Search

Rapid growth in industrialization and urbanization have resulted in high concentration of air pollutants in the environment and thus causing severe air pollution. Excessive emission of particulate matter to ambient air has negatively impacted the health and well-being of human society. Therefore, accurate forecasting of air pollutant concentration is crucial to mitigate the associated health risk. This study aims to predict the hourly PM2.5 concentration for an urban area in Malaysia using a hybrid deep learning model. Ensemble empirical mode decomposition (EEMD) was employed to decompose the original sequence data of particulate matter into several subseries. Long short-term memory (LSTM) was used to individually forecast the decomposed subseries considering the influence of air pollutant parameters for 1-h ahead forecasting. Then, the outputs of each forecast were aggregated to obtain the final forecasting of PM2.5 concentration. This study utilized two air quality datasets from two monitoring stations to validate the performance of proposed hybrid EEMD-LSTM model based on various data distributions. The spatial and temporal correlation for the proposed dataset were analysed to determine the significant input parameters for the forecasting model. The LSTM architecture consists of two LSTM layers and the data decomposition method is added in the data pre-processing stage to improve the forecasting accuracy. Finally, a comparison analysis was conducted to compare the performance of the proposed model with other deep learning models. The results illustrated that EEMD-LSTM yielded the highest accuracy results among other deep learning models, and the hybrid forecasting model was proved to have superior performance as compared to individual models., (© 2022. The Author(s).)

Evaporation is the primary aspect causing water loss in the hydrological cycle; therefore, water loss must be precisely measured. Evaporation is an intricate nonlinear process occurring as a result of several climatic aspects. The purpose of this research is to assess the feasibility of using Random Forest (RF) and two deep learning techniques, namely convolutional neural network (CNN), and deep neural network (DNN) to accurately estimate monthly pan evaporation rates. Month-based weather data gathered from four Malaysian weather stations during the 2000-2019 timeframe was used to train and evaluate the models. Several input attributes (predictor variables) were investigated to select the most suitable variables for machine learning models. Every approach was tested with several models, each with a different set of model aspects and input parameter combinations. The formulated ML approaches were benchmarked against two commonly used empirical methods: Stephens & Stewart and Thornthwaite. Model outcomes were assessed using standard statistical measures to determine their effectiveness in predicting evaporation. The results indicated that the three ML models developed in the study performed better than empirical models and could significantly improve the precision of monthly Ep estimates even with the identical input sets. The performance assessment metrics also show that the formulated CNN approach was acceptable for modelling monthly water loss due to evaporation with a higher degree of accuracy than other ML frameworks explored in this study. In addition, the CNN framework outperformed other AI techniques evaluated for the same areas using identical data inputs. The investigation's findings in relation to the various performance criteria show that the proposed CNN model is capable of capturing the highly non-linearity of evaporation and could be regarded as an effective tool to predict evaporation., (© 2022. The Author(s).)

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., (© 2022. The Author(s).)

Rapid progress of industrial development, urbanization and traffic has caused air quality reduction that negatively affects human health and environmental sustainability, especially among developed countries. Numerous studies on the development of air quality forecasting model using machine learning have been conducted to control air pollution. As such, there are significant numbers of reviews on the application of machine learning in air quality forecasting. Shallow architectures of machine learning exhibit several limitations and yield lower forecasting accuracy than deep learning architecture. Deep learning is a new technology in computational intelligence; thus, its application in air quality forecasting is still limited. This study aims to investigate the deep learning applications in time series air quality forecasting. Owing to this, literature search is conducted thoroughly from all scientific databases to avoid unnecessary clutter. This study summarizes and discusses different types of deep learning algorithms applied in air quality forecasting, including the theoretical backgrounds, hyperparameters, applications and limitations. Hybrid deep learning with data decomposition, optimization algorithm and spatiotemporal models are also presented to highlight those techniques' effectiveness in tackling the drawbacks of individual deep learning models. It is clearly stated that hybrid deep learning was able to forecast future air quality with higher accuracy than individual models. At the end of the study, some possible research directions are suggested for future model development. The main objective of this review study is to provide a comprehensive literature summary of deep learning applications in time series air quality forecasting that may benefit interested researchers for subsequent research., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

As a result of global climate change, sustainable water supply management is becoming increasingly difficult. Dams and reservoirs are key tools for controlling and managing water resources; they have benefited human cultures in a variety of ways, including enhanced human health, increased food production, water supply for domestic and industrial use, economic growth, irrigation, hydro-power generation, and flood control. This study aims to compare the application of deep learning and conventional machine learning algorithms for predicting daily reservoir inflow. Long short-term memory (LSTM) has been applied as a deep learning algorithm and boosted regression tree (BRT) has been implemented as a machine learning algorithm. Five statistical indices have been selected to evaluate the performance of the proposed models. The selected statistical measurements are mean absolute error (MAE), root mean square error (RMSE), correlation coefficient (R), coefficient of determination (R2), mean square error (MSE), Nash Sutcliffe Model Efficiency Coefficient (NSE), and the RMSE-observations standard deviation ratio (RSR). The findings showed that LSTM outperformed BRT with a significant difference in terms of accuracy. [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]

For decision-making in farming, the operation of dams and irrigation systems, as well as other fields of water resource management and hydrology, evaporation, as a key activity throughout the universal hydrological processes, entails efficient techniques for measuring its variation. The main challenge in creating accurate and dependable predictive models is the evaporation procedure's non-stationarity, nonlinearity, and stochastic characteristics. This work examines, for the first time, a transformer-based deep learning architecture for evaporation prediction in four different Malaysian regions. The effectiveness of the proposed deep learning (DL) model, signified as TNN, is evaluated against two competitive reference DL models, namely Convolutional Neural Network and Long Short-Term Memory, and with regards to various statistical indices using the monthly-scale dataset collected from four Malaysian meteorological stations in the 2000–2019 period. Using a variety of input variable combinations, the impact of every meteorological data on the Ep forecast is also examined. The performance assessment metrics demonstrate that compared to the other benchmark frameworks examined in this work, the developed TNN technique was more precise in modelling monthly water loss owing to evaporation. In terms of predictive effectiveness, the proposed TNN model, enhanced with the self-attention mechanism, outperforms the benchmark models, demonstrating its potential use in the forecasting of evaporation. Relating to application, the predictive model created for Ep projection offers a precise estimate of water loss due to evaporation and can thus be used in irrigation management, agriculture planning based on irrigation, and the decrease in fiscal and economic losses in farming and related industries where consistent supervision and estimation of water are considered necessary for viable living and economy. [ABSTRACT FROM AUTHOR]

The massive environmental noise interference and insufficient effective sample degradation data of the intelligent fault diagnosis performance methods pose an extremely concerning issue. Realising the challenge of developing a facile and straightforward model that resolves these problems, this study proposed the One-Dimensional Convolutional Neural Network (1D-CNN) based on frequency-domain signal processing. The Fast Fourier Transform (FFT) analysis is initially utilised to transform the signals from the time domain to the frequency domain; the data was represented using a phasor notation, which separates magnitude and phase and then fed to the 1D-CNN. Subsequently, the model is trained with White Gaussian Noise (WGN) to improve its robustness and resilience to noise. Based on the findings, the proposed model successfully achieved 100% classification accuracy from clean signals and simultaneously achieved considerable robustness to noise and exceptional domain adaptation ability. The diagnosis accuracy retained up to 97.37%, which was higher than the accuracy of the CNN without training under noisy conditions at only 43.75%. Furthermore, the model achieved an accuracy of up to 98.1% under different working conditions, which was superior to other reported models. In addition, the proposed model outperformed the state-of-art methods as the Signal-to-Noise Ratio (SNR) was lowered to −10 dB achieving 97.37% accuracy. In short, the proposed 1D-CNN model is a promising effective rolling bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

Predicting the compressive strength of concrete is a complicated process due to the heterogeneous mixture of concrete and high variable materials. Researchers have predicted the compressive strength of concrete for various mixes using machine learning and deep learning models. In this research, compressive strength of high-performance concrete with high volume ground granulated blast-furnace slag replacement is predicted using boosting machine learning (BML) algorithms, namely, Light Gradient Boosting Machine, CatBoost Regressor, Gradient Boosting Regressor (GBR), Adaboost Regressor, and Extreme Gradient Boosting. In these studies, the BML model's performance is evaluated based on prediction accuracy and prediction error rates, i.e., R2, MSE, RMSE, MAE, RMSLE, and MAPE. Additionally, the BML models were further optimised with Random Search algorithms and compared to BML models with default hyperparameters. Comparing all 5 BML models, the GBR model shows the highest prediction accuracy with R2 of 0.96 and lowest model error with MAE and RMSE of 2.73 and 3.40, respectively for test dataset. In conclusion, the GBR model are the best performing BML for predicting the compressive strength of concrete with the highest prediction accuracy, and lowest modelling error. [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]

Rapid progress of industrial development, urbanization and traffic has caused air quality reduction that negatively affects human health and environmental sustainability, especially among developed countries. Numerous studies on the development of air quality forecasting model using machine learning have been conducted to control air pollution. As such, there are significant numbers of reviews on the application of machine learning in air quality forecasting. Shallow architectures of machine learning exhibit several limitations and yield lower forecasting accuracy than deep learning architecture. Deep learning is a new technology in computational intelligence; thus, its application in air quality forecasting is still limited. This study aims to investigate the deep learning applications in time series air quality forecasting. Owing to this, literature search is conducted thoroughly from all scientific databases to avoid unnecessary clutter. This study summarizes and discusses different types of deep learning algorithms applied in air quality forecasting, including the theoretical backgrounds, hyperparameters, applications and limitations. Hybrid deep learning with data decomposition, optimization algorithm and spatiotemporal models are also presented to highlight those techniques' effectiveness in tackling the drawbacks of individual deep learning models. It is clearly stated that hybrid deep learning was able to forecast future air quality with higher accuracy than individual models. At the end of the study, some possible research directions are suggested for future model development. The main objective of this review study is to provide a comprehensive literature summary of deep learning applications in time series air quality forecasting that may benefit interested researchers for subsequent research. [ABSTRACT FROM AUTHOR]

To accurately predict tropospheric ozone concentration(O3), it is needed to investigate the variety of artificial intelligence techniques' performance, such as machine learning, deep learning and hybrid models. This research aims to effectively predict the hourly ozone trend via fewer input variables. This ozone prediction attempt is performed on diversity data of air pollutants (NO2, NOx, CO, SO2) and meteorological parameters (wind-speed and humidity). The historical datasets are collected from 3 sites in Malaysia. The study's methodology progressed in two paths: standalone and hybrid models where hourly-averaged datasets are applied based on 5-time horizon analysis scenario, with different inputs' combinations. For evaluation, all models are tested throughout 5-performance indicator and illustrated on Modified Taylor diagram. Sensitivity analysis of input variables is quantified. Additionally, uncertainty analysis is conducted to assess their confidence level associated with Willmott Index. Based on R2, results indicated that XGBoost has higher accuracy compared to MLP and SVR; meanwhile, LSTM and CNN outweighs XGBoost. In terms of robustness and accuracy, the proposed hybrid model possesses superlative performance compared to all above-mentioned techniques. The proposed model achieved exceptional results as the highest R2, the highest 95% confidence degree, and narrower confidence interval width, are 93.48%, 98.16%, and 0.0014195, respectively. [ABSTRACT FROM AUTHOR]

This study proposes two techniques: Deep Learning (DL) and Ensemble Deep Learning (EDL) to predict groundwater level (GWL) for five wells in Malaysia. Two scenarios were proposed, scenario-1 (S1): GWL from 4 wells was used as inputs to predict the GWL in the fifth well and scenario-2 (S2): time series with lag time up to 20 days for all five wells. The results from S1 prove that the ensemble EDL generally performs superior to the DL in the estimation of GWL of each station using data of remaining four wells except the Paya Indah Wetland in which the DL method provide better estimates compared to EDL. Regarding S2, the EDL also exhibits superior performance in predicting daily GWL in all five stations compared to the DL model. Implementing EDL decreased the RMSE, NAE and RRMSE by 11.6%, 27.3% and 22.3% and increased the R, Spearman rho and Kendall tau by 0.4%, 1.1% and 3.5%, respectively. Moreover, EDL for S2 shows a high level of precision within less time lag, ranging between 2 and 4 compared to DL. Therefore, the EDL model has the potential in managing the sustainability of groundwater in 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]

Sustainable management of water supplies faces a comprehensive challenge due to global climate change. Improving forecasts of streamflow based on erratic precipitation is a significant activity nowadays. In recent years, the techniques of data-driven have been widely used in the hydrological parameter's prediction especially streamflow. In the current research, a deep learning model namely Long Short-Term Memory (LSTM), and two conventional machine learning models namely, Random Forest (RF), and Tree Boost (TB) were used to predict the streamflow of the Kowmung river at Cedar Ford in Australia. Different scenarios proposed to determine the optimal combination of input predictor variables, and the input predictor variables were selected based on the auto-correlation function (ACF). Model output was evaluated using indices of the root mean square error (RMSE), and the Nash and Sutcliffe coefficient (NSE). The findings showed that the LSTM model outperformed RF and TB in predicting the streamflow with RMSE and NSE equal to 102.411, and 0.911 respectively. for the LSTM model. The proposed model could adopt by hydrologists to solve the problems associated with forecasting daily streamflow with high precision. This study may not be generalized because of the geographical condition and the nature of the data for each location. [ABSTRACT FROM AUTHOR]

The synergy between deep learning and meta-heuristic algorithms presents a promising avenue for tackling the complexities of energy-related modeling and forecasting tasks. While deep learning excels in capturing intricate patterns in data, it may falter in achieving optimality due to the nonlinear nature of energy data. Conversely, meta-heuristic algorithms offer optimization capabilities but suffer from computational burdens, especially with high-dimensional data. This paper provides a comprehensive review spanning 2018 to 2023, examining the integration of meta-heuristic algorithms within deep learning frameworks for energy applications. We analyze state-of-the-art techniques, innovations, and recent advancements, identifying open research challenges. Additionally, we propose a novel framework that seamlessly merges meta-heuristic algorithms into deep learning paradigms, aiming to enhance performance and efficiency in addressing energy-related problems. The contributions of the paper include: 1. Overview of recent advancements in MHs, DL, and integration. 2. Coverage of trends from 2018 to 2023. 3. Introduction of Alpha metric for performance evaluation. 4. Innovative framework harmonizing MHs with DL for energy problems. • Overview of recent advancements in Meta-Heuristics, Deep Learning in energy applications. • Covers 2018-2023 trends, providing insights into recent innovations in energy technologies. • Introduces Alpha metric for evaluating energy tech adoption and performance globally. • Proposes a framework integrating Meta-Heuristics and Deep Learning for energy solutions. [ABSTRACT FROM AUTHOR]

• Importance of predicting Water Quality Index (WQI) for assessing water bodies' health and safety. • Development of hybrid model (CNN-CRNN-M5T) combining CNN, Clockwork RNN, and M5 Tree for WQI prediction. • Enhancement of M5T model's data analysis capability for intricate patterns in water quality parameters. • Utilization of GLM-ANOVA to determine significant input variables for WQI prediction. • CNN-CRNN-M5T model's superiority in reducing MAE and increasing efficiency for spatial and temporal WQI predictions in Malaysia. Predicting a water quality index (WQI) is important because it serves as an important metric for assessing the overall health and safety of water bodies. Our paper develops a new hybrid model for predicting the WQI. The study uses a combination of a convolutional neural network (CNN), clockwork recurrent neural network (Clockwork RNN), and M5 Tree (CNN-CRNN-M5T) to predict a WQI. The M5T model lacks advanced operators for extracting meaningful data from water quality parameters, so the new model enhances its ability to analyze intricate patterns. The general linear model analysis of variance (GLM-ANOVA) is an improved version of the ANOVA. Our study uses the GLM-ANOVA to determine significant inputs. As all input variables had p < 0.050, they were defined as significant variables. Results showed that NH-NL and PH had the highest and lowest impact, respectively. Our study used the CNN-CRNN-M5T, CNN-CRNN, CRNN-M5T, CNN-M5T, CRNN, CNN, and M5T models to predict the WQI of a large basin in Malaysia. The CNN-CRNN decreased testing mean absolute error (MAE) of the CRNN, CNN, and M5T models by 2.1 %, 12 %, and 15 %, respectively. The CNN-CRNN-M5T model increased Nash–Sutcliffe efficiency coefficient of the other models by 4–20 % and 2.1–19 %, respectively. The CNN-CRNN-M5T model was a reliable tool for spatial and temporal predictions of WQI. [ABSTRACT FROM AUTHOR]

Accurate air pollution forecasting may provide valuable information for urban planning to maintain environmental sustainability and reduce mortality risk due to health problems. The city with higher industrial activities, traffic congestion, population density, and energy consumption is most likely to produce higher pollution than the other cities. Therefore, this study uses hybrid deep learning models to forecast air pollution based on the concentration of particulate matter with diameter size of less than 2.5 μm (PM 2.5) for two air quality monitoring stations in Kuala Lumpur, Malaysia. The proposed models predict the hourly air pollutant concentration based on 4-h historical input based on six air pollutant data, meteorology parameters, and PM 2.5 concentration data from the neighboring air quality monitoring stations. Long short-term memory based on metaheuristic algorithms, namely particle swarm optimization and sparrow search algorithm (PSO-LSTM and SSA-LSTM), are first developed and applied to determine the significance input combination to the changes of PM 2.5 concentration at respective target stations. Then, the input configuration that gives the best forecasting accuracy was selected for subsequent experiments using enhanced approaches based on ensemble empirical mode decomposition (EEMD-PSO-LSTM and EEMD-SSA-LSTM). Subsequently, this study also analyzed the contributions of the neighboring PM 2.5 dataset to the fluctuation of PM 2.5 concentration at target stations. It is found that EEMD-SSA-LSTM model of M5 improves other models in Batu Muda and Cheras by 2.65% and 20.00% for RMSE and 9.31% and 25.30% for MAE, respectively. The results indicate that the proposed model yields the highest forecasting accuracy compared to the other models, and additional information on neighboring PM 2.5 significantly improves the forecasting accuracy at both target stations. Besides that, comparing the performance of the two optimization approaches, SSA provides better performance compared to PSO in optimizing LSTM hyperparameters to forecast PM 2.5 concentration. • LSTM architecture is implemented to forecast PM 2.5 concentration. • Two optimization algorithms are proposed to find optimal hyperparameters for LSTM. • The efficiency of PSO and SSA are compared. • Forecasting of PM 2.5 integrating the surrounding datasets is emphasized. [ABSTRACT FROM AUTHOR]

Rolling bearing fault detection is critical for improving production efficiency and lowering accident rates in complicated mechanical systems, as well as huge monitoring data, posing significant challenges to present fault diagnostic technology. Deep Learning is now an extraordinarily popular research topic in the field and a promising approach for detecting intelligent bearing faults. This paper aims to give a comprehensive overview of Deep Learning (DL) based on bearing fault diagnosis. The most widely used DL algorithms for detecting bearing faults include Convolutional Neural Network, Recurrent neural network, Autoencoder, and Generative Adversarial Network. It discusses a variety of transfer learning architectures and relevant theories while summarises, classifies, and explains several publications on the subject. The research area's applications and problems are also addressed. [ABSTRACT FROM AUTHOR]

• A critical review based on 142 articles on the web of science. • The performances of various models are evaluated. • The modeling best practices are discussed. • Several potential research opportunities are recommended. Groundwater, the world's most abundant source of freshwater, is rapidly depleting in many regions due to a variety of factors. Accurate forecasting of groundwater level (GWL) is essential for effective management of this vital resource, but it remains a complex and challenging task. In recent years, there has been a notable increase in the use of machine learning (ML) techniques to model GWL, with many studies reporting exceptional results. In this paper, we present a comprehensive review of 142 relevant articles indexed by the Web of Science from 2017 to 2023, focusing on key ML models, including artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), support vector regression (SVR), evolutionary computing (EC), deep learning (DL), ensemble learning (EN), and hybrid-modeling (HM). We also discussed key modeling concepts such as dataset size, data splitting, input variable selection, forecasting time-step, performance metrics (PM), study zones, and aquifers, highlighting best practices for optimal GWL forecasting with ML. This review provides valuable insights and recommendations for researchers and water management agencies working in the field of groundwater management and hydrology. [Display omitted] [ABSTRACT FROM AUTHOR]