Search

Scouring around bridge piers is a critical concern, as the risk of bridge failures poses significant economic and safety threats to the public. Traditional models often struggle to accurately estimate the equilibrium scour depth (deq) at bridge piers due to the complexity of scour processes and their reliance on simple regression methods. This study combines two metaheuristic optimization techniques—Siberian tiger optimization (STO) and brown-bear optimization algorithms (BOA)—with artificial neural networks (ANNs) to enhance deq prediction accuracy for both round- and sharp-nosed piers using both field and laboratory data. The findings indicate that BOA and STO effectively optimize ANN hyperparameters, resulting in improved prediction accuracy. Furthermore, both BOA–ANN and STO–ANN outperformed empirical equations and other machine learning techniques. An explicit equation was also derived from the BOA–ANN model. The influence of independent variables on deq was further examined using SHAP, revealing that pier width has the greatest impact on deq estimates.

Accurate runoff forecasting is crucial for effective water resource management, yet existing models often face challenges due to the complexity of hydrological systems. This study addresses these challenges by introducing a novel bio-inspired metaheuristic algorithm, Artificial Rabbits Optimization (ARO), integrated with various machine learning (ML) models for runoff forecasting in the Carson and Chehalis River basins. The ARO-ML models are rigorously evaluated, demonstrating their superior ability to enhance forecasting accuracy compared to widely used ML techniques, including gradient boosting (GB), multi-layer perceptron (MLP), and K-nearest neighbor regression (KNN). In the Carson River, the GB model achieves the highest forecasting accuracy, which is significantly improved by ARO, resulting in a 24.8 % reduction in root mean square error (RMSE). The MLP model also benefits notably from ARO, with RMSE improvements of 4.8 % and a substantial 48.9 % reduction in mean absolute error (MAE). The ARO-optimized KNN model shows exceptional performance, surpassing the baseline KNN during testing. In the Chehalis River Basin, ARO integration leads to substantial improvements in both GB and MLP models across various performance metrics during training and testing. Crucially, the results indicate that in both river basins, rainfall in preceding days has the most significant influence on streamflow forecasts, followed by air temperature. This study advances hydrological forecasting by validating the efficacy of ARO-ML models, offering a robust framework for enhanced predictive accuracy and providing deeper insights into the key drivers of streamflow in diverse hydrological contexts.

The potential of advanced tree-based models and optimized deep learning algorithms to predict fluvial bedload transport was explored, identifying the most flexible and accurate algorithm, and the optimum set of readily available and reliable inputs. Using 926 datasets for 20 rivers, the performance of three groups of models was tested: (1) standalone tree-based models Alternating Model Tree (AMT) and Dual Perturb and Combine Tree (DPCT); (2) ensemble tree-based models Iterative Absolute Error Regression (IAER), ensembled with AMT and DPCT; and (3) optimized deep learning models Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) ensembled with Grey Wolf Optimizer. Comparison of the predictive performance of the models with that of commonly used empirical equations and sensitivity analysis of the driving variables revealed that: (i) the coarse grain-size percentile D90 was the most effective variable in bedload transport prediction (where Dx is the xth percentile of the bed surface grain size distribution), followed by D84, D50, flow discharge, D16, and channel slope and width; (ii) all tree-based models and optimized deep learning algorithms displayed ‘very good’ or ‘good’ performance, outperforming empirical equations; and (iii) all algorithms performed best when all input parameters were used. Thus, a range of different input variable combinations must be considered in the optimization of these models. Overall, ensemble algorithms provided more accurate predictions of bedload transport than their standalone counterpart. In particular, the ensemble tree-based model IAER-AMT performed most strongly, displaying great potential to produce robust predictions of bedload transport in coarse-grained rivers based on a few readily available flow and channel variables.

Abstract Electrical conductivity (EC) is widely recognized as one of the most essential water quality metrics for predicting salinity and mineralization. In the current research, the EC of two Australian rivers (Albert River and Barratta Creek) was forecasted for up to 10 days using a novel deep learning algorithm (Convolutional Neural Network combined with Long Short-Term Memory Model, CNN-LSTM). The Boruta-XGBoost feature selection method was used to determine the significant inputs (time series lagged data) to the model. To compare the performance of Boruta-XGB-CNN-LSTM models, three machine learning approaches—multi-layer perceptron neural network (MLP), K-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) were used. Different statistical metrics, such as correlation coefficient (R), root mean square error (RMSE), and mean absolute percentage error, were used to assess the models' performance. From 10 years of data in both rivers, 7 years (2012–2018) were used as a training set, and 3 years (2019–2021) were used for testing the models. Application of the Boruta-XGB-CNN-LSTM model in forecasting one day ahead of EC showed that in both stations, Boruta-XGB-CNN-LSTM can forecast the EC parameter better than other machine learning models for the test dataset (R = 0.9429, RMSE = 45.6896, MAPE = 5.9749 for Albert River, and R = 0.9215, RMSE = 43.8315, MAPE = 7.6029 for Barratta Creek). Considering the better performance of the Boruta-XGB-CNN-LSTM model in both rivers, this model was used to forecast 3–10 days ahead of EC. The results showed that the Boruta-XGB-CNN-LSTM model is very capable of forecasting the EC for the next 10 days. The results showed that by increasing the forecasting horizon from 3 to 10 days, the performance of the Boruta-XGB-CNN-LSTM model slightly decreased. The results of this study show that the Boruta-XGB-CNN-LSTM model can be used as a good soft computing method for accurately predicting how the EC will change in rivers.

Accurate prediction of daily river flow (Qt) remains a challenging yet essential task in hydrological modeling, particularly crucial for flood mitigation and water resource management. This study introduces an advanced M5 Prime (M5P) predictive model designed to estimate Qt as well as one- and two-day-ahead river flow forecasts (i.e. Qt+1 and Qt+2). The predictive performance of M5P ensembles incorporating Bootstrap Aggregation (BA), Disjoint Aggregating (DA), Additive Regression (AR), Vote (V), Iterative classifier optimizer (ICO), Random Subspace (RS), and Rotation Forest (ROF) were comprehensively evaluated. The proposed models were applied to a case study data in Tuolumne County, US, using a dataset comprising measured precipitation (Pt), evaporation (Et), and Qt. A wide range of input scenarios were explored for predicting Qt, Qt+1, and Qt+2. Results indicate that Pt and Qt significantly influence prediction accuracy. Notably, relying solely on the most correlated variable (e.g., Qt-1) does not guarantee robust prediction of Qt. However, extending the forecast horizon mitigates the influence of low-correlation input variables on model accuracy. Performance metrics indicate that the DA-M5P model achieves superior results, with Nash-Sutcliff Efficiency of 0.916 and root mean square error of 23 m3/s, followed by ROF-M5P, BA-M5P, AR-M5P, AR-M5P, RS-M5P, V-M5P, ICO-M5P, and the standalone M5P model. The ensemble M5P modeling framework enhanced the predictive capability of the stand-alone M5P algorithm by 1.2 %–22.6 %, underscoring its efficacy and potential for advancing hydrological forecasting.

Agricultural productivity is highly correlated with climatic variations, including drought events. This study is aimed at performing a comprehensive assessment of agricultural drought conditions in the Köppen–Geiger climate zones in Bangladesh, based on the temperature condition index (TCI), vegetation condition index (VCI), and vegetation health index (VHI). The zones are classified as follows: temperate dry winter with a hot summer zone, tropical savannah zone, and tropical monsoon zone. The range of VHI is optimized based on its correlation with TCI and VCI. The correlation among the stratified drought indices is also examined to quantify and measure the strength and direction of the linear relationships between them. Moreover, Mann–Kendall test is conducted to assess the statistical trends in the spatiotemporal propagation of droughts across different climate zones. The balanced correlation approach for VHI reveals that vegetation health is governed by the temperature conditions. Certain variations in the drought intensity, frequency, and duration are observed across climatic zones in earlier years while the recent years are noted with less droughts. Normal or no drought conditions are noticed mostly in the tropical monsoon zone through VCI and VHI. The correlations among the drought classes indicate that VHI is more strongly correlated with TCI than with VCI, while NDVI exhibits stronger correlations with VCI than with either VHI or TCI. The Mann-Kendall test revealed that VCI has significant downward trends in drought categories and an upward trend in normal conditions, whereas VHI and TCI displayed inconsistency in statistical trends. By extensively exploring the agricultural drought conditions within specific climate zones, this study offers valuable insights for agronomists and stakeholders involved in climate resilience planning and agricultural development in Bangladesh.

In this study, two deep learning approaches, bidirectional long short-term memory (BiLSTM) and long short-term memory (LSTM), were used along with adaptive boosting and general regression neural network to forecast multi-step-ahead pan evaporation in two arid climate stations in Iran (Ahvaz and Yazd). Lagged time series of meteorological data and pan evaporation data were input to the machine learning models. Two feature selection methods, i.e., the Boruta extra tree and XGBoost, were used to select significant inputs to reduce the number of inputs and model complexity. Different statistical metrics were used to investigate the model performance. The results demonstrated that Boruta-extra-tree-based models were more accurate than XGBoost-based models. Compared with the machine learning techniques, the combination of Boruta extra tree and BiLSTM enabled more accurate one-day-ahead forecasting of pan evaporation for both sites (Root Mean Square Error (RMSE) = 1.6857, for the Ahvaz station, and RMSE = 1.3996 for the Yazd station). The proposed model was used to forecast up to 30 days ahead of pan evaporation in both stations. The results showed that the Boruta-BiLSTM model could accurately forecast the pan evaporation for up to 30 days in both stations.

Accurate predictions of sea surface temperature (SST) are crucial due to the significant impact of SST on the global ocean-atmospheric system and its potential to trigger extreme weather events. Many existing machine-learning-based SST predictions adapt the traditional iterative point-wise prediction mechanism, whose predicting horizons and accuracy are limited owing to the high sensitivity to cumulative errors during iterative predictions. Therefore, this paper proposes a novel granulation-based long short-term memory (LSTM)-random forest (RF) combination model that can fully capture the feature dependencies involved in the fluctuation of SST sequences, reduce the cumulative error in the iteration process, and extend the prediction horizons, which includes two sub-models (adaptive granulation model and hybrid prediction model). They can restack the one-dimensional SST time-series into multidimensional feature variables, and achieve a strong forecasting ability. The analysis shows that the proposed model can achieve more accurate prediction-hours in nearly all prediction ranges from 1 to 125 h. The average prediction error of the proposed model in 25–125 h is 0.07 K, similar to that (0.067 K) in the first 24 h, which exhibits a high generalization performance and robustness and isthus a promising platform for the medium- and long-term forecasting of hourly SSTs.

Rapid urbanization and increased human activity have negatively impacted the microclimate of cities, leading to unfavorable conditions for human thermal comfort, particularly in outdoor spaces. Thermal comfort can be improved through various means, such as adjusting the height of urban buildings, the aspect ratio of road widths, and the placement of street trees. This study employed the ENVI-met software V5.5.1 to simulate the microclimate based on aspect ratio (H/W = 1.5) and street tree spacing (6 m) similar to actual conditions with different aspect ratios (H/W = 0.5, 1.0, and 2.0) and street tree spacing (2 m) in Seoul, Republic of Korea. Thermal comfort was assessed through a comprehensive predicted mean vote (PMV) evaluation, considering the gender (male and female) and age (8, 35, and 80 years) of residents in the target area, to determine the optimal urban canyon scenario. The results of the study indicated that the height of the building and the percentage of trees had a significant impact on the temperature and PMV results. When comparing PMV results, women have higher thermal vulnerability than men, and based on age, older adults have higher thermal vulnerability. The aspect ratio of 1.5 and tree spacing of 2 m resulted in the lowest temperature of 35.91 °C at 12:00 p.m. at 0° wind direction and 36.09 °C at 90° wind direction, lower than the actual input value of 36.9 °C. The PMV values were also under the same conditions, with an average PMV by gender of 3.87 at 0° and 4.21 at 90° and an average PMV by age of 3.86 at 0° and 4.19 at 90°. This finding is significant because it can inform the development of planned cities that prioritize urban thermal comfort during summer. This can be achieved through the strategic design of urban canyons and incorporation of street trees in both new and existing cities.

Accurate predictions are crucial for addressing the challenges posed by climate change. Given South Korea’s location within the East Asian summer monsoon domain, characterized by high spatiotemporal variability, enhancing prediction accuracy for regions experiencing heavy rainfall during the summer monsoon is essential. This study aims to derive temporal weighting functions using hybrid surface rainfall radar-observation data as the target, with input from two forecast datasets: the McGill Algorithm for Precipitation Nowcasting by Lagrangian Extrapolation (MAPLE) and the KLAPS Forecast System. The results indicated that the variability in the optimized parameters closely mirrored the variability in the rainfall events, demonstrating a consistent pattern. Comparison with previous blending results, which employed event-type-based weighting functions, showed significant deviation in the average AUC (0.076) and the least deviation (0.029). The optimized temporal weighting function effectively mitigated the limitations associated with varying forecast lead times in individual datasets, with RMSE values of 0.884 for the 1 h lead time of KLFS and 2.295 for the 4–6 h lead time of MAPLE. This blending methodology, incorporating temporal weighting functions, considers the temporal patterns in various forecast datasets, markedly reducing computational cost while addressing the temporal challenges of existing forecast data.

This paper proposes a novel method to estimate rainfall intensity by analyzing the sound of raindrops. An innovative device for collecting acoustic data was designed, capable of blocking ambient noise in rainy environments. The device was deployed in real rainfall conditions during both the monsoon season and non-monsoon season to record raindrop sounds. The collected raindrop sounds were divided into 1 s, 10 s, and 1 min intervals, and the performance of rainfall intensity estimation for each segment length was compared. First, the rainfall occurrence was determined based on four extracted frequency domain features (average of dB, frequency-weighted average of dB, standard deviation of dB, and highest frequency), followed by a quantitative estimation of the rainfall intensity for the periods in which rainfall occurred. The results indicated that the best estimation performance was achieved when using 10 s segments, corresponding to the following metrics: accuracy: 0.909, false alarm ratio: 0.099, critical success index: 0.753, precision: 0.901, recall: 0.821, and F1 score: 0.859 for rainfall occurrence classification; and root mean square error: 1.675 mm/h, R2: 0.798, and mean absolute error: 0.493 mm/h for quantitative rainfall intensity estimation. The proposed small and lightweight device is convenient to install and manage and is remarkably cost-effective compared with traditional rainfall observation equipment. Additionally, this compact rainfall acoustic collection device can facilitate the collection of detailed rainfall information over vast areas.

Wildfire indices have been widely used to assess wildfire potential under varying climate conditions. However, their region-specific applicability remains limited due to inherent incompatibilities among various indices. This study proposes post-processing procedures for wildfire forecasting by applying statistical index-merging methods to enhance the utility of conventional wildfire indices in forested regions of South Korea. Accordingly, 126 wildfire cases from 2014 to 2023 are analyzed, and the performance of conventional indices is assessed individually and in combination using three merging methods: simple averaging, variance-covariance (VC), and triple collocation (TC). The forecasting capabilities of individual and merged indices are evaluated using hit/miss metrics, specifically the probability of detection and false alarm ratio. The results reveal that ensemble merging techniques can partially enhance the forecasting performance of conventional indices that are otherwise suboptimal for the target region. The forecasting performance of both individual and merged indices is higher in forested areas, highlighting vegetation as a significant factor in wildfires. Notably, the forecasting performance of the VC method, which incorporates inter-index correlations, is superior to that of TC, which does not account for these correlations. This robust performance is evident regardless of wildfire size or severity. Furthermore, the findings underscore the critical role of climate conditions in wildfire detection, highlighting the need to address the effects of climate change. Consequently, the application of statistical index-merging methods enhances wildfire forecasting accuracy in Gangwon Province, South Korea, surpassing that of conventional indices alone, despite their global reliability.

Most bridge failures result from scouring around bridge piers, resulting in economic losses and risks to public safety. The conventional equations for predicting the depth of scour at bridge piers have several limitations: (1) They mainly use regression-based techniques that cannot robustly capture the nonlinear relationship between the scour depth and its effective variables; (2) they are applicable only to a narrow range of variability of data; and (3) they are typically calibrated using laboratory data rather than field measurements and thus cannot simulate the prototype environment. To overcome these limitations, in this study, three novel hybrid machine learning methods: particle swarm optimization - extreme gradient boosting (PSO – XGBoost), red fox optimization - XGBoost (RFO – XGBoost), and relativistic particle swarm optimization - XGBoost (RPSO – XGBoost) are applied to estimate the scour depth around circular bridge piers, and their effectiveness is validated using three statistical metrics, i.e. the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). RPSO – XGBoost generates the best results for both dimensional and dimensionless data. Moreover, the proposed approaches outperform the state-of-the-art techniques. The SHapley Additive exPlanations (SHAP) method is used to assess the relative significance of the contributing factors for predicting the scour depth.

This paper presents a novel approach for enhancing long-term runoff simulations through the integration of empirical mode decomposition (EMD) with four machine learning (ML) models: ensemble, support vector machine (SVM), convolutional neural networks (CNN), and artificial neural networks with backpropagation (ANN-BP). The proposed methodology uses EMD to decompose precipitation and temperature time-series into intrinsic mode functions, thereby revealing underlying data patterns. Subsequently, these components are incorporated into the ML models to simulate the runoff time-series. The effectiveness of the hybrid models is evaluated using streamflow runoff data obtained from the Grand, Winnipeg, and Moosonee Rivers in Ontario, Canada. Four widely used performance indices, namely, correlation coefficient, root mean square error (RMSE), mean absolute relative error, and Nash–Sutcliffe efficiency, are employed to assess the models’ performance. The results demonstrate that the hybrid EMD-ML models exhibit significantly superior performance compared with the standalone ML methods. During the validation phase, the EMD-Ensemble, EMD-SVM, EMD-CNN, and EMD-ANN-BP models exhibit notable reductions in the RMSEs of monthly streamflow estimates for the Grand River, amounting to 11%, 22%, 8%, and 33%, respectively, compared with their non-EMD counterparts. Additionally, these hybrid models exhibit improved RMSEs for yearly simulations in the Winnipeg River, with reductions of 54%, 0.08%, 6%, and 4.5% respectively. To further enhance the accuracy of monthly and yearly streamflow estimates, an SVM-recursive feature elimination technique is employed to select a more appropriate EMD dataset in all study cases. This research underscores the potential of integrating EMD with ML models to enhance long-term runoff simulations. The outcomes highlight the superior performance of the hybrid EMD-ML models, demonstrating their ability in generating lower biases than the standalone ML methods. These findings hold significant implications for the field of computational fluid mechanics and can contribute to the understanding of hydrological processes.

AbstractIn this study, the generalized linear model (GLM) and four ensemble methods (partial least squares (PLS), boosting, bagging, and Bayesian) were applied to predict forest fire hazard in the Chalus Rood watershed in the Mazandaran Province, Iran. Data from 108 historical forest fire events collected through field surveys were applied as the basis of the analysis. About 70% of the data were used for training the models, while the remaining 30% was used for testing. A total of 14 environmental, climatic, and vegetation variables were used as input features to the models to predict forest fire probability. After conducting a multicollinearity test on the independent variables, the GLM and the ensemble models were applied for modeling. The efficiency of the models was evaluated using receiver operating characteristic (ROC) curve parameters. Results from the validation process, based on the area under the ROC curve (AUC), showed that the GLM, PLS-GLM, boosted-GLM, Bagging-GLM, and Bayesian-GLM models had efficiencies of 0.79, 0.75, 0.81, 0.84, and 0.85, respectively. The results indicated that all ensemble methods, except the PLS algorithm, improved the performance of the GLM model in modeling forest fire hazards in the Chalus Rood watershed, with the Bayesian algorithm being the most efficient method among them.

Applying data mining techniques for rainfall modeling because of a lack of sufficient memory components may increase uncertainty in rainfall forecasting. To solve this issue, in this research, a deep-learning-based long short-term memory (LSTM) model is developed for the first time for forecasting monthly rainfall data, and its capability is compared with a random forest (RF) data-driven model. To this end, monthly rainfall data for a period of 41 years (1980–2020) from two meteorological stations in Turkey, namely Rize and Konya, with different climatic conditions, are used. The analysis is carried out using optimum window sizes for determining the optimum lag times of rainfall time series. The performance of the models is evaluated using five statistical measures, namely root mean square error (RMSE), RMSE-observations standard deviation ratio (RSR), Legate and McCabe’s index (LMI), correlation coefficient (R) and Nash–Sutcliffe efficiency (NSE), and also using two visual means, namely Taylor and violin diagrams. The results reveal that the LSTM model, as a more efficient tool, outperforms the RF model in forecasting rainfall at both stations, with improved RMSE of 12.2–14.9%, RSR of 12.3–14.8%, R of 9.4–13.5% and NSE of 32.9–33.2%. The LSTM-based approach proposed herein could be adopted over any global climatic conditions to forecast the monthly rainfall with reasonable accuracy.

The optimization problems are becoming more complicated, requiring new and efficient optimization techniques to solve them. Many bio-inspired meta-heuristic algorithms have emerged in the last decade to solve these complex problems as most of these algorithms may be trapped into local optima and could not effectively solve all types of optimization problems. Hence, researchers are still trying to develop new and better optimization algorithms. This paper introduces a novel biologically-based optimization algorithm called circulatory system-based optimization (CSBO). CSBO is modeled based on the function of the body’s blood vessels with two distinctive circuits, i.e. pulmonary and systemic circuits. The proposed CSBO algorithm is tested on a wide variety of complex functions of the real world and validated with the standard meta-heuristic algorithms. The results indicate that the CSBO algorithm successfully achieves the optimal solutions and avoids local optima. Note that the source code of the CSBO algorithm is publicly available at http://www.optim-app.com/projects/csbo.

Abstract Dry days at varied scale are an important topic in climate discussions. Prolonged dry days define a dry period. Dry days with a specific rainfall threshold may visualize a climate scenario of a locality. The variation of monthly dry days from station to station could be correlated with several climatic factors. This study suggests a novel approach for predicting monthly dry days (MDD) of six target stations using different machine learning (ML) algorithms in Bangladesh. Several rainfall thresholds were used to prepare the datasets of monthly dry days (MDD) and monthly wet days (MWD). A group of ML algorithms, like Bagged Trees (BT), Exponential Gaussian Process Regression (EGPR), Matern Gaussian Process Regression (MGPR), Linear Support Vector Machine (LSVM), Fine Trees (FT) and Linear Regression (LR) were evaluated on building a competitive prediction model of MDD. In validation of the study, EGPR-based models were able to better capture the monthly dry days (MDD) over Bangladesh compared to those by MGPR, LSVM, BT, LR and FT-based models. When MDD were the predictors for all six target stations, EGPR produced highest mean R 2 of 0.91 (min. 0.89 and max. 0.92) with a least mean RMSE of 2.14 (min. 1.78 and max. 2.69) compared to other models. An explicit evaluation of the ML algorithms using one-year lead time approach demonstrated that BT and EGPR were the most result-oriented algorithms (R 2 = 0.78 for both models). However, having a least RMSE, EGPR was chosen as the best model in one year lead time. The dataset of monthly dry–wet days was the best predictor in the lead-time approach. In addition, sensitivity analysis demonstrated sensitivity of each station on the prediction of MDD of target stations. Monte Carlo simulation was introduced to assess the robustness of the developed models. EGPR model declared its robustness up to certain limit of randomness on the testing data. The output of this study can be referred to the agricultural sector to mitigate the impacts of dry spells on agriculture.

Estimating wind energy plays an important role in energy science as it can be considered a crucial source of renewable and sustainable energy. In this study, five types of soft computing approaches were implemented to estimate the long-term mean monthly wind speed (W) at 50 weather stations in Iran. The applied models were artificial neural networks (ANN), gene expression programming (GEP), multivariate adaptive regression spline (MARS), adaptive neuro-fuzzy inference system (ANFIS), and random forest (R.F.). In addition, the geographical information (i.e., latitude, longitude, and altitude) and periodicity term (i.e., the number of months in a year) were used to input the models. Results demonstrated that the R.F. technique was the best model for estimating W, utilizing the geographical information and number of the month. Hence, it can be concluded that the applied soft computing techniques can employ the aforementioned inputs for estimating W.

Study region: Urmia Lake basin, Iran. Study focus: An accurate estimation of baseflow provides useful information for various aspects of water resources management. Baseflow estimation is subject to many uncertainties because it cannot be measured directly. This study aims to quantify the influence of uncertainties on the baseflow separation in the Urmia Lake basin, Iran. Herein, long-term observational data was used to evaluate the stability and reliability of baseflow estimation. Seven baseflow separation methods were compared with the mass balance filter (MBF) as a reference method. Here, two indicators including the average annual baseflow coefficient (BFC) and the baseflow index (BFI) were used to assess the impact of climate condition on baseflow separation. In addition, we investigated two sources of uncertainty in the digital filter methods: the recession constant (α) value and the approximation of groundwater recharge. New hydrological insights for the region: Eckhardt's method exhibited a better estimate of the baseflow during both wet and dry years, and exhibited acceptable accuracy during peak flows, even during multiple events. The results of uncertainties among the filter methods revealed that the Lynie & Holick (LH) algorithm and Eckhardt’s method were more sensitive to the amount of α. Moreover, Eckhardt’s method demonstrated a more reliable estimation of the ratio of groundwater recharge to streamflow.

Abstract Discharge of pollution loads into natural water systems remains a global challenge that threatens water and food supply, as well as endangering ecosystem services. Natural rehabilitation of contaminated streams is mainly influenced by the longitudinal dispersion coefficient, or the rate of longitudinal dispersion (D x ), a key parameter with large spatiotemporal fluctuations that characterizes pollution transport. The large uncertainty in estimation of D x in streams limits the water quality assessment in natural streams and design of water quality enhancement strategies. This study develops an artificial intelligence-based predictive model, coupling granular computing and neural network models (GrC-ANN) to provide robust estimation of D x and its uncertainty for a range of flow-geometric conditions with high spatiotemporal variability. Uncertainty analysis of D x estimated from the proposed GrC-ANN model was performed by alteration of the training data used to tune the model. Modified bootstrap method was employed to generate different training patterns through resampling from a global database of tracer experiments in streams with 503 datapoints. Comparison between the D x values estimated by GrC-ANN to those determined from tracer measurements shows the appropriateness and robustness of the proposed method in determining the rate of longitudinal dispersion. The GrC-ANN model with the narrowest bandwidth of estimated uncertainty (bandwidth-factor = 0.56) that brackets the highest percentage of true D x data (i.e., 100%) is the best model to compute D x in streams. Considering the significant inherent uncertainty reported in the previous D x models, the GrC-ANN model developed in this study is shown to have a robust performance for evaluating pollutant mixing (D x ) in turbulent environmental flow systems.

Solar radiation (SR) is considered as a critical factor in determining energy management. In this research, the potential of the Bayesian averaging model (BMA) was investigated for estimating monthly SR. The inputs were monthly average temperature, wind speed, relative humidity, and sunshine duration. The BMA model was employed to estimate SR by extracting information from multiple adaptive neuro-fuzzy systems (ANFIS) and multi-layer perceptron (MLP) models. In this study, Archimedes optimization algorithm (AOA), particle swarm optimization (PSO), genetic algorithm (GA), and bat algorithm (BA) were used to tune the parameters of the ANIFS and MLP. In addition, a multitude of error indices such as root mean square error (RMSE), and Nash Sutcliff efficiency (NSE), and several graphical tools were used to investigate the accuracy of the models. The results showed the better performance of the BMA model than other models for estimating solar radiation. For example, BMA with RMSE of 6.78, MAE of 5.25, and NSE of 0.96 had the best accuracy in the training stage of the Tabriz station. On the other hand, in the testing level of Tehran station, BMA (RMSE=7.89 MJ/ m2, MAE=6.89 MJ/ m2, NSE=0.95) gave the best accuracy, and the MLP model (RMSE= 14.12 MJ/ m2, MAE=12.23 MJ/ m2, and NSE=0.77) gave the worst performance, respectively.

Landslides are among the most frequent secondary disasters caused by earthquakes in areas prone to seismic activity. Given the necessity of assessing the current seismic conditions for ensuring the safety of life and infrastructure, there is a rising demand worldwide to recognize the extent of landslides and map their susceptibility. This study involved two stages: First, the regions prone to earthquake-induced landslides were detected, and the data were used to train deep learning (DL) models and generate landslide susceptibility maps. The application of DL models was expected to improve the outcomes in both stages. Landslide inventory was extracted from Sentinel-2 data by using U-Net, VGG-16, and VGG-19 algorithms. Because VGG-16 produced the most accurate inventory locations, the corresponding results were used in the landslide susceptibility detection stage. In the second stage, landslide susceptibility maps were generated. From the total measured landslide locations (63,360 cells), 70% of the locations were used for training the DL models (i.e., convolutional neural network [CNN], CNN-imperialist competitive algorithm, and CNN-gray wolf optimizer [GWO]), and the remaining 30% were used for validation. The earthquake-induced landslide conditioning factors included the elevation, slope, plan curvature, valley depth, topographic wetness index, land cover, rainfall, distance to rivers, and distance to roads. The reliability of the generated susceptibility maps was evaluated using the area under the receiver operating characteristic curve (AUROC) and root mean square error (RMSE). The CNN-GWO model (AUROC = 0.84 and RMSE = 0.284) outperformed the other methods and can thus be used in similar applications. The results demonstrated the efficiency of applying DL in the natural hazard domain. The CNN-GWO predicted that approximately 38% of the total area consisted of high and very high susceptibility regions, mainly concentrated in areas with steep slopes and high levels of rainfall and soil wetness. These outcomes contribute to an enhanced understanding of DL application in the natural hazard domain. Moreover, using the knowledge of areas highly susceptible to landslides, officials can actively adopt steps to reduce the potential impact of landslides and ensure the sustainable management of natural resources.

The accurate estimation of dew point temperature (Tdew) is important in climatological, agricultural, and agronomical studies. In this study, the feasibility of two soft computing methods, random forest (RF) and multivariate adaptive regression splines (MARS), is evaluated for predicting the long-term mean monthly Tdew. Various weather variables including air temperature, sunshine duration, relative humidity, and incoming solar radiation from 50 weather stations in Iran as well as their geographical information (or a subset of them) are used in RF and MARS as inputs. Three statistical indicators namely, root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R) are used to assess the accuracy of Tdew estimates from both models for different input configurations. The results demonstrate the capability of the RF and MARS methods for predicting the long-term mean monthly Tdew. The combined scenarios in both the RF and MARS methods are found to produce the best Tdew estimates. The best Tdew estimates were obtained by the MARS model with the RMSE, MAE, and R of respectively 0.17°C, 0.14°C, and 1.000 in the training phase; 0.15°C, 0.12°C, and 1.000 in the validation phase; and 0.18°C, 0.14°C, and 0.999 in the testing phase.

Predicting the amount of sediment in water resource projects is one of the most important measures to be taken, while sediments have an unknown nature in their behavior. In this research, using the data recorded at the Mazrae station between 2002 and 2013, the amount of sediment in the catchment area of Maku Dam has been predicted using different models of intelligent algorithms. Recorded data including river flow (m3/s), sediment concentration (mg/L), and temperature (°C) were considered input data, and sediment load (ton/day) was considered output data. Initially, using the correlation test, the relationship between each input data with output data was considered. The results show high correlation of sediment concentration data and river flow with sediment load and low correlation of temperature data with these data. In order to find the best combination of data for prediction, the combination of single, binary, and triple data was considered in sensitivity analysis. In order to achieve the purpose of this study, first with the classical adaptive neuro-fuzzy inference system (ANFIS), the amount of sediment load was predicted, and then using evolutionary algorithms in ANFIS training, their performance was examined. The intelligent algorithms used in this study were ant colony optimization extended to continuous domain, particle swarm optimization, differential evolution, and genetic algorithm. The results showed that adaptive neuro-fuzzy inference system–ant colony optimization extended to continuous domain, adaptive neuro-fuzzy inference system–particle swarm optimization, adaptive neuro-fuzzy inference system–genetic algorithm, adaptive neuro-fuzzy inference system–differential evolution, and classical ANFIS had the best performance in predicting the amount of sediment load. In the meantime, it was observed that the coefficient of determination, root mean square error, and scatter index in the test mode for the adaptive neuro-fuzzy inference system–ant colony optimization extended to continuous domain algorithm with the best prediction dataset (sediment concentration + river flow) are equal to 0.991, 13.001, and (ton/day), 0.112, and those for the ANFIS with the weakest prediction (temperature + river flow) are equal to 0.490, 107.383 (ton/day), and 0.929, respectively. The present study showed that the use of intelligent algorithms in ANFIS training has been able to improve its performance in predicting the amount of sediment load in the catchment area of Maku Dam.

Green roof systems could help reduce peak discharge and retain rainwater in urban areas. The objective of this study was to investigate the hydrological behavior of a green roof system by using the SEEP/W model. The rainfall-runoff relationship within the green roof system was simulated and the results were compared with actual data from a test bed for green roof systems to verify the applicability of SEEP/W. Then, the verified SEEP/W model was used to simulate the green roof system by varying four factors (soil type, rainfall intensity, substrate depth, and green roof slope) to explore the hydrological performance through the peak discharge to rainfall intensity (PD/RI) ratio and the rain water retention rate. The results show that the model presents slightly faster and greater peak time and peak discharge values, respectively, as compared to the observational data. This is attributed to the vegetation conditions in the real green roof system. However, it is also shown that the SEEP/W model can be used to design green roof systems and evaluate their hydrological behavior because of its modeling efficiency. Thus, the SEEP/W model can be used to reliably design and manage green roof systems by further considering the vegetation conditions and water flow dynamics. Furthermore, it would be desirable to consider additional factors, such as vegetation and an insulating pebble layer, in the design and management of green roofs in future work.

A haptic sensor coupled to a gamepad or headset is frequently used to enhance the sense of immersion for game players. However, providing haptic feedback for appropriate sound effects involves specialized audio engineering techniques to identify target sounds that vary according to the game. We propose a deep learning-based method for sound event detection (SED) to determine the optimal timing of haptic feedback in extremely noisy environments. To accomplish this, we introduce the BattleSound dataset, which contains a large volume of game sound recordings of game effects and other distracting sounds, including voice chats from a PlayerUnknown’s Battlegrounds (PUBG) game. Given the highly noisy and distracting nature of war-game environments, we set the annotation interval to 0.5 s, which is significantly shorter than the existing benchmarks for SED, to increase the likelihood that the annotated label contains sound from a single source. As a baseline, we adopt mobile-sized deep learning models to perform two tasks: weapon sound event detection (WSED) and voice chat activity detection (VCAD). The accuracy of the models trained on BattleSound was greater than 90% for both tasks; thus, BattleSound enables real-time game sound recognition in noisy environments via deep learning. In addition, we demonstrated that performance degraded significantly when the annotation interval was greater than 0.5 s, indicating that the BattleSound with short annotation intervals is advantageous for SED applications that demand real-time inferences.

Retrieval of near-surface air temperature (NSAT) from remote sensing data is often ill-posed because of insufficient observational information. Many factors influence the NSAT, which can lead to the instability of the accuracy of traditional algorithms. To overcome this problem, in this study, a fully coupled framework was developed to robustly retrieve NSAT from thermal remote sensing data, integrating physical, statistical, and deep learning methods (PS-DL). Based on physical derivation, the optimal combinations of remote sensing bands were chosen for building the inversion equations to retrieve NSAT, and deep learning was used to optimize the calculations. Multisource data (physical model simulations, remote sensing data, and assimilation products) were used to establish the training and test databases. The NSAT retrieval accuracy was enhanced using the land surface temperature (LST) and land surface emissivity (LSE) as prior knowledge. The highest mean absolute error (MAE) and root-mean-square error (RMSE) of the retrieved NSAT data were 0.78 K and 0.89 K, respectively. In a cross-validation against the China Meteorological Forcing Dataset (CMFD), the MAE and RMSE were 1.00 K and 1.29 K, respectively. The actual inversion MAE and RMSE for the optimal band combination were 1.21 K and 1.33 K, respectively. The proposed method effectively overcomes the limitations of traditional methods as the inversion accuracy is enhanced by adding the information of atmospheric water vapor and more bands, and the applicability (portability) of the algorithm is enhanced using LST and LSE as prior knowledge. This model can become a general inversion paradigm for geophysical parameter retrieval, which is of milestone significance because of its accuracy and the ability to allow deep learning for physical interpretation.

Accurate rainfall-runoff modeling is crucial for water resource management. However, the available models require more field-measured data to produce accurate results, which has been a long-term issue in hydrological modeling. Machine learning (ML) models have shown superiority in the hydrological field over statistical models. The primary aim of the present study was to advance a new coupled model combining model-driven models and ML models for accurate rainfall-runoff simulation in the Voshmgir basin in northern Iran. Rainfall-runoff data from 2002 to 2007 were collected from the tropical rainfall measuring mission (TRMM) satellite and the Iran water resources management company. The findings revealed that the model-driven model could not fully describe river runoff patterns during the investigated time period. The extreme learning machine and support vector regression models showed similar performances for 1-day-ahead rainfall–runoff forecasting, while the long short-term memory (LSTM) model outperformed these two models. Our results demonstrated that the coupled physically based model and LSTM model outperformed other models, particularly for 1-day-ahead forecasting. The present methodology could be potentially applied in the same hydrological properties catchment.

This paper proposes a novel hybrid method for flood susceptibility mapping using a geographic information system (ArcGIS) and satellite images based on the analytical hierarchy process (AHP). Here, the following nine multisource environmental controlling factors influencing flood susceptibility were considered for relative weight estimation in AHP: elevation, land use, slope, topographic wetness index, curvature, river distance, flow accumulation, drainage density, and rainfall. The weight for each factor was determined from AHP and analyzed to investigate critical regions that are more vulnerable to floods using the overlay weighted sum technique to integrate the nine layers. As a case study, the ArcGIS-based framework was applied in Seoul to obtain a flood susceptibility map, which was categorized into six regions (very high risk, high risk, medium risk, low risk, very low risk, and out of risk). Finally, the flood map was verified using real flood maps from the previous five years to test the model’s effectiveness. The flood map indicated that 40% of the area shows high flood risk and thus requires urgent attention, which was confirmed by the validation results. Planners and regulatory bodies can use flood maps to control and mitigate flood incidents along rivers. Even though the methodology used in this study is simple, it has a high level of accuracy and can be applied for flood mapping in most regions where the required datasets are available. This is the first study to apply high-resolution basic maps (12.5 m) to extract the nine controlling factors using only satellite images and ArcGIS to produce a suitable flood map in Seoul for better management in the near future.

This paper proposes a novel hybrid solution of SfM (Structure from Motion) and SLAM (Simultaneous Localization And Mapping) for the online generation of a 3D photorealistic map. As it is well known, the SfM can generate a 3D photo map, but it is difficult to get the real-scale as well as to build an online map (i.e., the map cannot be generated on the fly). In contrast, while SLAM frameworks are suitable for online real-scale mapping, they are not adequate for 3D photo map generation. To create a synergy effect, the proposed method combines SfM and SLAM. The way of combination is to use SfM for the generation of local maps and to utilize SLAM for a fusion of local maps in a globally consistent manner. Experimental results show that the proposed hybrid approach enables online 3D photorealistic mapping.