Search

The COVID-19 pandemic has profoundly impacted every aspect of our lives, from economic to the social facets of contemporary society. While the new COVID-19 waves may not be anticipated to be as severe as previous ones, it would be unreasonable to assume that they will cease any time soon. Consequently, forecasting the number of future infections, recovered patients, and death cases remains a very much logical step in trying to fight against further waves, in conjunction with ongoing vaccination efforts. In this paper, we investigate the efficiency of three intelligent machine learning algorithms, namely GMDH, Bi-LSTM, and GA + NN, for COVID-19 forecasting, with an application to Iran and the United Kingdom. The experimental results show that the algorithms can be used to forecast the next six months of COVID-19 in terms of confirmed, recovered, and death cases, which gives a more ample timeframe for using the results to make better practical yet strategic decisions and take appropriate actions or measures to deploy resources effectively to contain or curb the spread of the coronavirus. Despite the distinct dynamics observed in the data, our analysis proves the robustness of the employed models. [ABSTRACT FROM AUTHOR]

The concept of leveraging the predictive capacity of predisposing factors for landslide susceptibility (LS) modeling has been continuously improved in recent work focusing on computational and machine learning algorithms. This paper explores the predictive capacity of different approaches to LS modelling using artificial intelligence. The key objective of this study is to estimate a LS map for the Taleghan-Alamut basin of Iran using Credal Decision Tree (CDT)-based (i.e. CDT-Bagging, CDT-Multiboost and CDT-SubSpace) hybrid machine learning approaches, which are state-of-the-art soft computing approaches that are hardly ever utilized in the assessment of LS. In this study, we used eighteen landslide predisposing factors (LPFs) that we considered to be the most important local morphological and geo-environmental factors influencing the occurrence of landslides. We calculated the significance of each of the LPFs in the landslide susceptibility assessment using the Random Forest Method. We also employed the Receiver Operating Characteristic curve, precision, performance, map robustness measurement and selection of the best-fitting models. The results shows that, compared to the other models, the CDT-Multiboost is the excellent model in this perspective with an average area under curve (AUC) of 0.993 based on a 4-fold cross-validation. We, therefore, consider the CDT-Multiboost models to be an effective method for improving spatial prediction of LS where landslide scarps or bodies are not clearly identified during the preparation of landslide inventory maps. Therefore, it will be helpful for preparing future landslide inventory maps and mitigate landslide damages. [ABSTRACT FROM AUTHOR]

By accurate predicting of pipe bursts, it is possible to schedule pipe maintenance, rehabilitation and improve level of services in Water Distribution Networks (WDNs). In recent years, artificial intelligence techniques have been used vastly in pipe burst prediction. These techniques need big input dataset for deep learning but big dataset might not be available in old WDNs. This paper aimed to compare the performance of multivariate adaptive regression splines (MARS) and regressive convolution neural network with least square support vector regression (RCNN-LSSVR) for predicting of Pipe Burst Rate (PBR) with limited dataset. Pipes age, diameter, depth of installation, length, average and maximum hydraulic pressure are considered as effective parameters of PBR. Data collected from real-case study in Iran include 158 cases for polyethylene and 124 cases for asbestos cement pipes during 2012–2019. The results indicate that RCNN-LSSVR model has a great performance of PBR prediction on limited dataset. [ABSTRACT FROM AUTHOR]

The goal of this study is mapping flood risks over Golestan province in Iran using one of the artificial intelligence methods called multivariate adaptive regression splines (MARS). In this sense, 14 flood conditioning factors were considered and the maps were made in ArcGIS. Additionally, two novel metaheuristic algorithms namely cat swarm optimization (CSO) and water cycle algorithm (WCA) were applied to optimized the MARS parameters. According to the results, the area under the curve provided by receiver operating characteristic curve illustrated the accuracy of 94.5% for the integrated MARS-WCA. As regards the MARS-WCA model, a total area of 44.74% was identified as highly susceptible for flooding. In addition, to determine the maximum influence of input variables on mapping flood risks, the sensitivity analysis was performed. By performing sensitivity analysis, altitude and slope with NDVI were the three important variables, respectively, for spatially flash flood prediction. [ABSTRACT FROM AUTHOR]

Snow avalanches impose a considerable threat to infrastructure and human safety in snow bound mountain areas. Nevertheless, the spatial prediction of snow avalanches has received little research attention in many vulnerable parts of the world, particularly in developing countries. The present study investigates the applicability of a stand alone convolutional neural network (CNN) model, as a deep learning approach, along with two metaheuristic algorithms including grey wolf optimization (CNN-GWO) and imperialist competitive algorithm (CNN-ICA) in snow avalanche modelling in the Darvan watershed, Iran. The analysis was based on thirteen potential drivers of avalanche occurrence and an inventory map of previously documented avalanche occurrences. The efficiency of models' performance was evaluated by Area Under the Receiver Operating Characteristic curve (AUC) and the Root Mean Square Error (RMSE). The CNN-ICA model yielded the highest accuracy in both training (AUC = 0.982, RMSE = 0.067) and validation (AUC = 0.972, RMSE = 0.125) steps, followed by the CNN-GWO model (AUC of 0.975 for training, RMSE of 0.18 for training, AUC of 0.968 for validation, RMSE of 0.157 for validation). However, the standalone CNN model showed lower goodness-of- fit (AUC = 0.864, RMSE = 0.22) and predictive performance (AUC = 0.811, RMSE = 0.330). The approach utilized in this study is broadly applicable for identifying areas where avalanche hazard is likely to be high and where mitigation measures or corresponding land use planning should be prioritized. [ABSTRACT FROM AUTHOR]

This study tested three multilayer Markov random-fields (MRFs) models -- multicue MRF (MMRF), conditional mixed MRF (CMMRF), and fusion MRF (FMRF) -- to produce groundwater nitrate pollution maps for the first time. Random forest (RF) was also used as a baseline model. Several cutoff-dependent and cutoff-independent evaluation metrics were used to assess the goodness-of-fit and predictive performance aspects of the models. Validation results indicated that the conditional mixed MRF (with AUC = 0.805, TSS = 0.692, MCC= 0.692, F-score= 0.846, E=0.846, MR = 0.153) outperformed the other models when producing groundwater nitrate pollution maps. The next best model was RF. All models identified hydraulic conductivity(with > 50%) as the most important variable for investigating groundwater nitrate pollution, whereas lineament density (with <7%) was the least important. Since the goodness-of-fit of all applied models ranged from very good (0.7

In this research, the mean monthly groundwater level with a range of 3.78 m in Qoşaçay plain, Iran, is forecast. Regarding three different layers of gated recurrent unit (GRU) structures and a hybrid of variational mode decomposition with gated recurrent unit (VMD-GRU), deep learning-based neural network models are developed. As the base model for performance comparison, the general single-long short-term memory-layer network model is developed. In all models, the module of sequence-to-one is used because of the lack of meteorological variables recorded in the study area. For modeling, 216 monthly datasets of the mean monthly water table depth of 33 different monitoring piezometers in the period April 2002–March 2020 are utilized. To boost the performance of the models and reduce the overfitting problem, an algorithm tuning process using different types of hyperparameter accompanied by a trial-and-error procedure is applied. Based on performance evaluation metrics, the total learnable parameters value and especially the model grading process, the new double-GRU model coupled with multiplication layer (×) (GRU2× model) is chosen as the best model. Under the optimal hyperparameters, the GRU2× model results in an R2 of 0.86, a root mean square error (RMSE) of 0.18 m, a corrected Akaike's information criterion (AICc) of −280.75, a running time for model training of 87 s and a total grade (TG) of 6.21 in the validation stage; and the hybrid VMD-GRU model yields an RMSE of 0.16 m, an R2 of 0.92, an AICc of −310.52, a running time of 185 s and a TG of 3.34. [ABSTRACT FROM AUTHOR]

In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models. [ABSTRACT FROM AUTHOR]

Soil water content characteristics included field capacity (FC) and permanent wilting point (PWP) are key soil indicators to study permeability, soil water retention capacity, drainage, irrigation, plant water stress and solute movement. It is necessary to use an appropriate model for predicting these characteristics because of the hardness of their measurement. The present research shows a comparison of intelligent models included ANN, ANFIS, SVM and SVM optimised by firefly and particle swarm meta-heuristic algorithms (SVM-FFA and SVM-PSA) to predict soil water content at −33 and −1500 kPa matric potentials in agricultural soils. Results showed that the SVM-PSA and SVM-FFA hybrid models presented the best performance rather than the others, with predictor variables included geometric mean diameter (dg) of soil particles, bulk density, organic carbon, NDVI and NSMI and the values of R2 and NRMSE in validation dataset, 0.94, 0.081, 0.96 and 0.077 for FC and PWP in SVM-PSA, respectively, and 0.96, 0.079, 0.97 and 0.075 for FC and PWP in SVM-FFA model. Therefore, these intelligent machines are preferable for accurate prediction and could be used to predict soil water content of soils with different soil textures in other regions of Iran or even the world. [ABSTRACT FROM AUTHOR]

With growing interest in global environmental change, it is crucial to have a reliable model to accurately predict the suspended sediment load (SSL). This study investigates the efficiency and capability of two time-series data decomposition algorithms, namely empirical mode decomposition (EMD) and ensemble EMD (EEMD), to address the complexity and non-stationary behaviour of the monthly SSL time series data. These algorithms were coupled with three artificial intelligence models – gene expression programming (GEP), extreme learning machine (ELM), and extreme gradient boosting (XGBoost) – to predict SSL at two stations in Tajan Basin, northern Iran. The results indicate that EEMD, with coefficient of determination values higher than 0.9, performed better than EMD when coupled with XGBoost as the ensemble model. To verify the the predicted SSL data, Monte Carlo simulation was used. The results confirmed the lower uncertainty of the EEMD-XGBoost model in predicting SSL at a monthly scale. [ABSTRACT FROM AUTHOR]

Monitoring the water contaminants is of utmost importance in water resource management. Prediction of the total dissolved solid (TDS) is particularly essential for water quality management and planning in the areas exposed to a mixture of pollutants. TDS primarily includes inorganic minerals and organic matters, and various salts and increasing the concentration of TDS causes the esthetic problems. The reflection of the pollutant burden of the aquatic system can remarkably determined by TDS magnitudes. This study focuses on the prediction of TDS and several biochemical parameters such as Na, Ca, HCO3, and Mg in a river system. To overcome nonstationarity, randomness, and nonlinearity of the TDS data, a multi-step supervised machine learning evolutionary algorithm (MSMLEA) is proposed to improve the model's performance at two gaging stations, namely Rig-Cheshmeh and Soleyman-Tangeh, in the Tajan River, Iran. In addition, a hybrid model that recruits intrinsic time-scale decomposition (ITD) for frequency resolution of the input data as well as a multivariate adaptive regression spline (MARS) were adopted. A novel metaheuristic optimization algorithm, crow search algorithm (CSA), was also implemented to compute the optimal parameter values for the MARS model. To validate the proposed hybrid model, standalone MARS, empirical mode decomposition (EMD)-based models, and hybrid ITD-MARS as well as a MARS-CSA were considered as the benchmark models. Results suggest the ITD-MARS-CSA outperforms other models. [ABSTRACT FROM AUTHOR]

This research specifically addresses the prediction of dairy product demand (DPD). Since dairy products have a short consumption period, it is important to have accurate information about their future demand. The main contribution of this research is to provide an integrated framework based on statistical tests, time-series neural networks, and improved MLP, ANFIS, and SVR with novel meta-heuristic algorithms in order to obtain the best prediction of DPD in Iran. At first, a series of economic and social indicators that seemed to be effective in the demand for dairy products is identified. Then, the ineffective indices are eliminated by using the Pearson correlation coefficient, and statistically significant variables are determined. Since the regression relation is not able to predict this demand properly, the artificial intelligence tools including MLP, ANFIS, and SVR are implemented and improved with the help of novel meta-heuristic algorithms such as grey wolf optimization (GWO), invasive weed optimization (IWO), cultural algorithm (CA), and particle swarm optimization (PSO). The designed hybrid method is used to predict the DPD in Iran by using data from 2013 to 2017. The high accurate results confirm that the proposed hybrid methods have the ability to improve the prediction of the demand for various products. [ABSTRACT FROM AUTHOR]

The predictive capability of a new artificial intelligence method, random subspace (RS), for the prediction of suspended sediment load in rivers was compared with commonly used methods: random forest (RF) and two support vector machine (SVM) models using a radial basis function kernel (SVM-RBF) and a normalized polynomial kernel (SVM-NPK). Using river discharge, rainfall and river stage data from the Haraz River, Iran, the results revealed: (a) the RS model provided a superior predictive accuracy (NSE = 0.83) to SVM-RBF (NSE = 0.80), SVM-NPK (NSE = 0.78) and RF (NSE = 0.68), corresponding to very good, good, satisfactory and unsatisfactory accuracies in load prediction; (b) the RBF kernel outperformed the NPK kernel; (c) the predictive capability was most sensitive to gamma and epsilon in SVM models, maximum depth of a tree and the number of features in RF models, classifier type, number of trees and subspace size in RS models; and (d) suspended sediment loads were most closely correlated with river discharge (PCC = 0.76). Overall, the results show that RS models have great potential in data poor watersheds, such as that studied here, to produce strong predictions of suspended load based on monthly records of river discharge, rainfall depth and river stage alone. [ABSTRACT FROM AUTHOR]

A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) and Bagging] was introduced for landslide susceptibility mapping in a part of Kamyaran city in Kurdistan Province, Iran. A spatial database was generated which includes a total of 60 landslide locations and a set of conditioning factors tested by the Information Gain Ratio technique. Performance of these models was evaluated using the area under the ROC curve (AUROC) and statistical index-based methods. Results showed that the hybrid ensemble models could significantly improve the performance of the base classifier of BLR (AUROC = 0.930). However, RS model (AUROC = 0.975) had the highest performance in comparison to other landslide ensemble models, followed by Bagging (AUROC = 0.972), MB (AUROC = 0.970) and AB (AUROC = 0.957) models, respectively. [ABSTRACT FROM AUTHOR]

Infiltration plays a fundamental role in streamflow, groundwater recharge, subsurface flow, and surface and subsurface water quality and quantity. In this study, adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and random forest (RF) models were used to determine cumulative infiltration and infiltration rate in arid areas in Iran. The input data were sand, clay, silt, density of soil and soil moisture, while the output data were cumulative infiltration and infiltration rate, the latter measured using a double-ring infiltrometer at 16 locations. The results show that SVM with radial basis kernel function better estimated cumulative infiltration (RMSE = 0.2791 cm) compared to the other models. Also, SVM with M4 radial basis kernel function better estimated the infiltration rate (RMSE = 0.0633 cm/h) than the ANFIS and RF models. Thus, SVM was found to be the most suitable model for modelling infiltration in the study area. [ABSTRACT FROM AUTHOR]