Search

Driven piles are used in many geological environments as a practical and convenient structural component. Hence, the determination of the drivability of piles is actually of great importance in complex geotechnical applications. Conventional methods of predicting pile drivability often rely on simplified physical models or empirical formulas, which may lack accuracy or applicability in complex geological conditions. Therefore, this study presents a practical machine learning approach, namely a Random Forest (RF) optimized by Bayesian Optimization (BO) and Particle Swarm Optimization (PSO), which not only enhances prediction accuracy but also better adapts to varying geological environments to predict the drivability parameters of piles (i.e. maximum compressive stress, maximum tensile stress, and blow per foot). In addition, support vector regression, extreme gradient boosting, k nearest neighbor, and decision tree are also used and applied for comparison purposes. In order to train and test these models, among the 4072 datasets collected with 17 model inputs, 3258 datasets were randomly selected for training, and the remaining 814 datasets were used for model testing. Lastly, the results of these models were compared and evaluated using two performance indices, i.e. the root mean square error (RMSE) and the coefficient of determination (R). The results indicate that the optimized RF model achieved lower RMSE than other prediction models in predicting the three parameters, specifically 0.044, 0.438, and 0.146; and higher R² values than other implemented techniques, specifically 0.966, 0.884, and 0.977. In addition, the sensitivity and uncertainty of the optimized RF model were analyzed using Sobol sensitivity analysis and Monte Carlo (MC) simulation. It can be concluded that the optimized RF model could be used to predict the performance of the pile, and it may provide a useful reference for solving some problems under similar engineering conditions. Graphic Abstract [ABSTRACT FROM AUTHOR]

To analyze the operation risk of check dams under extreme precipitation conditions, taking Ningxia area as an example, this paper carried out a risk assessment of check dams under extreme precipitation conditions in Ningxia through data collection, hydrological statistics, numerical simulation, and other methods. The conclusions are the following: (1) By the end of 2020, about 40% of the silt reservoir capacity of check dams in various water and soil conservation zones in Ningxia has been accumulated. During 1966–2020, the extreme precipitation and frequency of extreme precipitation in Ningxia increased while the intensity of extreme precipitation decreased. The extreme precipitation in Ningxia increased year by year and lasted longer. (2) Under two future scenarios of RCP4.5 (the full name of RCP is Representative Concentration Pathway) and RCP8.5, the extreme precipitation threshold in Ningxia is gradually decreasing from south to north. Extreme precipitation in the future will bring high risk to the operation of check dams in Ningxia. The results of this paper can provide a scientific basis for the operation and management of check dams in Ningxia. [ABSTRACT FROM AUTHOR]

Sewage treatment carbon emissions are one of the notable sources of total carbon emission in industrial parks. In order to explore the evolutionary characteristics of sewage treatment carbon emission in industrial parks and its coupling relationship with industrial economic development, based on the quarterly sewage quality monitoring data and regional economic development data of an energy and chemical industry park in Northern Shaanxi from 2016 to 2020, this paper analyzes the evolutionary characteristics of sewage treatment carbon emissions and the coupling relationship between economic development in the industrial parks by using the Intergovernmental Panel on Climate Change carbon emission accounting method and the coupling coordination degree model. The results show that the total carbon emission of sewage treatment in the industrial parks is increasing year by year, and the indirect carbon emissions occupy the dominant position. In 2020, the direct and indirect carbon emissions in the sewage treatment process accounted for 2.4% and 97.6% of the total carbon emission, respectively. It was found that the coupling and coordination relationship between sewage treatment carbon emissions and the economy has experienced the transformation process of serious imbalance—lagging economic development, lagging carbon emission and lagging economic development. In the past five years, the coordinated development degree of the two systems has increased year by year, and the benign mutual feedback mechanism between the two systems has gradually formed. However, regional economic development has lagged due to the impact of the COVID-19 epidemic, so speeding up regional economic development while protecting the environment is recommended. [ABSTRACT FROM AUTHOR]

In order to study quantitative indexes and characteristics of soil erosion on the Loess Plateau, degree of complexity and stability of erosion patterns are discussed. The fractal characteristics of soil erosion spatial patterns in the Dalihe River basin were evaluated by combining them with measurements extracted from the soil erosion database of the Loess Plateau, illustrated using GIS. Results demonstrate that fractal characteristics of spatial patterns of soil erosion intensity are obvious in the Dalihe River basin. Indeed, the results show that fractal dimension reflects the degree of soil erosion complexity at certain scales of observation, is indirectly related to soil erosion degree of complexity at certain scales of observation, which indirectly corresponds to the level of difficulty to implement soil-water erosion management. In addition, the fractal characteristics of soil erosion spatial patterns in the Dalihe River basin show that patch shapes correspond with size. In other words, when the patch size is about 0.2 km², scale conversion is observed in spatial patterns of soil erosion intensity and complexity of patch shape also changes. However, at patch sizes greater than 0.2 km², the two dimensional feature was gradually enhanced for a single patch, while with the patch size less than 0.2 km², the point feature was gradually enhanced. Thus, the order of complexity in spatial patterns of soil erosion intensities in the Dalihe River basin is drastic erosion > extreme erosion > serious erosion > moderate erosion, and thus the order of priorities for the implementation of management controls on soil erosion should be moderate erosion > serious erosion > extreme erosion > drastic erosion. [ABSTRACT FROM AUTHOR]

Ren, Z.; Feng Z.; Li, P.; Wang, D.; Cheng, S., and Gong J., 2017. Response of runoff and sediment yield from climate change in the Yanhe watershed, China. In: Zhi, Y. and Guido Aldana, P.A. (eds.), Sustainability of Water Resources and the Development of Coastal Environments: Select Proceedings from the 2016 International Conference on Water Resource and Environment (WRE2016). Journal of Coastal Research, Special Issue No. 80, pp. 30-35. Coconut Creek (Florida), ISSN 0749-0208. Changes in temperature and precipitation in the Loess Plateau, China have been studied for many years. The runoff and sediment yield in the Loess Plateau are sensitive to global climate change. Understanding the characteristics of runoff and sediment will be of great importance in the future. The Soil and Water Assessment Tool (SWAT) was used to simulate the runoff and the sediment yield in the Yanhe watershed, a typical water basin with soil erosion in the Loess Plateau. The resulting statistics of the SWAT simulation of the runoff and sediment yield were acceptable. The rainfall for the period from 2010 to 2099, as predicted by the Statistical Down Scaling Model (SDSM), was used to simulate the runoff and sediment yield in the future, using SWAT. Compared with the period from the 1980 to 2000, the annual precipitation increased by 9.2% to 16.4%. Under simulated future climate change, the annual runoff of the Yanhe watershed changes averaged −2.6% to 52.7%, compared with the baseline period. In the context of future climate change, in general, the runoff distribution was more even within the year when it increased significantly from March to May and decreased from July to August. The variations of the sediment yield for the watershed were −31.3% to 62.5% compare with the period from the 1980 to 2000. Overall, the trends of the sediment yield for the watershed were consistent with the runoff. [ABSTRACT FROM AUTHOR]