Search

Due to excessive streamflow (SF), Peninsular Malaysia has historically experienced floods and droughts. Forecasting streamflow to mitigate municipal and environmental damage is therefore crucial. Streamflow prediction has been extensively demonstrated in the literature to estimate the continuous values of streamflow level. Prediction of continuous values of streamflow is not necessary in several applications and at the same time it is very challenging task because of uncertainty. A streamflow category prediction is more advantageous for addressing the uncertainty in numerical point forecasting, considering that its predictions are linked to a propensity to belong to the pre-defined classes. Here, we formulate streamflow prediction as a time series classification with discrete ranges of values, each representing a class to classify streamflow into five or ten, respectively, using machine learning approaches in various rivers in Malaysia. The findings reveal that several models, specifically LSTM, outperform others in predicting the following n-time steps of streamflow because LSTM is able to learn the mapping between streamflow time series of 2 or 3 days ahead more than support vector machine (SVM) and gradient boosting (GB). LSTM produces higher F1 score in various rivers (by 5% in Johor, 2% in Kelantan and Melaka and Selangor, 4% in Perlis) in 2 days ahead scenario. Furthermore, the ensemble stacking of the SVM and GB achieves high performance in terms of F1 score and quadratic weighted kappa. Ensemble stacking gives 3% higher F1 score in Perak river compared to SVM and gradient boosting. [ABSTRACT FROM AUTHOR]

Conventional machine learning models have been widely used for reservoir inflow and rainfall prediction. Nowadays, researchers focus on a new computing architecture in the area of AI, namely, deep learning for hydrological forecasting parameters. This review paper tends to broadcast more of the intriguing interest in reservoir inflow prediction utilizing deep learning and machine learning algorithms. The AI models utilized for different hydrology sectors, as well as the most prevalent machine learning techniques, will be explored in this thorough study, which divides AI techniques into two primary categories: deep learning and machine learning. In this study, we look at the long short-term memory deep learning method as well as three traditional machine learning algorithms: support vector machine, random forest, and boosted regression tree. Under each part, a summary of the findings is provided. For convenience of reference, some of the benefits and drawbacks discovered through literature reviews have been listed. Finally, future recommendations and overall conclusions based on research findings are given. This review focuses on papers from high-impact factor periodicals published over a 4 years period beginning in 2018 onwards. [ABSTRACT FROM AUTHOR]

Sediment transport is a normal phenomenon in rivers and streams, contributing significantly to ecosystem production and preservation by replenishing vital nutrients and preserving aquatic life's natural habitats. Thus, sediment transport prediction through modeling is crucial for predicting flood events, tracking coastal erosion, planning for water supplies, and managing irrigation. The predictability of process-driven models may encounter various restrictions throughout the validation process. Given that data-driven models work on the assumption that the underlying physical process is not requisite, this opens up the avenue for AI-based model as alternative modeling. However, AI-based models, such as ANN and SVM, face problems, such as long-term dependency, which require alternative dynamic procedures. Since their performance as universal function approximation depends on their compatibility with the nature of the problem itself, this study investigated several distinct AI-based models, such as long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM), in predicting sediment transport in the Johor river. The collected historical daily sediment transport data from January 1, 2008, to December 01, 2018, through autocorrelation function, were used as input for the model. The statistical results showed that, despite their ability (deep learning and machine learning) to provide sediment predictions based on historical input datasets, machine learning, such as ANN, might be more prone to overfitting or being trapped in a local optimum than deep learning, evidenced by the worse in all metrics score. With RMSE = 11.395, MAE = 18.094, and R2 = 0.914, LSTM outperformed other models in the comparison. [ABSTRACT FROM AUTHOR]

Earthquake is one of the natural disasters that have a big impact on society. Currently, there are many studies on earthquake detection. However, the vibrations that were detected by sensors were not only vibrations caused by the earthquake, but also other vibrations. Therefore, this study proposed an earthquake multi-classification detection with machine learning algorithms that can distinguish earthquake and non-earthquake, and vandalism vibration using acceleration seismic waves. In addition, velocity and displacement as integration products of acceleration have been considered additional features to improve the performances of machine learning algorithms. Several machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Artificial Neural Network (ANN) have been used to develop the best algorithm for earthquake multi-classification detection. The results of this study indicate that the ANN algorithm is the best algorithm to distinguish between earthquake and non-earthquake, and vandalism vibrations. Moreover, it's also more resistant to various input features. Furthermore, using velocity and displacement as additional features has been proven to increase the performance of every model. [ABSTRACT FROM AUTHOR]

The suspended sediment load (SSL) is one of the major hydrological processes affecting the sustainability of river planning and management. Moreover, sediments have a significant impact on dam operation and reservoir capacity. To this end, reliable and applicable models are required to compute and classify the SSL in rivers. The application of machine learning models has become common to solve complex problems such as SSL modeling. The present research investigated the ability of several models to classify the SSL data. This investigation aims to explore a new version of machine learning classifiers for SSL classification at Johor River, Malaysia. Extreme gradient boosting, random forest, support vector machine, multi-layer perceptron and k-nearest neighbors classifiers have been used to classify the SSL data. The sediment values are divided into multiple discrete ranges, where each range can be considered as one category or class. This study illustrates two different scenarios related to the number of categories, which are five and 10 categories, with two time scales, daily and weekly. The performance of the proposed models was evaluated by several statistical indicators. Overall, the proposed models achieved excellent classification of the SSL data under various scenarios. [ABSTRACT FROM AUTHOR]

The objective of the current study is to investigate the effectiveness of specifically the Support Vector Machine (SVM) and the k-Nearest Neighbors (kNN) models for sea level prediction. The SVM and kNN models are compared using the predicted data determined by the machine learning model's performance. Thirteen models were trained precisely and properly throughout the machine learning process. The results showed that SVM models provide good performance during the training process and attained relatively poor performance during testing process. On the other hand, the KNN model showed consistent performance for both training and testing process. Regarding the effectiveness of different kernels of the SVM algorithm, the Radial Basis Function (RBF) kernel is the most suitable, which provides the finest analysis for the sea level rise dataset and acceptable values for RSME, MAE, and R2. [ABSTRACT FROM AUTHOR]

Groundwater resources (GWR) play a crucial role in agricultural crop production, daily life, and economic progress. Therefore, accurate prediction of groundwater (GW) level will aid in the sustainable management of GWR. A comparative study was conducted to evaluate the performance of seven different ML models, such as random tree (RT), random forest (RF), decision stump, M5P, support vector machine (SVM), locally weighted linear regression (LWLR), and reduce error pruning tree (REP Tree) for GW level (GWL) prediction. The long-term prediction was conducted using historical GWL, mean temperature, rainfall, and relative humidity datasets for the period 1981–2017 obtained from two wells in the northwestern region of Bangladesh. The whole dataset was divided into training (1981–2008) and testing (2008–2017) datasets. The output of the seven proposed models was evaluated using the root mean square error (RMSE), mean absolute error (MAE), relative absolute error (RAE), root relative squared error (RRSE), correlation coefficient (CC), and Taylor diagram. The results revealed that the Bagging-RT and Bagging-RF models outperformed other ML models. The Bagging-RT models can effectively improve prediction precision as compared to other models with RMSE of 0.60 m, MAE of 0.45 m, RAE of 27.47%, RRSE of 30.79%, and CC of 0.96 for Rajshahi and RMSE of 0.26 m, MAE of 0.18 m, RAE of 19.87%, RRSE of 24.17%, and 0.97 for Rangpur during training, and RMSE of 0.60 m, MAE of 0.40 m, RAE of 24.25%, RRSE of 29.99%, and CC of 0.96 for Rajshahi and RMSE of 0.38 m, MAE of 0.24 m, RAE of 23.55%, RRSE of 31.77%, and CC of 0.95 for Rangpur during testing stages, respectively. Our study offers an effective and practical approach to the forecast of GWL that could help to formulate policies for sustainable GWR management. [ABSTRACT FROM AUTHOR]

Floods and droughts are environmental phenomena that occur in Peninsular Malaysia due to extreme values of streamflow (SF). Due to this, the study of SF prediction is highly significant for the purpose of municipal and environmental damage mitigation. In the present study, machine learning (ML) models based on the support vector machine (SVM), artificial neural network (ANN), and long short-term memory (LSTM), are tested and developed to predict SF for 11 different rivers throughout Peninsular Malaysia. SF data sets for the rivers were collected from the Malaysian Department of Irrigation and Drainage. The main objective of the present study is to propose a universal model that is most capable of predicting SFs for rivers within Peninsular Malaysia. Based on the findings, the ANN3 model which was developed using the ANN algorithm and input scenario 3 (inputs consisting of previous 3 days SF) is deduced as the best overall ML model for SF prediction as it outperformed all the other models in 4 out of 11 of the tested data sets; and obtained among the highest average RMs with a score of 3.27, hence indicating that the model is very adaptable and reliable in accurately predicting SF based on different data sets and river case studies. Therefore, the ANN3 model is proposed as a universal model for SF prediction within Peninsular Malaysia. [ABSTRACT FROM AUTHOR]

This paper focuses on the development of a robust accurate streamflow prediction model by balancing the abilities of exploitation and exploration to find the best parameters of a machine learning model. To do so, the simulated annealing (SA) algorithm is integrated with the mayfly optimization algorithm (MOA) as SAMOA to determine the optimal hyper-parameters of support vector regression (SVR) to overcome the exploration weakness of the MOA method. The proposed method is compared with the classical SVR and hybrid SVR-MOA. To examine the accuracy of the selected methods, monthly hydroclimatic data from Jhelum River Basin is used to predict the monthly streamflow on the basis of RMSE, MAE, NSE, and R2 indices. Test results show that the SVR-SAMOA outperformed the SVR-MOA and SVR models. SVR-SAMOA reduced the prediction errors of the SVR-MOA and SVR models by decreasing the RMSE and the MSE from 21.4% to 14.7% and from 21.7% to 15.1%, respectively, in the test stage. [ABSTRACT FROM AUTHOR]

High loads of suspended sediments in rivers are known to cause detrimental effects to potable water sources, river water quality, irrigation activities, and dam or reservoir operations. For this reason, the study of suspended sediment load (SSL) prediction is important for monitoring and damage mitigation purposes. The present study tests and develops machine learning (ML) models, based on the support vector machine (SVM), artificial neural network (ANN) and long short-term memory (LSTM) algorithms, to predict SSL based on 11 different river data sets comprising of streamflow (SF) and SSL data obtained from the Malaysian Department of Irrigation and Drainage. The main objective of the present study is to propose a single model that is capable of accurately predicting SSLs for any river data set within Peninsular Malaysia. The ANN3 model, based on the ANN algorithm and input scenario 3 (inputs consisting of current-day SF, previous-day SF, and previous-day SSL), is determined as the best model in the present study as it produced the best predictive performance for 5 out of 11 of the tested data sets and obtained the highest average RM with a score of 2.64 when compared to the other tested models, indicating that it has the highest reliability to produce relatively high-accuracy SSL predictions for different data sets. Therefore, the ANN3 model is proposed as a universal model for the prediction of SSL within Peninsular Malaysia. [ABSTRACT FROM AUTHOR]

Forecasting of reservoir inflow is one of the most vital concerns when it comes to managing water resources at reservoirs to mitigate natural hazards such as flooding. Machine learning (ML) models have become widely prevalent in capturing the complexity of reservoir inflow time-series data. However, the model structure's selection required several trails-and-error processes to identify the optimal architecture to capture the necessary information of various patterns of input–output mapping. In this study, the effectiveness of a deep learning (DL) approach in capturing various input–output patterns is examined and applied to reservoir inflow forecasting. The proposed DL approach has a distinct benefit over classical ML models as all the hidden layers are stacked afterward to train on a diverging set of topologies derived from the previous layer's output. Given the nonlinearity of day-to-day data about reservoir inflow, a deep learning algorithm centered on the long short-term memory (LSTM) and two standard machine learning algorithms, namely support vector machine (SVM) and artificial neural network (ANN), were deployed in this study for forecasting reservoir inflow on a daily basis. The gathered data pertained to historical daily inflow from 01/01/2018 to 31/12/2019. The area of study was Durian Tunggal Reservoir, Melaka, Peninsular Malaysia. The choice of the input set was made on the basis of the autocorrelation function. The formulated model was assessed on the basis of statistical indices, such as mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R2). The outcomes indicate that the LSTM model performed much better than SVM and ANN. Based on the comparison, LSTM outperformed other models with MAE = 0.088, RMSE = 0.27, and R2 = 0.91. This research demonstrates that the deep learning technique is an appropriate method for estimating the daily inflow of the Durian Tunggal Reservoir, unlike the standard machine learning models. [ABSTRACT FROM AUTHOR]

Earthquake is one of the devastating and frightening natural disasters that caused big casualties in a small duration. Earthquake caused lots of damage in just a few minutes and the casualties of the earthquake increase as the population increase which also contribute to higher amount of property and buildings. Therefore, by developing model capable of detecting the recurrence behaviour of earthquake helps in predicting earthquake as well as minimizing the casualties caused by the earthquake. In this report, a few of artificial intelligence algorithms such as support vector machine, boosted decision tree regression, random forest and multivariate adaptive regression spline will be used in the development of best model algorithm in earthquake prediction. Meteorological data are collected from several stations in Terengganu and processed for normalization and the data will be analysed using algorithms and its performance will be evaluated. Terengganu is situated on the east coast of Peninsular Malaysia and is bordered on the north-west and south-west by Kelantan and Pahang. Terengganu's east side is bordered by the South China Sea. Terengganu is located within the vicinity of the South China Sea, which is possible to be affected by the Marina Trench Earthquake. The subduction zone of Manila Trench is capable of producing a high magnitude of earthquake activity that can create a deadliest tsunami disaster. Therefore, Terengganu is studied for the investigation of artificial intelligence in earthquake prediction. The model algorithms are then analysed to measure its sensitivity and accuracy in prediction and consistency of the result. [ABSTRACT FROM AUTHOR]

The prediction of tropospheric ozone concentrations is vital due to ozone's passive impacts on atmosphere, people's health, flora and fauna. However, ozone prediction is a complex process and the wide range of traditional models is incapable to obtain an accurate prediction. "Artificial intelligence", "machine learning" and "ozone prediction model" search terms in the title, abstract or keywords are involved. Inclusion criteria include subject area (engineering, computer science), English language and being published from 2015. This criterion obtained 156 articles, which were categorized into 4 areas of interest based on the machine learning technique applied. Recently as a result of the rapid development in the technology and the increase in the number of measured data, artificial intelligence techniques have been intensively used in predicting ozone concentration as an alternative to the traditional models. Therefore, the main objective of this study is to investigate the most developed techniques that have been used in predicting ozone concentrations as well as theoretic approaches such as information set approaches, fuzzy set approach and probabilistic set approaches. It is clearly stated that the standalone algorithms such as decision tree (DT) and support vector machine (SVM) outperformed multilayer perceptron (MLP); however, the latter is massively implemented by many researchers in the prediction of ozone concentrations. This review paper investigated artificial intelligence techniques integrated with optimization approaches. It can be concluded that hybrid algorithms have significantly improved the prediction accuracy. However, the majority of the proposed hybrid models have limitations; thus, there is a need to develop better hybrid algorithm that is able to tackle all the drawbacks of the improved algorithms and capable to capture the ozone concentration changes with a high level of accuracy. [ABSTRACT FROM AUTHOR]

Reference evapotranspiration (ET0) plays a fundamental role in irrigated agriculture. The objective of this study is to simulate monthly ET0 at a meteorological station in India using a new method, an improved support vector machine (SVM) based on the cuckoo algorithm (CA), which is known as SVM-CA. Maximum temperature, minimum temperature, relative humidity, wind speed and sunshine hours were selected as inputs for the models used in the simulation. The results of the simulation using SVM-CA were compared with those from experimental models, genetic programming (GP), model tree (M5T) and the adaptive neuro-fuzzy inference system (ANFIS). The achieved results demonstrate that the proposed SVM-CA model is able to simulate ET0 more accurately than the GP, M5T and ANFIS models. Two major indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), indicated that the SVM-CA outperformed the other methods with respective reductions of 5–15% and 5–17% compared with the GP model, 12–21% and 10–22% compared with the M5T model, and 7–15% and 5–18% compared with the ANFIS model, respectively. Therefore, the proposed SVM-CA model has high potential for accurate simulation of monthly ET0 values compared with the other models. [ABSTRACT FROM AUTHOR]

Phosphate (PO 4) is a major component of most fertilizers, and when erosion and runoff occur, large amounts of it enter the water bodies, causing several problems such as eutrophication. Feitsui reservoir, the primary source of water supply to Taipei, reported half of the reservoir's pollutants from nonpoint-source pollution. The value of the PO 4 in the water body fluctuates in highly nonlinear and stochastic patterns. However, conventional modeling techniques are no longer sufficiently effective in predicting accurately such stochastic patterns in the concentrations of PO 4 in water. Therefore, this study proposes different machine learning algorithms: the artificial neural network (ANN), support vector machine (SVM), random forest (RF), and boosted trees (BT) to predict the concentration of PO 4. Monthly measured data between 1986 and 2014 were used to train and test the accuracy of these models. The performances of these models were examined using different statistical indices. Hyperparameters optimization such as cross-validation was performed to enhance the precision of the models. Five water quality parameters were used as input to the proposed models. Different input combinations were explored to optimize the precision. The findings revealed that ANN outperformed the other three models to capture the changes in the concentrations of PO 4 with high precision where RMSE is equal to 1.199, MAE is equal to 0.858, and R2 is equal to 0.979, MSE is equal to 1.439, and finally, CC is equal to 0.9909. The developed model could be used as a reliable means for managing eutrophication problems. [ABSTRACT FROM AUTHOR]

Water quality analysis is a crucial step in water resources management and needs to be addressed urgently to control any pollution that may adversely affect the ecosystem and to ensure the environmental standards are being met. Thus, this work is an attempt to develop an efficient model using support vector machine (SVM) to predict the water quality of Langat River Basin through the analysis of the data of six parameters of dual reservoirs that are located in the catchment. The proposed model could be considered as an effective tool for identifying the water quality status for the river catchment area. In addition, the major advantage of the proposed model is that it could be useful for ungauged catchments or those lacking enough numbers of monitoring stations for water quality parameters. These parameters, namely pH, Suspended Solids (SS), Dissolved Oxygen (DO), Ammonia Nitrogen (AN), Chemical Oxygen Demand (COD), and Biochemical Oxygen Demand (BOD) were provided by the Malaysian Department of Environment (DOE). The differences between dual scenarios 1 and 2 depend on the information from prior stations to forecast DO levels for succeeding sites (Scenario 2). This scheme has the capacity to simulate water-quality accurately, with small prediction errors. The resulting correlation coefficient has maximum values of 0.998 and 0.979 after the application of Scenario 1. The approach with Type 1 SVM regression along with 10-fold cross-validation methods worked to generate precise results. The MSE value was found to be between 0.004 and 0.681, with Scenario 1 showing a better outcome. [ABSTRACT FROM AUTHOR]

The support vector classifier (SVC) is one of the most powerful machine learning algorithms. This algorithm has been accepted as an effective method in three-dimensional geological modeling. Although the model selection has a great impact on the performance of SVC algorithm, most of mining studies have neglected it and used the grid search method. Therefore, in this study, a new approach is proposed for improving the selection of SVC models. This approach uses particle swarm optimization (PSO) to determine the important parameters of SCV such as penalty and kernel parameters. The proposed approach was applied in the modeling process of the Iju porphyry copper deposit to delineate alteration and mineralization zones. The optimal penalty and kernel parameters were found to be 27.2 and 2−4.75 for alteration zone, and 22.72 and 2−6.23 for mineralization zone, respectively. With 97.4% and 97.01% rates of accuracy for mineralization and alteration zones, the PSO results showed reasonable performance in classification. The proposed approach had better accuracy than grid search method. Therefore, because of its better performance, the geological models were developed using the PSO method to be used as a basis for future resource evaluation. • The particle swarm optimization (PSO) algorithm and grid search method were compared in parameter optimization. • Implicit geological modeling by a support vector classifier whose parameters were optimized using PSO. • Implicit geological model of alteration and mineralization domains are separately prepared. [ABSTRACT FROM AUTHOR]

• Precise mapping to the rainfall-runoff (RR) relationship is required. • Integrated data-driven models with nature-inspired optimizers provide promising accuracy in RR modeling. • Implementing HHO algorithm with LSSVM, ANN, and MLR to create alternative models to improve the performance accuracy. • LSSVM-HHO model improves the predictive precision of runoff compared with other models. Rainfall and runoff are considered the main components in the hydrological cycle. Developing an accurate model to capture the dynamic connection between rainfall and runoff remains a problematic task for engineers. Several studies have been carried out to develop models to accurately predict the changes in runoff from rainfall. However, these models have limitations in terms of accuracy and complexity when large numbers of parameters are needed. Therefore, recently, with the advancement of data-driven techniques, a vast number of hydrologists have adopted models to predict changes in runoff. However, data-driven models still encounter several limitations related to hyperparameter optimization and overfitting. Hence, there is a need to improve these models to overcome these limitations. In this study, data-driven techniques such as a Multi-Layer Perceptron (MLP) neural network and Least Squares Support Vector Machine (LSSVM) are integrated with an advanced nature-inspired optimizer, namely, Harris Hawks Optimization (HHO) to model the rainfall-runoff relationship. Five different scenarios will be examined based on the autocorrelation function (ACF), cross-correlation function (CCF) and partial autocorrelation function (PACF). Finally, for comprehensive analysis, the performance of the proposed model will then be compared with integrated data-driven techniques with particle swarm optimization (PSO). The results revealed that all the augmented models with HHO outperformed other integrated models with PSO in predicting the changes in runoff. In addition, a high level of accuracy in predicting runoff values was achieved when HHO was integrated with LSSVM. [ABSTRACT FROM AUTHOR]