RESUMEN
For economical and sustainable benefits, conventional retaining walls are being replaced by geosynthetic reinforced soil (GRS). However, for safety and quality assurance purposes, prior tests of pullout capacities of these materials need to be performed. Conventionally, these tests are conducted in a laboratory with heavy instruments. These tests are time-consuming, require hard labor, are prone to error, and are expensive as a special pullout machine is required to perform the tests and acquire the data by using a lot of sensors and data loggers. This paper proposes a data-driven machine learning architecture (MLA) to predict the pullout capacity of GRS in a diverse environment. The results from MLA are compared with actual laboratory pullout capacity tests. Various input variables are considered for training and testing the neural network. These input parameters include the soil physical conditions based on water content and external loading applied. The soil used is a locally available weathered granite soil. The input data included normal stress, soil saturation, displacement, and soil unit weight whereas the output data contains information about the pullout strength. The data used was obtained from an actual pullout capacity test performed in the laboratory. The laboratory test is performed according to American Society for Testing and Materials (ASTM) standard D 6706-01 with little modification. This research shows that by using machine learning, the same pullout resistance of a geosynthetic reinforced soil can be achieved as in laboratory testing, thus saving a lot of time, effort, and money. Feedforward backpropagation neural networks with a different number of neurons, algorithms, and hidden layers have been examined. The comparison of the Bayesian regularization learning algorithm with two hidden layers and 12 neurons each showed the minimum mean square error (MSE) of 3.02 × 10-5 for both training and testing. The maximum coefficient of regression (R) for the testing set is 0.999 and the training set is 0.999 for the prediction interval of 99%.
Asunto(s)
Aprendizaje Automático , Suelo , Teorema de Bayes , Redes Neurales de la Computación , AlgoritmosRESUMEN
After the accident at the Fukushima Daiichi nuclear power plant in Japan, the migration of radioactive cesium (Cs) in soils has become a crucial issue since this can negatively affect human health and the surrounding environment. Dissolved organic matter (DOM) may have different influences on Cs migration in soils depending on Cs adsorption sites with different selectivity. It is unclear how DOM affects the rapid migration of Cs in soils under flowing water conditions during rainfall events. This study evaluated the effects of DOM on Cs migration in weathered granite soil depending on Cs adsorption sites by conducting laboratory experiments under different DOM conditions and Cs concentrations in the liquid phase. Cs concentration can affect the fraction of Cs adsorbed onto differently selective sites, and DOM can have different influences on Cs migration in the soil accordingly. Under condition of high-Cs concentration, the DOM adsorbed on the soil reduced Cs migration due to increasing Cs electrostatic adsorption to less selective sites in the soil. Meanwhile, under low-Cs concentration, the DOM adsorbed on the soil enhanced Cs migration because the DOM on the soil decreased the Cs adsorption to highly selective sites. Furthermore, DOM in the liquid phase detached the Cs adsorbed on the less selective sites and enhanced Cs migration in the soil, regardless of the Cs concentration.
Asunto(s)
Accidente Nuclear de Fukushima , Monitoreo de Radiación , Contaminantes Radiactivos del Suelo , Cesio/análisis , Radioisótopos de Cesio/análisis , Materia Orgánica Disuelta , Humanos , Japón , Dióxido de Silicio , Suelo , Contaminantes Radiactivos del Suelo/análisis , AguaRESUMEN
Highly weathered acidic soils tend to have high phosphorus adsorption rates. Studying the differential phosphorus adsorption and desorption characteristics of these soils is of great significance to improve phosphorus utilization efficiency and reduce soil phosphorus loss in agricultural management. Erosive weathered granite soil (TL-Tillage layer, LL-Laterite layer, and SL-Sand layer) in Anji County, Zhejiang Province were selected for batch experiments and phosphorus fractionation test. The soil properties that are generally considered to have a greater impact on phosphorus adsorption and desorption are also studied. Derived from the Langmuir adsorption isotherm, the maximum absorption capacity (Qmax) of phosphorus in TL soil was greater than that in LL and SL soil. With a pH of 4.3-5.0, the three soils have the most phosphorus adsorption. The desorption ratio (Dr) in the SL soil is larger than the LL and TL soil. Six key soil property indicators can fit Qmax and Dr values well. Al-P is the main fraction in the phosphorus adsorption-desorption process. The particle size classification (PSC) method can be used to accurately calculate soil-specific surface area. The results of the soil phosphorus adsorption-desorption test can be used as an explanation of the results of artificial rainfall tests. Our results reveal the differential adsorption-desorption mechanism of eroded weathered granite soil, and provide a reference for selecting soil indicators for soil adsorption-desorption studies in different regions.