Search

Determination of the permeability coefficient (K) of soil is considered as one of the essential steps to assess infiltration, runoff, groundwater, and drainage in the design process of the construction projects. In this study, three cost-effective algorithms, namely, artificial neural network (ANN), support vector machine (SVM), and random forest (RF), which are well-known as advanced machine learning techniques, were used to predict the permeability coefficient (K) of soil (10−9 cm/s), based on a set of simple six input parameters such as natural water content w (%), void ratio (e), specific density (g/cm3), liquid limit (LL) (%), plastic limit (PL) (%), and clay content (%). For this, a total of 84 soil samples data collected from the detailed design stage investigations of Da Nang-Quang Ngai national road project in Vietnam was used to generate training (70%) and testing (30%) datasets for building and validating the models. Statistical error indicators such as RMSE and MAE and correlation coefficient (R) were used to evaluate and compare performance of the models. The results show that all the three models performed well (R > 0.8) for the prediction of permeability coefficient of soil, but the RF model (RMSE = 0.0084, MAE = 0.0049, and R = 0.851) is more efficient compared with the other two models, namely, ANN (RMSE = 0.001, MAE = 0.005, and R = 0.845) and SVM (RMSE = 0.0098, MAE = 0.0064, and R = 0.844). Thus, it can be concluded that the RF model can be used for accurate estimation of the permeability coefficient (K) of the soil. [ABSTRACT FROM AUTHOR]

Determination of the permeability coefficient (K) of soil is considered as one of the essential steps to assess infiltration, runoff, groundwater, and drainage in the design process of the construction projects. In this study, three cost-effective algorithms, namely, artificial neural network (ANN), support vector machine (SVM), and random forest (RF), which are well-known as advanced machine learning techniques, were used to predict the permeability coefficient (K) of soil (10−9 cm/s), based on a set of simple six input parameters such as natural water content w (%), void ratio (e), specific density (g/cm3), liquid limit (LL) (%), plastic limit (PL) (%), and clay content (%). For this, a total of 84 soil samples data collected from the detailed design stage investigations of Da Nang-Quang Ngai national road project in Vietnam was used to generate training (70%) and testing (30%) datasets for building and validating the models. Statistical error indicators such as RMSE and MAE and correlation coefficient (R) were used to evaluate and compare performance of the models. The results show that all the three models performed well (R > 0.8) for the prediction of permeability coefficient of soil, but the RF model (RMSE = 0.0084, MAE = 0.0049, and R = 0.851) is more efficient compared with the other two models, namely, ANN (RMSE = 0.001, MAE = 0.005, and R = 0.845) and SVM (RMSE = 0.0098, MAE = 0.0064, and R = 0.844). Thus, it can be concluded that the RF model can be used for accurate estimation of the permeability coefficient (K) of the soil. [ABSTRACT FROM AUTHOR]

Landslides are a dangerous natural hazard that can critically harm road infrastructure in mountainous places, resulting in significant damage and fatalities. The primary purpose of this study was to assess the efficacy of three machine learning algorithms (MLAs) for landslide susceptibility mapping including random forest (RF), decision tree (DT), and support vector machine (SVM). We selected a case study region that is frequently affected by landslides, the important Kamyaran–Sarvabad road in the Kurdistan province of Iran. Altogether, 14 landslide evaluation factors were input into the MLAs including slope, aspect, elevation, river density, distance to river, distance to fault, fault density, distance to road, road density, land use, slope curvature, lithology, stream power index (SPI), and topographic wetness index (TWI). We identified 64 locations of landslides by field survey of which 70% were randomly employed for building and training the three MLAs while the remaining locations were used for validation. The area under the receiver operating characteristics (AUC) reached a value of 0.94 for the decision tree compared to 0.82 for the random forest, and 0.75 for support vector machines model. Thus, the decision tree model was most accurate in identifying the areas at risk for future landslides. The obtained results may inform geoscientists and those in decision-making roles for landslide management. [ABSTRACT FROM AUTHOR]

Saturated hydraulic conductivity (Ks) is an important soil characteristic that controls water moves through the soil. On the other hand, its measurement is difficult, time-consuming, and expensive; hence Pedotransfer Functions (PTFs) are commonly used for its estimation. Despite significant development over the years, the PTFs showed poor performance in predicting Ks. Using Genetic Algorithm (GA), two hybrid Machine Learning based PTFs (ML-PTF), i.e. a combination of GA with Multilayer Perceptron (MLP-GA) and Support Vector Machine (SVM-GA), were proposed in this study. We compared the performances of four machine learning algorithms for different sets of predictors. The predictor combination containing sand, clay, Field Capacity, and Wilting Point showed the highest accuracy for all the ML-PTFs. Among the ML-PTFs, the SVM-GA algorithm outperformed the rest of the PTFs. It was noticed that the SVM-GA PTF demonstrated higher efficiency than the MLP-GA algorithm. The reference model for hydraulic conductivity prediction was selected as the SVM-GA PTF paired with the K-5 predictor variables. The proposed PTFs were compared with 160 models from past literature. It was found that the algorithms advocated were an improvement over these PTFs. The current model would help in efficient spatio-temporal measurement of hydraulic conductivity using pre-available databases. [ABSTRACT FROM AUTHOR]

We mapped landslide susceptibility in Kamyaran city of Kurdistan Province, Iran, using a robust deep-learning (DP) model based on a combination of extreme learning machine (ELM), deep belief network (DBN), back propagation (BP), and genetic algorithm (GA). A total of 118 landslide locations were recorded and divided in the training and testing datasets. We selected 25 conditioning factors, and of these, we specified the most important ones by an information gain ratio (IGR) technique. We assessed the performance of the DP model using statistical measures including sensitivity, specificity, accuracy, F1-measure, and area under-the-receiver operating characteristic curve (AUC). Three benchmark algorithms, i.e., support vector machine (SVM), REPTree, and NBTree, were used to check the applicability of the proposed model. The results by IGR concluded that of the 25 conditioning factors, only 16 factors were important for our modeling procedure, and of these, distance to road, road density, lithology and land use were the four most significant factors. Results based on the testing dataset revealed that the DP model had the highest accuracy (0.926) of the compared algorithms, followed by NBTree (0.917), REPTree (0.903), and SVM (0.894). The landslide susceptibility maps prepared from the DP model with AUC = 0.870 performed the best. We consider the DP model a suitable tool for landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

In the present study, estimating pan evaporation (Epan) was evaluated based on different input parameters: maximum and minimum temperatures, relative humidity, wind speed, and bright sunshine hours. The techniques used for estimating Epan were the artificial neural network (ANN), wavelet-based ANN (WANN), radial function-based support vector machine (SVM-RF), linear function-based SVM (SVM-LF), and multi-linear regression (MLR) models. The proposed models were trained and tested in three different scenarios (Scenario 1, Scenario 2, and Scenario 3) utilizing different percentages of data points. Scenario 1 includes 60%: 40%, Scenario 2 includes 70%: 30%, and Scenario 3 includes 80%: 20% accounting for the training and testing dataset, respectively. The various statistical tools such as Pearson's correlation coefficient (PCC), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), and Willmott Index (WI) were used to evaluate the performance of the models. The graphical representation, such as a line diagram, scatter plot, and the Taylor diagram, were also used to evaluate the proposed model's performance. The model results showed that the SVM-RF model's performance is superior to other proposed models in all three scenarios. The most accurate values of PCC, RMSE, NSE, and WI were found to be 0.607, 1.349, 0.183, and 0.749, respectively, for the SVM-RF model during Scenario 1 (60%: 40% training: testing) among all scenarios. This showed that with an increase in the sample set for training, the testing data would show a less accurate modeled result. Thus, the evolved models produce comparatively better outcomes and foster decision-making for water managers and planners. [ABSTRACT FROM AUTHOR]

With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objective of our study is to evaluate the performance of Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), and Mahalanobis (MH) algorithms and compare them in order to generate a LULC map using data from Sentinel 2 and Landsat 8 satellites. Further, we also investigate the effect of a penalty parameter on SVM results. Our study uses different kernel functions and hidden layers for SVM and ANN algorithms, respectively. We generated the training and validation datasets from Google Earth images and GPS data prior to pre-processing satellite data. In the next phase, we classified the images using training data and algorithms. Ultimately, to evaluate outcomes, we used the validation data to generate a confusion matrix of the classified images. Our results showed that with optimal tuning parameters, the SVM classifier yielded the highest overall accuracy (OA) of 94%, performing better for both satellite data compared to other methods. In addition, for our scenes, Sentinel 2 date was slightly more accurate compared to Landsat 8. The parametric algorithms MD and MLC provided the lowest accuracy of 80.85% and 74.68% for the data from Sentinel 2 and Landsat 8. In contrast, our evaluation using the SVM tuning parameters showed that the linear kernel with the penalty parameter 150 for Sentinel 2 and the penalty parameter 200 for Landsat 8 yielded the highest accuracies. Further, ANN classification showed that increasing the hidden layers drastically reduces classification accuracy for both datasets, reducing zero for three hidden layers. [ABSTRACT FROM AUTHOR]