Search Results (5)

Accurately predicting the permeability of coarse-grained soils is crucial for ensuring geotechnical safety and performance. In this study, 64 coarse-grained soil (CGS) samples were designed using a negative exponential gradation equation (NEGE), and computational fluid dynamics–discrete element method (CFD-DEM) coupled seepage simulations were conducted to generate a permeability coefficient (k) dataset comprising 256 entries under varying porosity and gradation conditions. Three machine learning models—a neural network model (BPNN), a regression model (GPR), and a tree-based model (RF)—were employed to predict k, with hyperparameters optimized via particle swarm optimization (PSO) and four-fold cross-validation applied to improve generalization. Gray relational analysis (GRA) revealed that all input parameters (α, β, d_max, n) significantly influence k (R > 0.6). The interquartile range (IQR) method confirmed data suitability for modeling. Among the models, BPNN achieved the best performance (R² = 0.99, MAE = 1.5, RMSE = 2.9, U₉₅ = 0.4), effectively capturing the complex nonlinear relationship between gradation and permeability. GPR (R² = 0.92) was hindered by kernel selection and noise sensitivity, while RF (R² = 0.97) was limited by its discrete regression nature. Compared to a traditional empirical model (R² = 0.9031), BPNN improved prediction accuracy by 10.13%, demonstrating the advantage of data-driven methods for evaluating CGS permeability. Full article

A non-periodic “step-like” variation in displacement is exhibited owing to the repeated instability of expansive soil landslides. The dynamic prediction of deformation for expansive soil landslides has become a challenge in actual engineering for disaster prevention and mitigation. Therefore, a support vector regression prediction (AMPSO-SVR) model based on adaptive mutation particle swarm optimization is proposed, which is suitable for small samples of data. The shallow displacement is decomposed into a trend component and fluctuating component by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and the trend displacement is predicted by cubic polynomial fitting. In this paper, the multiple disaster-inducing factors of expansive landslides and the time hysteresis effect between displacement and its influencing factors are fully considered, and the crucial influencing factors which eliminate the time lag effect and state factors are input into the model to predict the fluctuation displacement. Monitoring data in the Ningming area of China are employed for the model validation. The predicted results are compared with those of the traditional model. The model performance is evaluated through indicators such as the goodness of fit R² and root mean square error RMSE. The results show that the prediction RMSE of the new model for three monitoring stations can reach 2.6 mm, 6.6 mm, and 2.5 mm, respectively. Compared with the common Grid search support vector regression (GS-SVR), the Particle Swarm Optimization Support Vector Regression (PSO-SVR) and Back Propagation Neural Network (BPNN) models have average improvements of 58.4%, 38.1%, and 25.2% respectively. The goodness of fit R² is superior to 0.99 in the new method. The proposed model can effectively be deployed for the displacement prediction of non-periodic stepped expansive soil landslides driven by multiple influencing factors, providing a reference idea for the deformation prediction of expansive soil landslides. Full article

Soil organic matter (SOM) is a key factor for evaluating soil fertility. Rapidly monitoring organic matter content in desert soil can provide a scientific basis for the rational development and utilization of reserve arable land resources. Although spectral inversion accuracy for SOM under laboratory-controlled conditions is high, it is time-consuming and costly compared to the in situ spectroscopic determination method. However, in situ spectroscopy causes losses in accuracy due to interference from external environmental factors (e.g., the surface roughness of soil, changes in weather conditions, atmospheric water vapor, etc.). Therefore, reducing or removing the interference of external environmental factors to improve the accuracy of in situ spectroscopy for estimating SOM is challenging. In this study, visible and near-infrared (Vis-NIR) in situ spectral data were collected from 135 topsoil (0–20 cm) samples in a desert area of northwestern China, and organic matter content was measured. Three spectral pre-processing methods—the standard normal transform (SNV), reciprocal logarithm (log(1/R)) and normalization (NOR)—combined with three feature variable selection methods—the particle swarm algorithm (PSO), ant colony algorithm (ACO) and simulated annealing (SA) algorithm—were used to filter the spectral feature bands of SOM, and then partial least squares regression (PLSR), a back propagation neural network (BPNN) and a convolutional neural network (CNN) were used to construct the estimation models of SOM. The results indicated that the SNV could enhance the spectral information related to SOM and improve the accuracy of model estimation, and it was one of the most effective spectral pretreatment methods. Compared with the model constructed with the full-band spectroscopy method, the feature variable selection method could effectively improve the estimation accuracy of the Vis-NIR in situ spectroscopy model. The most obvious improvement was found with PSO, where R² and RPD were improved by more than 0.34 and 0.16, respectively, and RMSE was reduced by more than 0.29 g kg⁻¹. The accuracy of the CNN model was higher than that of the BPNN and PLSR models, both for the inversion model of SOM built from full-band spectral data and the bands selected by the characteristic variable selection method. SNV-PSO-CNN is the optimal hybrid model for in situ spectral measurement of SOM (R² = 0.71, RPD = 1.88, RMSE = 1.67 g kg⁻¹) and can realize the quantitative in situ spectral inversion of SOM in desert soils. Full article

Soil salinization is prominent environmental issue in arid and semi-arid regions, such as Xinjiang in Northwest China. Salinization severely restricts economic and agricultural development and would lead to ecosystem degradation. Finding a method of rapidly and accurately determining soil salinity (SS) is one of the main challenges in salinity evaluation, saline soil development, and utilization. In situ visible and near infrared (Vis-NIR) spectroscopy has proven to be a promising technique for detecting soil properties since it can realize real-time, rapid detection of SS. However, it still remains challenging whether Vis-NIR in situ spectroscopy can invert SS with high accuracy due to the interference of environmental factors (e.g., light, water vapor, solar altitude angle, etc.) on the spectral in the field. To fill this knowledge gap, we collected Vis-NIR in situ spectral and lab-measured SS data from 135 surface soil samples in the Kongterik Pasture Nature Reserve (KPNR) in the desert oasis ecotone of southern Xinjiang, China. We used genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA) algorithms to select the feature bands of SS. Subsequently, we combined extreme learning machines (ELM), back-propagation neural networks (BPNN), and convolutional neural networks (CNN) to build inversion models of SS. The results showed that different feature bands selection methods could improve the Vis-NIR in situ spectral prediction model accuracy. Either SS inversion models were built using full-band spectral data or feature-band spectral data. Compared with the full-band (401–2400 nm) spectral modeling, the validation set R² of ELM, BPNN, and CNN models built selected feature bands selected by PSO, GA, and SA, respectively, were improved by more than 0.06. The accuracy of predicting SS varied widely among modeling methods. The accuracy of CNN model was obviously higher than that of BPNN and ELM models. The optimal hybrid model for predicting SS constructed in this study is SA-CNN model (R² = 0.79, RMSE = 9.41 g kg⁻¹, RPD = 1.81, RPIQ = 2.37). This study showed that the spectral feature bands selection methods can reduce the influence of environmental factors on in situ spectroscopy and significantly enhance the inversion accuracy of SS. The present study provided that estimating SS using in situ Vis-NIR spectral is feasible. Full article

Soil heavy metals affect human life and the environment, and thus, it is very necessary to monitor their contents. Substantial research has been conducted to estimate and map soil heavy metals in large areas using hyperspectral data and machine learning methods (such as neural network), however, lower estimation accuracy is often obtained. In order to improve the estimation accuracy, in this study, a back propagation neural network (BPNN) was combined with the particle swarm optimization (PSO), which led to an integrated PSO-BPNN method used to estimate the contents of soil heavy metals: Cd, Hg, and As. This study was conducted in Guangdong, China, based on the soil heavy metal contents and hyperspectral data collected from 90 soil samples. The prediction accuracies from BPNN and PSO-BPNN were compared using field observations. The results showed that, 1) the sample averages of Cd, Hg, and As were 0.174 mg/kg, 0.132 mg/kg, and 9.761 mg/kg, respectively, with the corresponding maximum values of 0.570 mg/kg, 0.310 mg/kg, and 68.600 mg/kg being higher than the environment baseline values; 2) the transformed and combined spectral variables had higher correlations with the contents of the soil heavy metals than the original spectral data; 3) PSO-BPNN significantly improved the estimation accuracy of the soil heavy metal contents, with the decrease in the mean relative error (MRE) and relative root mean square error (RRMSE) by 68% to 71%, and 64% to 67%, respectively. This indicated that the PSO-BPNN provided great potential to estimate the soil heavy metal contents; and 4) with the PSO-BPNN, the Cd content could also be mapped using HuanJing-1A Hyperspectral Imager (HSI) data with a RRMSE value of 36%, implying that the PSO-BPNN method could be utilized to map the heavy metal content in soil, using both field spectral data and hyperspectral imagery for the large area. Full article