66 Pags.- 1 Tabl.- 7 Figs. The definitive version is available at: http://www.sciencedirect.com/science/journal/00128252Soil erosion is a serious ecological and environmental problem, and the main cause of land degradation in many ecosystems at global scale. Detachment of soil particles by raindrop splash is the first stage in the soil erosion process. A review of the scientific literature published in peer-reviewed international journals (ISI) over the last decades on splash erosion research sheds light on the current scientific knowledge on this topic. In addition, it highlights the research gaps and unanswered questions in our understanding of soil erosion processes due to splash. In this literature review, a bibliographic search in Web of Science by the Institute for Scientific Information (ISI) database was carried out on August the 9th, 2016, that returned 669 papers containing the words “splash erosion”. The research found was categorised according to a number of criteria: i) devices used to measure splash erosion, ii) advantages and disadvantages of these devices, iii) splash erosion studies by country, iv) date of publication of the first article, v) evolution of the number of articles published in each ten-year period, vi) concepts studied, vii) keywords, viii) authors, ix) number of citations, and x) most cited articles. After this review a synthesis of the information that the science has published about splash erosion was made in order to improve our understanding about splash erosion, by identifying the research questions that still remain unanswered today about the first detachment mechanism. From this review several issues were found important for the advancement of this research topic: a) further study of the known basic factors influencing splash erosion; b) description and quantification of sources of uncertainty about the measurement of different variables; c) to understand the influences that the chosen research approach by individual researchers will have in the final result; and, d) to study the impact of drivers or mitigation techniques that may affect splash erosion.This research was funded by the José Castillejo Grant, a Program for Junior professors of the Ministry of Education, Culture and Sports, Spain (CAS16/00385).Peer reviewe
Several types of research currently use machine learning (ML) methods to estimate the mechanical characteristics of concrete. This study aimed to compare the capacities of four ML methods: eXtreme gradient boosting (XG Boost), gradient boosting (GB), Cat boosting (CB), and extra trees regressor (ETR), to predict the splitting tensile strength of 28-day-old self-compacting concrete (SCC) made from recycled aggregates (RA), using data obtained from the literature. A database of 381 samples from literature published in scientific journals was used to develop the models. The samples were randomly divided into three sets: training, validation, and test, with each having 267 (70%), 57 (15%), and 57 (15%) samples, respectively. The coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) metrics were used to evaluate the models. For the training data set, the results showed that all four models could predict the splitting tensile strength of SCC made with RA because the R2 values for each model had significance higher than 0.75. XG Boost was the model with the best performance, showing the highest R2 value of R2 = 0.8423, as well as the lowest values of RMSE (=0.0581) and MAE (=0.0443), when compared with the GB, CB, and ETR models. Therefore, XG Boost was considered the best model for predicting the splitting tensile strength of 28-day-old SCC made with RA. Sensitivity analysis revealed that the variable contributing the most to the split tensile strength of this material after 28 days was cement.
30 April 2022 in Archives of Civil and Mechanical Engineering