. The PTFs developed using MLR(MLR-PTFs) and ANN(ANN-PTFs) had better soil BD predictions than most of published PTFs. The ANN-PTFs had better performances than the MLR-PTFs and their performances could be improved when soil texture and depth were added as predictor variables. The idea of developing PTFs for predicting soil BD in the study area could provide reference for other areas and the results could lay foundation for the estimation of soil water retention and carbon pool.