Search

This paper for the first time improved a Robust Multi-Output machine learning regression model for seismic hazard zoning of Turkey, Iraq and Iran using constructed 3-D shear-wave velocity (Vs), seismic tomography dataset model for the crust and uppermost mantle beneath the study area. The focus of this paper's opportunity is to develop a scientific framework leveraging machine learning that will ultimately provide the rapid and more complete characterization of earthquake properties. This work can be targeted at improving the seismic hazard zones system ability to detect and associate seismic signals, or at estimating other seismic characteristics (crust acceleration and crust energy) while traditionally, methods cannot monitor the earthquakes system. This work has derived some physical equations for extraction of many variables as inputs for our developed machine learning model based on a reliable understanding of the tomography data to physical variables by preparing huge dataset from different physical conditions of crust. We have extracted the velocity values of the shear waves from the original NETCDF file, which contains the S velocity values for every one km of the depths of the crust for the study area from one km down to the uppermost mantle beneath the Middle East. For the first time, this study calculated new seismic hazard parameter called Peak Crust Acceleration (PCA) for seismic hazard analysis by considering the transmitted initial seismic energy through the Earth's crust layers from hypocenter. All machine learning algorithms in this study wrote in python language using anaconda platform the open-source Individual Edition (Distribution). [ABSTRACT FROM AUTHOR]

In this paper, an integrated workflow based on recent geoscience data is presented for assessing the reservoir characterization and structural interpretation of the Burgan formation, a highly productive formation in the Abadan plain, SW Iran. Utilizing newly acquired high-resolution SEM images, we evaluated the pore size, pore distribution, and pore aspect ratio of Burgan formation. The watershed segmentation algorithm is also capable of detecting throats and closed pores. The porosity fractions from SEM images are used for calibration of the porosity log at several well locations in order to perform petrophysical modeling. Due to the complexity of facies behavior in the study area, we utilized supervised Bayesian classifiers using P-wave velocity, density, and facies log data in order to incorporate spatial dependence into the model. The confusing matrix and machine learning metrics including Accuracy (97.01%), Precision (93.88%), F1 Score (94.16%), and False Positive Rate (2.52%), indicate that the classifier has been properly trained at well locations. A reasonable match is evident between the modeled petrophysical parameters and the true (core) porosity and water saturation at the location of the test well. Furthermore, we have demonstrated the validity of assumptions concerning the dominance of extensional structure in the Abadan plain by using interpreted seismic data. The presented workflow can be used to optimize drilling operations and reduce risks in similar geological settings in the studied formation. Highlights: • The vital pore properties have been evaluated using newly obtained SEM images. • Bayesian classification is a reliable classifier for complex facies modeling. • The dominant extensional structure can be observed in the Abadan plain. • The watershed segmentation algorithm can detect closed pores and throats. [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]

Machine learning approaches are increasingly being employed to forecast the key characteristics of strong ground motions, including the challenging classification of Pulse-Like (PL) ground motions. The PL ground motions are characterized by their impulsive nature and have the potential to cause significant damage to structures. The classification of PL ground motions continues to be a significant challenge due to the absence of consensus on their definition and categorization. This paper investigates the potential benefits of several Machine Learning Classifiers (MLCs) algorithms such as decision tree, random forest, logistic regression, naive Bayes, support vector machine, K-nearest neighbor, ensemble model, and artificial neural network models for predicting PL and Non-Pulse-Like (NPL) ground motions. In this regard, a dataset comprising 200 near-fault ground motions records compiled from active tectonic regions like Taiwan, Turkey, Iran, and Japan, was divided into 2 portions, with 75% used to train the model and the remaining 25% used for testing. Plots of performance metrics, confusion matrix, and receiver operating curve indicate that the ensemble classifier outperforms the other classifier with 86.2% accuracy and the lowest misclassification of PL and NPL ground motions. Additionally, the trained MLC has been compared with the existing ground motion classification models to further assess the accuracy of the different classifiers in the present study. [ABSTRACT FROM AUTHOR]

Many applications in agriculture as well as other related fields including natural resources, environment, health, and sustainability, depend on recent and reliable cropland maps. Cropland extent and intensity plays a critical input variable for the study of crop production and food security around the world. However, generating such variables manually is difficult, expensive, and time consuming. In this work, we discuss a cost effective, fast, and simple machine-learning-based approach to provide reliable cropland mapping model using satellite imagery. The study includes four test regions, namely Iran, Mozambique, Sri-Lanka, and Sudan, where Sentinel-2 satellite imagery were obtained with assigned NDVI scores. The solution presented in this paper discusses a complete pipeline including data collection, time series reconstruction, and cropland extent and crop intensity mapping using machine learning models. The approach proposed managed to achieve high accuracy results ranging between 0.92 and 0.98 across the four test regions at hand. [ABSTRACT FROM AUTHOR]

This paper employs machine learning algorithms to detect tax evasion and analyzes tax data. With the development of commercial businesses, traditional algorithms are not appropriate for solving the tax evasion detection problem. Hence, other algorithms with acceptable speed, precision, analysis, and data decisions must be used. In the case of assets and tax assessment, the integration of machine learning models with meta-heuristic algorithms increases accuracy due to optimal parameters. In this paper, intelligent machine learning algorithms are used to solve tax evasion detection. This research uses an improved particle swarm optimization (IPSO) algorithm to improve the multilayer perceptron neural network by finding the optimal weight and improving support vector machine (SVM) classifiers with optimal parameters. The IPSO-MLP and IPSO-SVM models using the IPSO algorithm are used as new models for tax evasion detection. Our proposed system applies the dataset collected from the general administration of tax affairs of West Azerbaijan province of Iran with 1500 samples for the tax evasion detection problem. The evaluations show that the IPSO-MLP model has a higher accuracy rate than the IPSO-SVM model and logistic regression. Moreover, the IPSO-MLP model has higher accuracy than SVM, Naive Bayes, k-nearest neighbor, C5.0 decision tree, and AdaBoost. The accuracy of IPSO-MLP and IPSO-SVM models is 93.68% and 92.24%, respectively. [ABSTRACT FROM AUTHOR]

This paper studies the application of two machine learning methods to model precipitable water vapor (PWV) using observations of 23 GPS stations from the local GPS network of north-west of Iran in 2011. In a first step, the zenith tropospheric delay (ZTD) and zenith hydrostatic delay (ZHD) is calculated with the Bernese GNSS software and Saastamoinen model as revised by Davis, respectively. Then, by subtracting the ZHD from the ZTD, the zenith wet delay (ZWD) is obtained at each GPS station, for all times. In a second step, ZWD is modeled by two different machine learning methods, based on the latitude, longitude, DOY, time, relative humidity, temperature and pressure. After training a Support Vector Machine (SVM) and an Artificial Neural Network (ANN), ZWD temporal and spatial variations are estimated. Using the formula by Bevis, the ZWD can be converted to PWV at any time and space, for each machine learning method. The accuracy of the two new models is evaluated using control stations, exterior and radiosonde station, whose observations were not used in the training step. Also, all the results of the SVM and ANN are compared with a voxel-based tomography (VBT) model. In the control and exterior stations, ZWD estimated by the SVM (ZWD SVM) and ANN (ZWD ANN) is compared with the ZWD obtained from the GPS (ZWD GPS). Also, in the control and exterior stations, precise point positioning (PPP) is used to evaluate the accuracy of the new models. In the radiosonde station, the PWV of the new models (PWV SVM , PWV ANN) is compared with the radiosonde PWV (PWV radiosonde) and voxel-based PWV (PWV VBT). The averaged relative error of the SVM, ANN and VBT models in the control stations is 10.50%, 12.71% and 12.91%, respectively. For SVM, ANN and VBT models, the averaged RMSE at the control stations is 1.87 (mm), 2.22 (mm) and 2.29 (mm), respectively. Analysis of the results of PWV estimated by the SVM, ANN and VBT, as well as the surface precipitation obtained from meteorological stations, indicate the high accuracy of the SVM in comparison with the ANN and VBT model. In the results shown in this paper, the SVM has the best ability to accurately estimate ZWD and PWV, using local GPS network observations. [ABSTRACT FROM AUTHOR]

Electricity distribution companies are in-charge-of supplying stable electric energy to urban customers over a wide geographical area. In these distribution networks, large number of Distribution-Transformers (DTs) are installed on towers or in electric-rooms with the ratings below 1000 kVA, which are the most important assets of distribution companies. Periodic maintenance and test services are not economically feasible for all in-operation transformers. Hence, estimating the remaining useful life and scheduling the maintenance times of DTs are of great technical and economic importance. An analytical approach is presented in this paper for predicting lifetime of DTs based on degree of polymerization. An appropriate Machine-Learning (ML) algorithm trained by measured data is selected for forecasting driven load according to the ambient temperature and humidity and day-hour schedules. The relation of Hot-Spot-Temperature in IEC60076∼7 is modified based on the measured data for accounting unbalanced-loading. Neutral-current is predicted using a trained ML-model. Another approach is proposed for determining times of oil filtering services aiming to minimize the maintenance cost and maximizing the remaining life. The proposed lifetime estimation method is validated by comparing its results with the damaged DT data of a sample network chosen as the case studies for this research, i.e., Bushehr province, Iran. [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]

Crash severity models play a crucial role in evaluating the influencing factors in the severity of traffic crashes. In this study, Extremely Randomised Tree (ERT) is used as a machine learning technique to analyse the severity of crashes. The crash data in the province of Khorasan Razavi, Iran, for a period of 5 years from 2013 to 2017, is used for crash severity model development. The dataset includes traffic-related variables, vehicle specifications, vehicle movement, land use characteristics, temporal characteristics, and environmental variables. In this paper, Feature Importance Analysis (FIA), Partial Dependence Plots (PDP), and Individual Conditional Expectation (ICE) plots are utilised to analyse and interpret the results. According to the results, the involvement of vulnerable road users such as motorcyclists and pedestrians alongside traffic-related variables are among the most significant variables in crash severity. Results show that the presence of motorcycles can increase the probability of injury crashes by around 30% and almost double the probability of fatal crashes. Analysing the interaction of PDPs shows that driving speeds above 60 km/h in residential areas raises the probability of injury crashes by about 10%. In addition, at speeds higher than 70 km/h, the presence of pedestrians approximately increases the probability of fatal crashes by 6%. [ABSTRACT FROM AUTHOR]

With the expansion of human activities, the volume of waste and hazardous waste produced has increased dramatically. Increasing the volume of waste has created challenges such as transportation hazards, cleanup, disposal, energy consumption, and most important environmental problems. The difficulty of unsafe waste control is one of the critical studies topics. Finding the optimal location of hazardous waste disposal is one of the issues that, if done properly, can significantly reduce the aforementioned challenges. The increasing volume of information, the complexity of multivariate decision criteria, have led to the lack of conventional methods for finding the optimal location. Machine learning methods have proven to be effective and superior in many areas. In this paper, a new method based on machine learning for finding the optimal location of hazardous waste disposal is presented. In the proposed method, after applying clustering in the separation of the desired areas, the gray wolf algorithm optimization is used to find the optimal location of waste disposal. In order to apply the gray wolf optimization algorithm, a multivariate target function is defined. Cluster centers as were chosen as location of waste disposal. Proposed method is performed on collected data from the study area in Iran, Tehran province. Proposed clustering method is evaluated and compared with some metaheuristics algorithm. The simulation results of the proposed method show cost reduction in finding the desired locations compared to similar researches. Also, Xi and Separation index was used for evaluation of the proposed clustering method to select the best location. The number of best locations using Xi and Separation index claim the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Prediction of geochemical concentration values is essential in mineral exploration as it plays a principal role in the economic section. In this paper, four regression machine learning (ML) algorithms, such as K neighbor regressor (KNN), support vector regressor (SVR), gradient boosting regressor (GBR), and random forest regressor (RFR), have been trained to build our proposed hybrid ML (HML) model. Three metric measurements, including the correlation coefficient, mean absolute error (MAE), and means squared error (MSE), have been selected for model prediction performance. The final prediction of Pb and Zn grades is achieved using the HML model as they outperformed other algorithms by inheriting the advantages of individual regression models. Although the introduced regression algorithms can solve problems as single, non-complex, and robust regression models, the hybrid techniques can be used for the ore grade estimation with better performance. The required data are gathered from in situ soil. The objective of the recent study is to use the ML model's prediction to classify Pb and Zn anomalies by concentration-area fractal modeling in the study area. Based on this fractal model results, there are five geochemical populations for both cases. These elements' main anomalous regions were correlated with mining activities and core drilling data. The results indicate that our method is promising for predicting the ore elemental distribution. [ABSTRACT FROM AUTHOR]

In this paper we propose a three-step approach to predict permeability. First, by using Electrofacies Analysis (EA), data are classified into several clusters. We take advantage of EA to overcome abrupt changes of permeability which its unpredictability prevents a machine to be learned. EA is also helpful for wells that suffer from core data. Second, fuzzy membership functions are applied on data points in each Electrofacies Log (EL). Third, Support Vector Regression (SVR) is employed to predict permeability using fuzzy clustered data for areas with core missing data. To perform this process, we applied the proposed technique on four well sets of a gas field located in South of Iran; three wells devoted to training and the fourth remained for testing operation. Seven ELs derived using Multi Regression Graph-Based Clustering (MRGC) method. MRGC is able to estimate more appropriate number of clusters without prior knowledge compared to other three algorithms for our case-study area. Then, fuzzy membership functions applied to data. Thereafter, SVR applied to both fuzzy and not-fuzzy ELs. Consequently, the predicted permeability log for both fuzzy and not-fuzzy inputs correlated to real permeability (core data obtained from plugs in laboratory) in the test well. Finally, predicted permeability for each face merged together to make an estimated permeability for the whole test well. The results show that predicted permeability obtained from application of SVR on fuzzy data (FSVR) has a notably better correlation with core data for both clusters individually and the whole data compared to SVR. [ABSTRACT FROM AUTHOR]

In wastewater treatment plants (WWTPs), the stochastic nature of influent wastewater and operational and weather conditions cause fluctuations in effluent quality. Data-driven models can forecast effluent quality a few hours ahead as a response to the influent characteristics, providing enough time to adjust system operations and avoid undesired consequences. However, existing data for training models are often incomplete and contain missing values. On the other hand, collecting additional data by installing new sensors is costly. The trade-off between using existing incomplete data and collecting costly new data results in three data challenges faced when developing data-driven WWTP effluent forecasters. These challenges are to determine important variables to be measured, the minimum number of required data instances, and the maximum percentage of tolerable missing values that do not impede the development of an accurate model. As these issues are not discussed in previous studies, in this research, for the first time, a comprehensive analysis is done to provide answers to these challenges. Another issue that arises in all data-driven modeling is how to select an appropriate forecasting model. This paper addresses these issues by first testing nine machine learning models on data collected from three wastewater treatment plants located in Iran, Australia, and Spain. The most accurate forecaster, Bayesian network, was then used to address the articulated challenges. Key variables in forecasting effluent characteristics were flow rate, total suspended solids, electrical conductivity, phosphorus compounds, wastewater temperature, and air temperature. A minimum of 250 samples was needed during the model training to achieve a great reduction in the forecasting error. Moreover, a steep increase in the error was observed should the portion of missing values exceed 10%. The results assist plant managers in estimating the necessary data collection effort to obtain an accurate forecaster, contributing to the quality of the effluent. [Display omitted] • Bayesian network is benchmarked against eight AI models to predict wastewater quality. • Bayesian networks can handle missing value in input data due to probabilistic nature. • Key variables in WWTP quality and quantity were specified. • Input data quality has a huge role in successful development of data-driven models. • The prediction error sharply increases when the portion of missing data exceeds 10%. [ABSTRACT FROM AUTHOR]

This paper focuses on a comprehensive solution for dry municipal solid waste (MSW) management with describes the scenario of the gasification process. For this purpose, the potential of implementing the MSW gasification process in Southeast Asia (Iran) with three agents of air, steam, and air-steam is investigated. In order to manage the MSW gasification process as accurately as possible in the study area, a thermodynamic, exergy, economic, environmental, carbon footprint, water footprint, ecological emergy, and risk assessment for the three mentioned gasification agents were carried out in the most populated cities of Iran. In the capital of Iran (Tehran) with the largest population and as a result of largest MSW production, the potential of the gasification process has been investigated at different times (10 consecutive years and 12 months of a year). Finally, by combining artificial neural networks and genetic programming, comprehensive relationships have been established to predict the thermodynamic conditions of gasification with an air-steam agent. The general results of the survey indicate that gasification with air agents has good potential for most regions. The use of the steam agent has created worse economic, environmental, and risk conditions than the other two agents. Investigating the potential of the gasification process in Tehran shows that this city has a good potential to implement this process compared to other cities in Iran, and the most suitable location for establishing the gasification process is the 4th region of this city. [Display omitted] • Potential of municipal solid waste (MSW) gasification for all Iranian cities. • Comparison of using air, steam, and air-steam agents for MSW gasification. • The payback period of air agent MSW gasification is lower than other agents. • Machine Learning used for prediction of the behavior of MSW gasification. [ABSTRACT FROM AUTHOR]

One of the most important features of a reliable power system is its capability to supply the demand continuously. This continuous supply has been maintained by the transient stability of the system against large disturbances. The study of this type of stability is examined through different indicators. One of the common indicators to evaluate the transient stability of the power system is the well-known Critical Clearing Time (CCT) index. Conventional methods for calculating CCT have presented good accuracy, however, their computational cost is very high which makes them not suitable for real-time applications and real large-scale networks. Considering their ability to feature extraction of big data, deep neural networks can be utilized as reliable tools to cover these deficiencies. In this regard, to cover the shortcomings of the conventional methods, this paper proposes a method based on deep Convolutional Neural Networks (CNN) to estimate the CCT index in real-time power system applications. Moreover, to analyze a realistic case, nonlinear limiters of the excitation systems which have a considerable effect on transient stability index are considered in this study. Thanks to the using of several deep layers and the comprehensive established database, the accuracy of proposed method is appropriately high. Numerical studies on IEEE standard networks as well as a real case in Iran Power Grid (IPG) represents the advantages of the proposed method. • A deep-learning-based convolutional neural network is designed to estimate CCT index of power system. • Nonlinear limiters of the excitation system are taken into account. • A real case study in Iran grid is considered for simulation. • As a result, the transient stability of system is accurately determined in on-line manner. [ABSTRACT FROM AUTHOR]

In this paper, the monthly long-term precipitation of the city of Ardabil from 1976 to 2020 is simulated by a modern hybrid learning machine. To this end, the Wavelet and Outlier Robust Extreme Learning Machine (ORELM) models are integrated to produce a hybrid model called "Wavelet-Outlier Robust Extreme Learning Machine (WORELM)". First, the observed data are normalized, and the best normalization coefficients for the study are acquired. About 70% of the observed data are employed to train the artificial intelligence models and the remaining (i.e., 30%) to test them. After that, the optimal mother wavelet and the best decomposition level of the wavelet model are computed. Then, the optimal number of the hidden layer neurons and the best activation function of the ORELM model is chosen by performing a trial and error procedure. In this study, the regularization parameter of the ORELM model is also optimized. Moreover, using the autocorrelation function (ACF), the most influencing lags of the time-series data are detected, and 14 WORELM models are developed. By analyzing the WORELM models, the best model and the effective lags of the time-series data are introduced. The outcomes of the hybrid WORELM model are finally compared with other machine learning (ML) algorithms to prove the superiority of the WORELM model. [ABSTRACT FROM AUTHOR]

Statins can help COVID-19 patients' treatment because of their involvement in angiotensin-converting enzyme-2. The main objective of this study is to evaluate the impact of statins on COVID-19 severity for people who have been taking statins before COVID-19 infection. The examined research patients include people that had taken three types of statins consisting of Atorvastatin, Simvastatin, and Rosuvastatin. The case study includes 561 patients admitted to the Razi Hospital in Ghaemshahr, Iran, during February and March 2020. The illness severity was encoded based on the respiratory rate, oxygen saturation, systolic pressure, and diastolic pressure in five categories: mild, medium, severe, critical, and death. Since 69.23% of participants were in mild severity condition, the results showed the positive effect of Simvastatin on COVID-19 severity for people that take Simvastatin before being infected by the COVID-19 virus. Also, systolic pressure for this case study is 137.31, which is higher than that of the total patients. Another result of this study is that Simvastatin takers have an average of 95.77 mmHg O2Sat; however, the O2Sat is 92.42, which is medium severity for evaluating the entire case study. In the rest of this paper, we used machine learning approaches to diagnose COVID-19 patients' severity based on clinical features. Results indicated that the decision tree method could predict patients' illness severity with 87.9% accuracy. Other methods, including the K -nearest neighbors (KNN) algorithm, support vector machine (SVM), Naïve Bayes classifier, and discriminant analysis, showed accuracy levels of 80%, 68.8%, 61.1%, and 85.1%, respectively. [ABSTRACT FROM AUTHOR]

As one of the most critical points of Iran, Lake Urmia has always been subjected to ecosystem changes due to severe water level drops. Many basins serve to feed the lake, e.g. the Shaharchay River basin, located west of the lake. In this paper, a new learning machine named "Weighted Regularization Extreme Learning Machine (WRELM)" is integrated with the Wavelet Transform (WT) (W-WRELM) to predict runoff-precipitation amounts of the Shaharchay River basin within an 18 year period from 2000 to 2017. Using the autocorrelation function, lags affecting runoff-precipitation time series are detected, then seven models are developed for both WRELM and W-ERELM by the mentioned lags. After that, all mother wavelets are testes and the best member of their family is identified. Also, the best models for the simulation of precipitation and runoff amounts are introduced through a sensitivity analysis. These models forecast target function values with acceptable exactness and high correlation. For example, the determination coefficient (R2) and Mean Absolute Error (MAE) for the best model of W-WRELM for the estimation of precipitation amounts are obtained to be 0.962 and 0.128, respectively. Moreover, the variance accounted for (VAF) and Scatter Index (SI) for the approximation of rainfall amounts are computed to 0.919 and 0.236, separately. Analyses showed that more than half of the precipitation amounts predicted by the W-WRELM 7 model have an error of more than 10%, but this value is about 64% for the predicted runoff. The lags (t-1), (t-2) and (t-12) are detected as the influencing lags in the simulation of the precipitation amounts of the Shaharchay River basin. Furthermore, the error and uncertainty analyses are conducted on the best models and it is concluded that the performance of W-WRELM in the prediction of precipitation amounts is underestimated, while its performance in the estimation of runoff values is overestimated. [ABSTRACT FROM AUTHOR]

Estimating the uniaxial compressive strength (UCS) of travertine rocks with an indirect modeling approach and machine learning algorithms is useful as models can reduce the cost and time required to obtain accurate measurements of UCS, which is important for the prediction of rock failure. This approach can also address the limitations encountered in preparing detailed measured samples using direct measurements. The current paper developed and compared the performance of three standalone tree-based machine learning models (random forest (RF), M5 model tree, and multivariate adaptive regression splines (MARS)) for the prediction of UCS in travertine rocks from the Azarshahr area of northwestern Iran. Additionally, an ensemble committee-based artificial neural network (ANN) model was developed to integrate the advantages of the three standalone models and obtain further accuracy in UCS prediction. To date, an ensemble approach for estimating UCS has not been explored. To construct and validate the models, a set of rock test data including p-wave velocity (Vp (Km/s)), Schmidt Hammer (Rn), porosity (n%), point load index (Is (MPa)), and UCS (MPa) were acquired from 93 travertine core samples. To develop the ensemble tree-based machine learning model, the input matrix representing Vp, Rn, n%, and Is data with the corresponding target variable (i.e., UCS) was incorporated with a ratio of 70:15:15 (train: validate: test). Results indicated that a standalone MARS model outperformed all other standalone tree-based models in predicting UCS. The ANN-committee model, however, obtained the best performance with an r-value of approximately 0.890, an RMSE of 3.980 MPa, an MAE of 3.225 MPa, a WI of 0.931, and an LMI of 0.537, demonstrating the improved accuracy of the ensemble model for the prediction of UCS relative to the standalone models. The results suggest that the proposed ensemble committee-based model is a useful approach for predicting the UCS of travertine rocks with a limited set of model-designed datasets. [ABSTRACT FROM AUTHOR]

In this paper, the capabilities of demotic unsupervised learning approaches were investigated to improve the procedure of geochemical anomaly identification. The separation of anomalous concentrations from the background is a crucial task in the mathematical analysis of geochemical data. The conventional methods rely on the statistical thresholds routinely; however, determining such boundary values fundamentally entails a normally distributed data and the involvement of expert knowledge. The unsupervised machine learning provides state-of-the-art facilities based on the information theory that leveraged to classify the geochemical data into the anomaly and background concentrations with specific characteristics. To examine the integrity of performance of geochemical data processing tools, the prevalent unsupervised learning methods of k-means, k-medoids, k-medians, expectation-maximization (EM) clustering, density-based spatial clustering of applications with noise (DBSCAN), and self-organizing maps (SOM), as well as traditional threshold-based techniques of the mean plus two standard deviations () and the concentration-number (C-N) fractal model were subjected to the separation of Cu anomalies from the background within 300 rock samples collected from Shadan porphyry copper deposit, northeast Iran. The efficiency of methods was quantitatively measured using criteria comprising student's t-test, signal to noise ratio, and the pooled coefficient of variation. The appraisal criteria have confirmed that most of the unsupervised techniques manage to isolate the geochemical anomalies from the background with a more significant contrast compared to the conventional methods of and C-N fractal model. The EM clustering has revealed the best performance among them so that it allocates the anomalies with the maximum resolution and distinguishes the weak anomalies from the high background. The anomaly Cu map obtained by the EM method has represented a significant spatial pattern that is properly consistent with the geological and mineralization evidences within the study area. The utilization of unsupervised learning methods substantially enjoys some advantages such as anomaly intensification, automaticity, being fast and non-parametric, and the capability to expand to the multivariate analysis. [ABSTRACT FROM AUTHOR]

Considering the nature of soils distribution, an important modeling issue in soil class mapping is imbalanced class observations. Imbalanced number of data in observed soil classes in an area can result in the underestimation or loss of minority classes and an overestimation of the majority classes in predictive modeling. The effect of this phenomenon is that an area of land with comparatively fewer soil profile observations could be unmapped in the digital maps. To address this problem, this paper investigated the usefulness of data pretreatment techniques called over- and under-sampling of data applied on three predictive models including decision trees (DT), random forest (RF), and multinomial logistic regression (MNLR). The study area is situated in the northwest of Iran with 452 profiles observations on a regular grid covering about 12,000 ha. This area has 8 USDA soil great groups with an imbalanced frequency distribution. Results showed that modeling using imbalanced distribution of class observation caused uncertain maps with minority classes being lost and relatively poor accuracies. After data treatment, with over- and under-sampling, all models showed significant improvement in maintaining the minority classes, in both calibration and validation evaluations. Balancing the classes led to a notable decrease in uncertainty of all 3 models by decreasing the confusion index and raising the probability of occurrence for the soil classes in the final maps. Comparing the 3 models, decision trees showed the largest calibration and validation accuracies with and without data treatment. RF has an issue of overestimation of some of the majority classes. Data resampling technique can be a useful solution for dealing with imbalanced class observations to produce more certain digital soil maps. • Imbalanced distribution of soil classes resulted in losing some classes in the map. • Imbalanced classes were treated by data resampling techniques before modeling. • Data resampling helped in maintaining minority classes and decreasing uncertainty. • Decision tree model performed well in response to balancing the classes. [ABSTRACT FROM AUTHOR]

In the digital soil mapping framework, machine learning (ML) algorithms are currently the most popular methods for the spatial prediction of soil properties. The fast developments of easy-to-use software implementations for a large panel of ML algorithms have encouraged comparison studies between algorithms, with the goal of ranking their performances and identifying the best ones among them. However, as no firm conclusions can be drawn about the best ML algorithm to be used in general, this suggests that combining a set of them could be a better approach. Numerous methods have been proposed to do so, most of them relying on a linear weighting of the individual algorithms. However, there are almost as many methods for linearly weighting ML algorithms as there are ML algorithms, thus leaving the problem unsolved. Moreover, these weighting methods are mostly used out-of-the-box, without paying a proper attention to the associated hypotheses. In this paper, we propose to address this issue by setting the problem in a more formal framework. Starting from classical hypotheses, it is shown how the benefit of averaging various ML algorithms can be estimated from their joint performances. Relying afterwards on the most commonly used linear weighting schemes, it is reminded that, as long as the performance metrics are based on mean square errors, the best averaging method is by essence the best linear (unbiased) predictor. Using a more general Bayesian framework, it is also shown that accounting for conditional biases when weighting ML algorithms is a key issue for obtaining improved predictions, and explicit formulas are proposed for that goal. Finally, these theoretical results are illustrated and discussed using a soil data set collected over an arid and semi-arid region in Iran where clay content, calcium carbonate equivalent, soil organic carbon and electrical conductivity were measured in topsoil samples. • Averaging results of several machine learning algorithms is beneficial. • Numerous averaging methods exist but are mostly used out-of-the-box. • The benefit of averaging depends on the correlation between prediction residuals. • Conditional biases are a key issue when averaging machine learning results. • A Bayesian approach provides the best results when conditional biases are present. [ABSTRACT FROM AUTHOR]

Incidences of disease, dieback, decline or mortality, some of which induced or enhanced by climate change, threaten the sustainability of forest stands in many ecosystems. Spatially explicit prediction of disease onset remains challenging, however, due to the involvement of several causative agents. In this paper, we developed a generic framework based on machine-learning algorithms and spatial analyses for landscape-level prediction of oak disease outbreaks caused by the charcoal fungus Biscogniauxia mediterranea in a mixed-oak forest of Mediterranean climate. For prediction, we used a set of fifteen causative factors as a cross-function of soil, site and stand-related predictors. A total of 80 sample plots, including 1134 affected trees, were surveyed and used for the modeling process at the 5600-ha landscape level of the southern Zagros, Iran, where the disease occurs in roughly 25% of forest lands. Ten machine learning algorithms were explored and the performance of each algorithm to predict oak disease outbreak was evaluated. The modeling framework used maximum entropy to remove the least influential variables and build the status-quo management scenario to which the results of the prediction models were compared. Results showed that the random forests algorithm (AUC = 0.96: Precision = 0.71: Accuracy = 0.90: F-Measure = 0.70) achieved significantly better results than the status-quo management (Precision = 0.13: Accuracy = 0.67: F-Measure = 0.12) and any other algorithm. Soil chemical properties (NPK, organic carbon and EC) and landform predictors (slope, distance to roads, and TWI) were major forecasters of oak disease outbreak identified by the random forest algorithm. Geostatistical analysis enabled the creation of a map that identified sites at higher risk of infestation, allowing epidemiologists and forest managers to find sites likely to be infested. Consequently, financial resources can be allocated and management practices such as sanitation felling treatments applied across large forest landscapes to minimize the risk of spread and severity to uninfested high-value trees on nearby or adjacent land zones that are in the early stage of epidemics. • Soil and landform attributes explain short-term presence of oak charcoal disease. • Random forest (RF) algorithms outperform nine other machine learning algorithms. • RF predicts 41% of Brant's oak at moderate disease intensity in southern Zagros. • RF algorithm predicts oak dieback, decline or mortality with 96% accuracy. • Machine-learning algorithms predict spatial charcoal disease intensity in Brant's oak. [ABSTRACT FROM AUTHOR]

Abstract: Natural language processing is a composition of several error‐prone and challenging tasks, including part of speech tagging, word sense disambiguation, named entity recognition, and compound verb detection. Studying intrasentence relations and roles is essential to improve the mentioned subtasks. Semi‐automatic schemes such as ontologies can be applied to clarify word's dependencies. This paper presents an ontology that is targeting to improve POS tagging, WSD, NER, and compound verb detection in Persian with extra properties that may ameliorate machine translation. The ontology is tested in combinations with several state‐of‐art algorithms on Dadegan corpus. The results show that coping semantic analysis with machine learning methods enhance relation detection and consequently precision of the mentioned subtasks, which is not widely addressed in Persian. Furthermore, the experimental results declare that the accuracy rate increases between 4.5 and 23% for different tasks. [ABSTRACT FROM AUTHOR]

• Reviewed more than 200 papers that used machine learning in groundwater quality modeling. • Neural networks are the most used machine learning model in groundwater quality modeling. • Nitrate is the most modeled contaminants. • Suggestions for further works are proposed. Groundwater is a crucial resource across agricultural, civil, and industrial sectors. The prediction of groundwater pollution due to various chemical components is vital for planning, policymaking, and management of groundwater resources. In the last two decades, the application of machine learning (ML) techniques for groundwater quality (GWQ) modeling has grown exponentially. This review assesses all supervised, semi-supervised, unsupervised, and ensemble ML models implemented to predict any groundwater quality parameter, making this the most extensive modern review on this topic. Neural networks are the most used ML model in GWQ modeling. Their usage has declined in recent years, giving rise to more accurate or advanced techniques such as deep learning or unsupervised algorithms. Iran and the United States lead the world in areas modeled, with a wealth of historical data available. Nitrate has been modeled most exhaustively, targeted by nearly half of all studies. Advancements in future work will be made with further implementation of deep learning and explainable artificial intelligence or other cutting-edge techniques, application of these techniques for sparsely studied variables, the modeling of new or unique study areas, and the implementation of ML techniques for groundwater quality management. [ABSTRACT FROM AUTHOR]

Due to land-use and hydrology changes, people are constantly exposed to floods. The adverse impact of floods is greater on vulnerable populations that disproportionately inhabit flood-prone areas. This paper reports a comprehensive study on flood vulnerability of flood prone areas in residential areas of the Tajan watershed, Iran in two periods before 2006 and after 2006. Flood prone area were determined by the random forest (RF) and K-nearest neighbor (KNN) machine learning methods. To reduce time and cost, the vulnerability was assessed only in areas with very high flood hazard using 4 main criteria (social, policy, economic, infrastructure), 40 items, and 210 questionnaires across 40 villages. Independent t -test, Kruskal-Wallis, and paired t -test were used for statistical analysis of questionnaire data. The results of machine learning models (MLMs) showed that the RF model with AUC = 0.92% is more accurate in determining flood prone areas. The results of paired t -test showed that the three criteria of social (mean P1 = 2.97 and P2 = 3.35), infrastructure (mean P1 = 2.88 and P2 = 3.25), and policy (mean P1 = 3.02 and P2 = 3.50) had significant changes in both periods. The Kruskal-Wallis test also revealed the mean of all four criteria in both periods and all sub-watersheds, except three sub-watersheds 10 (Khalkhil village), 19 (Tellarem and Kerasp villages), and 23 (Dinehsar and Jafarabad), had a significant difference. The results of the t -test also showed a decrease in vulnerability in the second period (before 2006) compared to the first period (after 2006), so the number of sub-watersheds in the very high vulnerability class was more in the first period than in the second period. A vulnerability map was developed using three factors of risk zone area, area of each sub-watershed, and population of each sub-watershed. • Using machine learning methods and field survey to assess vulnerability in flood hazard areas. • Investigating temporal and spatial variability in flood vulnerability of Tajan watershed. • Prioritizing flood-vulnerable areas using related criteria and indicators. [ABSTRACT FROM AUTHOR]

In this paper, land subsidence susceptibility was assessed for Shahryar County in Iran using the adaptive neuro-fuzzy inference system (ANFIS) machine learning algorithm. Another aim of the present paper was to assess if ensembles of ANFIS with two meta-heuristic algorithms (imperialist competitive algorithm (ICA) and gray wolf optimization (GWO)) would yield a better prediction performance. A remote sensing synthetic aperture radar (SAR) dataset from 2019 to 2020 and the persistent-scatterer SAR interferometry (PS-InSAR) technique were used to obtain a land subsidence inventory of the study area and use it for training and testing models. Resulting PS points were divided into two parts of 70% and 30% for training and testing the models, respectively. For susceptibility analysis, eleven conditioning factors were taken into account: the altitude, slope, aspect, plan curvature, profile curvature, topographic wetness index (TWI), distance to stream, distance to road, stream density, groundwater drawdown, and land use/land cover (LULC). A frequency ratio (FR) was applied to assess the correlation of factors to subsidence occurrence. The prediction power of the models and their generated land subsidence susceptibility maps (LSSMs) were validated using the root mean square error (RMSE) value and area under curve of receiver operating characteristic (AUC-ROC) analysis. The ROC results showed that ANFIS-ICA had the best accuracy (0.932) among the models (ANFIS-GWO (0.926), ANFIS (0.908)). The results of this work showed that optimizing ANFIS with meta-heuristics considerably improves LSSM accuracy although ANFIS alone had an acceptable result. [ABSTRACT FROM AUTHOR]

Lately, the kernel extreme learning machine (KELM) has gained considerable importance in the scientific area due to its great efficiency, easy implementation and fast training speed. In this paper, for the first time the potential of KELM to predict the daily horizontal global solar radiation from the maximum and minimum air temperatures ( T max and T min ) is appraised. The effectiveness of the proposed KELM method is evaluated against the grid search based support vector regression (SVR), as a robust methodology. Three KELM and SVR models are developed using different input attributes including: (1) T min and T max , (2) T min and T max −T min , and (3) T max and T max −T min . The achieved results reveal that the best predictions precision is achieved by models (3). The achieved results demonstrate that KELM offers favorable predictions and outperforms the SVR. For the KELM (3) model, the obtained statistical parameters of mean absolute bias error, root mean square error, relative root mean square error and correlation coefficient are 1.3445 MJ/m 2 , 2.0164 MJ/m 2 , 11.2464% and 0.9057%, respectively for the testing data. As further examination, a month-by-month evaluation is conducted and found that in six months from May to October the KELM (3) model provides further accuracy than overall accuracy. Based upon the relative root mean square error, the KELM (3) model shows excellent capability in the period of April to October while in the remaining months represents good performance. [ABSTRACT FROM AUTHOR]

• Developing a data-driven knowledge-based system for long term load forecasting. • Applying a machine learning-based decomposition method in the knowledge base. • Representing a reasoning method based on fuzzy logic to consider uncertain evidence. Reliable long-term hourly load forecasting is imperative for electricity utilities and planners' decision-making, especially in generation-transmission expansion planning. This paper develops a data-driven knowledge-based system for regional hourly load forecasting in the long-term horizon with contributions in both knowledge base and inference engine. In this regard, in the knowledge base, two types of driving factors are taken into account to determine the forecasting model: long-term trend-related features such as macro-economic factors and short-term factors such as temperature. The knowledge base is decomposed into three-step-related parts to deal with these groups' substantial differences in frequency. Firstly, the long-term trends are identified by the tendency variables. Then, the short-term variability is considered by temperature-related variables in addition to day type. Machine learning regression methods, support vector machines, random forest, and artificial neural networks are compared to determine the non-linear relationship of variables in these steps. The results of these steps are combined in the third step. Then, in the inference engine, a new reasoning method based on fuzzy logic is represented to forecast the regional long-term hourly load under uncertain evidence of temperature as an effective non-predictable feature in the long run. To evaluate the performance of the proposed system, a comparison against five systems is conducted. The results show the superiority of this system compared to the other systems for a publicly available dataset (ISO New England electricity market) as well as Iran's residential, commercial and agricultural electricity load. [ABSTRACT FROM AUTHOR]

Shear-wave velocity (V s) is a key petrophysical data for a wide spectrum of applications in the upstream oil industry. In many wells, however, the corresponding log cannot be acquired due to technical and/or cost-related issues. Appreciating the importance of this parameter, its relationship to other petrophysical logs has been extensively studied. For the most part, such studies focus on modes based on either rock physics, analytic equations, or artificial intelligence (AI). Inherent complexity of hydrocarbon reservoirs, especially carbonate ones, has made it difficult to build a comprehensive model of adequately high accuracy for various fields, keeping the research on novel models for such a purpose a still hot topic. This paper presents a high-accuracy high-generalizability model for predicting V s from logging data. The required logs were acquired along three wells penetrating three carbonate reservoirs in SW Iran. In a preprocessing step, a robust regression technique was applied to identify and omit outliers. Subsequently, the data at two wells were used for training the model, with the data at the third well used for validating the trained model. Feature selection was performed by NSGA-II and five parameters were selected (V p , Depth, RHOB, NPHI, and RT) as inputs to the model. For the first time, we employed the convolutional neural network (CNN) and multilayer extreme learning machine (MELM) in simple and hybrid forms with a few optimization algorithms, including particle swarm optimization (PSO), cuckoo optimization algorithm (COA), and genetic algorithm (GA) to build different models for predicting V s from logging data. For the sake of comparison, we further applied the least-squares support-vector machine (LSSVM) in simple and hybrid forms with COA, PSO, and GA as well as a couple of popular analytic methods. Results of the training showed the superiority of the CNN, as measured by RMSE. Nevertheless, the MELM-COA model provided for much shorter learning time although its RMSE was only marginally higher than the CNN. Results of the testing phase showed better generalizability and accuracy of the MELM-COA. The same outcome was confirmed in the validation phase. A comparison between the developed IAs and well-known empirical equations showed the higher performance of the IAs. Accordingly, the methodology proposed in this study is highly recommended for estimating the shear-wave velocity at other wells across similar fields provided the model can be trained on a larger set of training data. • Data were gathered from three wells drilled in the carbonate reservoirs in southwest of Iran. • Several artificial intelligence (AI) algorithms and empirical correlations were used to predict Shear wave velocity. • Hybrid algorithms are superior to empirical correlations in shear wave velocity estimation. • Multi-layer extreme learning machine has the highest precision among used AI algorithms. [ABSTRACT FROM AUTHOR]

Rate of penetration (ROP) is one of the most important parameters in reducing drilling expenditure. In this paper, a ROP management study has been conducted for a well in Southwest of Iran. As a part of this study, the best approach for ROP prediction was determined by comparing the performance of several methods and particle swarm optimization (PSO) algorithm was implemented for optimization of ROP. This paper highlights the effects of formation thickness and the magnitude of working data-set on the performance of different algorithms which are being used for ROP management studies, especially in horizontal and inclined wells. This topic has special importance, when the results show a massive difference in thin and thick formations for some ROP prediction methods. Comparing the results of different ROP prediction methods showed that hybrid Bingham model has the best performance in ROP prediction; only if a powerful mathematical tool like trust-region method is being used for the determination of its unknown coefficients. This superiority was not generalized in all individual formations and there were different results in the cases of thin and thick formations; so, application of the bag-of-algorithms strategy by using the most accurate method in each formation is suggested for the prediction of ROP. Performing this ROP management project resulted in the prediction of ROP with a total relative error of 13.59% and also 48.30% improvement in ROP. • The magnitude of working data-set affects the performance of ROP management algorithms. • This study expands the coverage of ROP prediction methods to horizontal and inclined wells. • Hybrid Bingham model in combination with trust-region method shows the best performance in ROP prediction. • Application of the bag-of-algorithms strategy is suggested for the prediction of ROP. [ABSTRACT FROM AUTHOR]

Shear wave velocity is considered as one of the most important rock physical parameters which can be measured by dipole sonic imager (DSI) tool. This parameter is applied to evaluate porosity and permeability, rock mechanical parameters, lithology, fracture assessment, etc. On the other hand, this data is not available in all wells and hence, an accurate and reliable estimation of this parameter with the least uncertainty is of great importance in reservoir characterization. In this study, regression, multi-layer perceptron artificial neural network (MLP-ANN), adaptive neuro-fuzzy inference system (ANFIS) and multi-gene genetic programming (MGGP) methods are utilized to estimate the shear wave velocity using well log data. Also, the reported empirical correlations in the literature are also investigated in the studied field. The input data include depth, effective porosity, V p , gamma ray logs (natural and spectral), neutron log, density log and caliper log from the Bangestan Group Formation in one of the fields in southwestern Iran. In this study, all the expressed methods are compared based on the best coefficient of determination (R2), root mean square error (RMSE), mean squared error (MSE), average absolute relative error (AARE), and average relative error (ARE). Among the used methods, MGGP was developed for using the useful features of this method including sensitivity analysis and correlation. Sensitivity analysis is performed on the input data using the MLP-ANN and MGGP method. Also, a correlation is suggested based on the MGGP method which is able to predict the shear wave velocity using the mentioned input parameters. The results show that the MLP-ANN method is more accurate, reliable and efficient compared to other methods studied in this paper. R2 for the train, validation, and test phase are 0.9973, 0.9901 and 0.9898, respectively. The results of sensitivity analysis imply that compressional wave velocity has the highest impact on the shear wave velocity. Finally, Young Dynamic Modulus and Poisson Dynamic Ratio are computed using both real and predicted shear wave velocities. The results indicate that these two parameters can be calculated with high accuracy using predicted shear wave velocity. • Five methods are implemented for predicting shear wave velocity (V s) using petrophysical logs. • ANN can predict the V s with high accuracy (R2 Test = 0.9898). • A sensitivity analysis performed on the significance of input variables on the V s using the results of MGGP. • A correlation is introduced for forecasting the V s. • Investigate the effects of V s prediction by ANN on the geomechanical modelling. [ABSTRACT FROM AUTHOR]

Forest environment classification in mountain regions based on single-sensor remote sensing approaches is hindered by forest complexity and topographic effects. Temperate broadleaf forests in western Asia such as the Hyrcanian forest in northern Iran have already suffered from intense anthropogenic activities. In those regions, forests mainly extend in rough terrain and comprise different stand structures, which are difficult to discriminate. This paper explores the joint analysis of Landsat7/ETM+, L-band SAR and their derived parameters and the effect of terrain corrections to overcome the challenges of discriminating forest stand age classes in mountain regions. We also verified the performances of three machine learning methods which have recently shown promising results using multisource data; support vector machines (SVM), neural networks (NN), random forest (RF) and one traditional classifier (i.e., maximum likelihood classification (MLC)) as a benchmark. The non-topographically corrected ETM+ data failed to differentiate among different forest stand age classes (average classification accuracy (OA) = 65%). This confirms the need to reduce relief effects prior data classification in mountain regions. SAR backscattering alone cannot properly differentiate among different forest stand age classes (OA = 62%). However, textures and PolSAR features are very efficient for the separation of forest classes (OA = 82%). The highest classification accuracy was achieved by the joint usage of SAR and ETM+ (OA = 86%). However, this shows a slight improvement compared to the ETM+ classification (OA = 84%). The machine learning classifiers proved t o be more robust and accurate compared to MLC. SVM and RF statistically produced better classification results than NN in the exploitation of the considered multi-source data. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a neural network model to predict the pyrite oxidation in the spoil of the Alborz Sharghi coal washing refuse pile, northeast Iran. Spoil depth, annual precipitation, effective diffusion coefficient and initial amount of pyrite in the spoil particles were used as inputs to the network. The output of the network was the amount of pyrite remained in the spoils at different depths. Feed-forward artificial neural network with back-propagation learning algorithm with 4-7-4-1 arrangement was found capable to predict the rate of pyrite oxidation. The network was used to predict the amount of pyrite remained at different depths of three trenches over the refuse pile. Simulated values obtained by the network were very close to the experimental results. The correlation coefficient (R) value was 0.99821 for training set, and in testing stage the R value was 0.99007, 0.9958 and 0.99898 for trench 1, trench 2 and trench 3 respectively which shows the model prediction was quite satisfactory. [Copyright &y& Elsevier]

Abstract: In this paper on mineral prospectivity mapping, a supervised classification method called Support Vector Machine (SVM) is used to explore porphyry-Cu deposits. Different data layers of geological, geophysical and geochemical themes are integrated to evaluate the Now Chun porphyry-Cu deposit, located in the Kerman province of Iran, and to prepare a prospectivity map for mineral exploration. The SVM method, a data-driven approach to pattern recognition, had a correct-classification rate of 52.38% for twenty-one boreholes divided into five classes. The results of the study indicated the capability of SVM as a supervised learning algorithm tool for the predictive mapping of mineral prospects. Multi-classification of the prospect for detailed study could increase the resolution of the prospectivity map and decrease the drilling risk. [Copyright &y& Elsevier]

• Introducing a new feature selection method based on entropy and mutual information to rank candidate inputs and eliminate redundant inputs according to their information value. • Using of wavelet transform to eliminate fluctuation behaviors of the electricity load and price time series decomposed the original signals. • Using of deep learning time series prediction based on LSTM to improve the forecast accuracy. Nowadays, a basic commodity for a human being to lead a standard lifestyle with human comfort irrespective of the nature of environmental conditions is electric power. The electricity load demand increases tremendously especially for a metropolitan city due to climatic conditions, population growth, local area development, industries expansion, air pollution, thermal device usage, etc. Hence, the accuracy of electricity load and its price forecasting is a deciding factor for the power distribution network to retain as an efficient, sustainable, and secure consumer-friendly network. On the other hand, based on the volatile, intermittent, and uncertain behavior of electricity load and price, an accurate, and robust forecast model should be designed. In this paper, a new hybrid forecast model for short-term electricity load and price prediction has been developed. The proposed method includes three modules: wavelet transform that is used to eliminate fluctuation behaviors of the electricity load and price time series, feature selection based on entropy and mutual information has been proposed to rank candidate inputs and eliminate redundant inputs according to their information value, and a new learning algorithm. The proposed learning method consists of a deep learning algorithm with LSTM networks which improves the accuracy of predictions. The performance of the proposed method has been validated successfully on load and price data collected from the Pennsylvania-New Jersey-Maryland (PJM) and Spain electricity markets. Also, for further test, the load data in Iran have been used. [ABSTRACT FROM AUTHOR]

In irrigation systems, salinity is a critical problem as it has undesirable impacts on crop health, agricultural throughput and farming management. Considering these, it is imperative to regularly monitor and develop measures to predict salinity of the soil to negate the salinization effects on agriculture. This paper constructs and evaluates the performance of the hybrid machine learning model of multilayer perceptron (MLP)-Grey Wolf Optimizer (MLP-GWO) for electrical conductivity (EC). MLP-GWO model is trained with soil sample data (i.e., parameters for organic matter, OM and soil constituents Ca+2, Mg+2, K+, Na+, Cl−, SO 4 −2, HCO 3 −) from Khuzestan province in Iran. Seven modelling scenarios representing different combinations of salinity parameters are investigated to establish a hybrid MLP-GWO model that aims to reduce the error rate of the resulting forecasts of EC. To ascertain conclusive results, the MLP-GWO model is cross-validated with its classical counterpart without the add-in (i.e., GWO) optimizer, and the model error metrics are evaluated by coefficients of determination (R2), root mean squared error (RMSE) and relative root mean square error (RRMSE) in independent test data. For all tested predictive models, the performance of the MLP-GWO hybrid model is superior to a classical model, evidenced by larger R2 (~0.552–0.711 relative to ~0.430–0.711) and a lower RMSE and RRSE (~1.293–3.537 vs. 1.616–4.421 and ~3.736–9.899 vs. 4.613–12.133). The proposed GWO as an optimizer leads to a plausible improvement in an MLP model due to the most optimal weights attained in the neuronal layer that facilitates a robust feature extraction process to predict EC. As conclusion, the obtained results proved the effectiveness of the hybrid MLP-GWI model for predicting soil properties, which has potential implications in precision agriculture where salinity needs to be modeled for crop management practices. • Prediction of soil electrical conductivity through a novel hybrid machine learning model • The effectiveness and generalization ability of the proposed model for different soil properties are reported. • Prediction accuracy for soil electrical conductivity is substantially improved. [ABSTRACT FROM AUTHOR]

S-wave velocity provides important information for the purpose of seismic reservoir characterization. However, it is not usually acquired in all wells due to the high cost and technical difficulties. Hence, different methods are developed for S-wave velocity prediction from other conventional petrophysical logs, generally using rock physics methods or artificial intelligence algorithms. Both of these methods have their own challenges for predicting S-wave velocity for complex reservoirs, which affects their prediction accuracy and efficiency accordingly. This paper proposes a combination of rock physics and machine learning methods on a carbonate reservoir to predict S-wave velocity. We used the Xu and Payne model and improved the estimation of the S-wave velocity by modifying the Gassmann's fluid substitution model and deriving a simplified form of it with a so-called C -factor exponent. Firstly, an inversion-based strategy is used to calculate this C -factor in a reference well as the training input data. Then, exponential Gaussian process regression is chosen to estimate the C -factor from the measured reservoir properties. The predicted C -factor, furthermore, is used to invert for a pore model, which was also validated with the computed tomography scanning analysis results. Our results confirm that this pore model, along with the computed C -factor, gives a better estimation for S-wave velocity in a blind well where the errors associated with the routine approaches are reduced significantly. Image 1 • We used a combination of rock physics, and machine learning to estimate V S. • A simplified Gassmann equation is derived with a defined C -factor. • We used the GPR technique to predict the C -factor from reservoir properties. • The pore volume fractions are defined and adjusted for both P- & S-wave velocities. • Our method improved V S prediction compared to the routine Xu-Payne model. [ABSTRACT FROM AUTHOR]

This paper examines some data mining techniques for lightning prediction. If we indicate by one the lightning event occurrence and by zero the non-occurrence of the event, then we will have a binary classification problem. In some cases, the dataset of lightning event is class imbalance. Thus, in the current research, the method of undersampling will be employed to generate several balanced datasets. Two binary classification algorithms, including neural networks and decision tree, were examined for lightning prediction. Furthermore, their performance was evaluated and compared. The proposed method was applied for some selected regions in Iran. Based on the evaluation results, decision tree outperforms feed-forward neural networks with one hidden layer for all datasets. • Lightning prediction considered as a binary classification problem. • Lightning dataset in this study is an imbalance dataset. • Under-bagging algorithm was applied for classification. [ABSTRACT FROM AUTHOR]

Energy has a strategic role in the economic and social development of countries. In the last few decades, energy demand has been increasing exponentially across the world, and predicting energy demand has become one of the main concerns in many countries. The residential and commercial sectors constitute about 34.7% of global energy consumption. Anticipating energy demand in these sectors will help governments to supply energy sources and to develop their sustainable energy plans such as using renewable and non-renewable energy potentials for the development of a secure and environmentally friendly energy system. Modeling energy consumption in the residential and commercial sectors enables identification of the influential economic, social, and technological factors, resulting in a secure level of energy supply. In this paper, we forecast residential and commercial energy demands in Iran using three different machine learning methods, including multiple linear regression, logarithmic multiple linear regression methods, and nonlinear autoregressive with exogenous input artificial neural networks. These models are developed based on several factors, including the share of renewable energy sources in final energy consumption, gross domestic production, population, natural gas price, and the electricity price. According to the results of the three machine learning methods applied in our study, by 2040, Iranian residential and commercial energy consumption will be 76.97, 96.42 and 128.09 Mtoe, respectively. Results show that Iran must develop and implement new policies to increase the share of renewable energy supply in final energy consumption. [ABSTRACT FROM AUTHOR]

• Agriculture and land management need up to date and high-resolution soil maps. • Conventional soil mapping began in 1953 in Iran, but not reliable for large areas. • Digital soil mapping approaches are in early stages in Iran. • Most Iranian soils have not been mapped at an appropriate scale. • Iranian soil scientists have paid great attention to digital soil mapping recently. Demand for accurate soil information is increasing for various applications. This paper investigates the history of soil survey in Iran, particularly more recent developments in the use of digital soil mapping (DSM) approaches rather than conventional soil mapping (CSM) methods. A 2000–2019 literature search of articles on DSM of areas of Iran in international journals found 40 studies. These showed an increase in frequency over time, and most were completed in the arid and semi-arid regions of central Iran. Artificial Neural Networks (ANN), Random Forests (RF), and Multinomial Logistic Regression (MnLR) were the most commonly applied models for predicting soil classes and properties and ANN performed best in most comparative studies. Given the scale of inquiry of most studies (local or regional), quantitative environmental variables such as terrain attributes and remote sensing data were frequently used whereas qualitative variables such as geomorphology, geology, land use, and legacy soil maps were rarely used. The literature review of CSM showed that this method is incapable of defining the spatial distribution of soils and also provides a lower accuracy than DSM method. This review has identified research gaps that need filling. In Iran, coherent national scale DSM with consistent methodology is needed to update legacy soil maps, and to apply DSM in forestlands, hillslopes, deserts, and mountainous regions which have largely been ignored in recent DSM studies. This review should also be useful for producing more local and regional digital soil maps more rapidly as it helps show which covariates and mathematical methods have been best suited to this scale of DSM in Iran. [ABSTRACT FROM AUTHOR]

Mapping flood-prone areas is a key activity in flood disaster management. In this paper, we propose a new flood susceptibility mapping technique. We employ new ensemble models based on bagging as a meta-classifier and K-Nearest Neighbor (KNN) coarse, cosine, cubic, and weighted base classifiers to spatially forecast flooding in the Haraz watershed in northern Iran. We identified flood-prone areas using data from Sentinel-1 sensor. We then selected 10 conditioning factors to spatially predict floods and assess their predictive power using the Relief Attribute Evaluation (RFAE) method. Model validation was performed using two statistical error indices and the area under the curve (AUC). Our results show that the Bagging–Cubic–KNN ensemble model outperformed other ensemble models. It decreased the overfitting and variance problems in the training dataset and enhanced the prediction accuracy of the Cubic–KNN model (AUC=0.660). We therefore recommend that the Bagging–Cubic–KNN model be more widely applied for the sustainable management of flood-prone areas. [ABSTRACT FROM AUTHOR]