Prediction Of Seepage Research Articles

Wavelet–ANN hybrid model evaluation in seepage prediction in nonhomogeneous earthen dams

ABSTRACT In this study, novel methods such as wavelet–artificial neural network hybrid models and artificial neural network models were used to predict seepage from the Zonouz earthen dam. The dataset consisted of 972 piezometric data points. Statistical fitting methods such as root mean squared error, determination coefficient, scatter plots, and data distribution diagrams were used to evaluate the results. The findings indicated that the wavelet–artificial neural network hybrid model was more accurate than the artificial neural network model. Specifically, during training, the wavelet–artificial neural network hybrid model had determination coefficients and root mean squared errors of 0.820, 0.680, 743.39, and 792.52, while the artificial neural network model had 0.700, 0.600, 426.39, and 131.45. Similarly, during validation, the wavelet–artificial neural network hybrid model had determination coefficients and root mean squared errors of 0.700, 0.600, 426.39, and 131.45, while the artificial neural network model had 0.823, 0.680, 743.39, and 792.52. Therefore, the wavelet–artificial neural network hybrid model can be proposed as a precise method for predicting seepage in earthen dams and is more accurate than the artificial neural network model. This study highlights the importance of preventing dam failures and using advanced modeling techniques for better predictions and preventive measures.

Seepage prediction model of the earth-rock dam based on TCN considering rainfall lag effect

Renewable energy has the highest conversion efficiency, is the most flexible in regulating peak power in the grid, and has the potential to significantly reduce emissions. Hydropower is one of the main ways to optimize power energy structure by building earth-rock dams that block water and generate electricity. Seepage is a physical quantity that characterizes the safety of earth-rock dams. Studying the intelligent prediction model of earth-rock dams is an effective means of understanding the evolution of seepage behavior, and it is also crucial for the safe operation and energy efficiency of earth-rock dams. To create a rainfall factor expression reflecting the hysteresis effect of rain, actual monitoring data of different piezoelectric tubes on the upstream and downstream sides of the soil core wall of an earth-rock dam is considered. Based on the key influencing factors of the seepage behavior of earth-rock dams, the novel temporal convolutional network (TCN) algorithm in deep learning is introduced into the seepage behavior prediction of earth-rock dams, constructing the intelligent prediction model of seepage of earth-rock dams based on TCN. The engineering example shows that the seepage prediction model of the earth-rock dam based on TCN has better prediction performance than the seepage prediction model of the earth-rock dam based on support vector regression (SVR), extreme learning machine, and long-short term memory. The determination coefficient is more significant than 0.9, and the relative error of prediction is less than 1‰. The model’s prediction accuracy is high, and the stability of the prediction performance is good. The model’s prediction performance also improves after considering the rainfall lag effect.

A Statistical Prediction Model for Sluice Seepage Based on MHHO-BiLSTM

The current seepage prediction model of the sluice gate is rarely used. To solve the problem, this paper selects the bidirectional long and short-term neural network (BiLSTM) with high information integration and accuracy, which can well understand and capture the temporal pattern and dependency relationship in the sequence and uses the multi-strategy improved Harris Hawks optimization algorithm (MHHO) to analyze its two hyperparameters: By optimizing the number of forward and backward neurons, the overfitting and long-term dependence problems of the neural network are solved, and the convergence rate is accelerated. Based on this, the MHHO-BiLSTM statistical prediction model of sluice seepage is established in this paper. To begin with, the prediction model uses water pressure, rainfall, and aging effects as input data. Afterward, the bidirectional long short-term memory neural network parameters are optimized using the multi-strategy improved Harris Hawks optimization algorithm. Then, the statistical prediction model based on the optimization algorithm proposed in this paper for sluice seepage is proposed. Finally, the seepage data of a sluice and its influencing factors are used for empirical analysis. The calculation and analysis results indicate that the optimization algorithm proposed in this paper can better search the optimal parameters of the bidirectional long short-term memory neural network compared with the original Harris Eagle optimization algorithm, optimizing the bidirectional long short-term memory neural network (HHO-BiLSTM) and the original bidirectional long short-term memory neural network (BiLSTM). Meanwhile, the bidirectional long and short-term neural network (BiLSTM) model shows higher prediction accuracy and robustness.

Assessing single and hybrid AI approaches in conjunction with FEM to enhance seepage prediction in earth dams

Assessing single and hybrid AI approaches in conjunction with FEM to enhance seepage prediction in earth dams

Settlement, slope stability and seepage analyses By Numerical Modelling Method and their applications in practice

The encountered situations during the design process of a gully erosion control site in Kano State are discussed in this article. The project was to design a rectangular concrete lined drainage channel with short side walls to efficiently convey flood water and prevent embankment erosion. Because of the embankment depth and soil type on the site which are mostly silty/clayey sand, settlement of the huge concrete channel, seepage and the unprotected embankment slope were issues of major concern. Settlement, slope stability and seepage analyses and designs were some of the several activities undertaken for the project. The anticipated total settlement prediction was performed by numerical simulation from which the differential settlement was then calculated. The prediction of the safety factor to determine the stability of the slope was performed by numerical simulation using SLOPE/W. The hydraulic velocity and rate of seepage prediction was performed by numerical modelling using SEEP/W. The use of numerical technique was specifically recommended by the consultants of the funder of the project, the World Bank. It was observed that numerical modelling technique provided accurate results of settlement, factor of safety, hydraulic velocity and rate of seepage and was therefore recommended for both research and practical applications.

Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization

In this study, a seepage prediction model was established for roller-compacted concrete dams using support vector regression (SVR) with hybrid parameter optimization (HPO). The model includes data processing via HPO and machine learning through SVR. HPO benefits from the correlation extraction capability of grey relational analysis and the dimensionality reduction technique of principal component analysis. The proposed model was trained, validated, and tested using 22 years of monitoring data regarding the Shuidong Dam in China. We compared the performance of HPO with other popular methods, while the SVR method was compared with the traditional time-series prediction method of long short-term memory (LSTM). Our findings reveal that the HPO method proves valuable real-time dam safety monitoring during data processing. Meanwhile, the SVR method demonstrates superior robustness in predicting seepage flowrate post-dam reinforcement, compared with LSTM. Thus, the developed model effectively identifies the factors related to seepage and exhibits high accuracy in predicting fluctuation trends regarding the Shuidong Dam, achieving a determination coefficient R2 > 0.9. Further, the model can provide valuable guidance for dam safety monitoring, including diagnosing the efficacy of monitoring parameters or equipment, evaluating equipment monitoring frequency, identifying locations sensitive to dam seepage, and predicting seepage.

A review of artificial intelligence methods for predicting gravity dam seepage, challenges and way-out

Abstract Seepage is the phenomenon of water infiltrating through a gravity dam's foundation, causing erosion and weakening the dam's construction over time. If not properly managed, this can eventually lead to the dam's catastrophic failure, posing a significant danger to public safety and the environment. As a result, precise seepage prediction in gravity dams is essential for ensuring their safety and stability. This review paper looks at the use of artificial intelligence (AI) techniques for predicting seepage in gravity dams, as well as the challenges and possible solutions. The paper identifies and suggests potential solutions to the challenges connected with using AI for seepage prediction, such as data quality and model interpretability. The paper also covers future research paths, such as the creation of advanced machine learning algorithms and the improvement of data collection and processing. Overall, this review gives insight on the current state of the art in using AI to predict gravity dam seepage and recommends methods to improve the accuracy and reliability of such models.

Research on Prediction of Dam Seepage and Dual Analysis of Lag-Sensitivity of Influencing Factors Based on MIC Optimizing Random Forest Algorithm

The seepage of the dam is an important representation of the operation characteristics of the dam, and there are many factors affecting the seepage with a certain lag. It is still difficult to predict its change and sensitivity because of complex operating conditions. At present, the lag-sensitivity of influence factors of the dam seepage has not been studied. The time series influence factors of seepage are determined by HTRT (hydrostatic-thermal-rainfall-time) model in this paper. To avoid the pseudo fitting of conventional methods, HTRT model nested random forest algorithm is used to establish the predicting model of the dam seepage. And MIC algorithm is used to achieve the dual purposes of time lag and sensitivity analysis. Firstly, the time lag of relationship between seepage and its influencing factors is characterized, and the most appropriate lag time of the HTRT model factors is determined. Secondly, independent correlation analysis on all influencing factors is carried out and the sensitivity of each factor is analyzed by MIC. Meanwhile, the sensitivity of the factors to seepage is quantitatively analyzed by the two parameters of %IncMSE and IncNodePurity of RF algorithm. The sensitivity of influencing factors is analyzed by comparing MIC results with RF results. Combined with the case, taking the error of fitting prediction as the evaluation index of seepage prediction, the prediction accuracy of MIC-RF model, RF model and MIC-BPNN (Back Propagation neural network) model is calculated and compared. Case study showed that MIC- RF monitoring model has high prediction accuracy, strong adaptability and high robustness in dam seepage, and the sensitivity and time lag of influencing factors can be quantitatively analyzed. The water pressure and rainfall of the lag time are 14 days and 16 days respectively. The sensitivity study of the time series influencing factors of seepage showed that the water pressure component is the main controlling factor of seepage, and rainfall component is more sensitive to later stage. The MIC-RF model can be used as a new dam seepage safety monitoring model.

Artificial Intelligence Based Dam Concrete Seepage Prediction Using Wireless Sensor Network

Leakage checking is a fundamental errand in the gamble the executives of substantial dams. Dams assume a fundamental part in reaping energy and using the energy for zap and water system purposes. Aside from that dam safeguard against flooding by gathering and holding waters when they arrive at a specific level. When gathered, a dam may be intended to deliver the water once again into the stream at a controlled speed or redirect the water somewhere else for different purposes. Because of unexpected circumstances blunder of dams would prompt devastating harms, which is exceptionally obvious on account of 2018 Kerala floods, where 35 of its 54 dams were let open without earlier alerts and early activity plans prompting loss of lives, property harms and so on Thus, the issue referenced above is corrected by continuous sensors, for example, temperature, water level, and precipitation and water pressure. These qualities are likewise shown through LCD

Extreme Learning Machine Using Improved Gradient-Based Optimizer for Dam Seepage Prediction

Extreme Learning Machine Using Improved Gradient-Based Optimizer for Dam Seepage Prediction

Use of Recurrent Neural Network with Long Short-Term Memory for Seepage Prediction at Tarbela Dam, KP, Pakistan

Estimating the quantity of seepage through the foundation and body of a dam using proper health and safety monitoring is critical to the effective management of disaster risk in a reservoir downstream of the dam. In this study, a deep learning model was constructed to predict the extent of seepage through Pakistan’s Tarbela dam, the world’s second largest clay and rock dam. The dataset included hydro-climatological, geophysical, and engineering characteristics for peak-to-peak water inflows into the dam from 2014 to 2020. In addition, the data are time series, recurring neural networks (RNN), and long short-term memory (LSTM) as time series algorithms. The RNN–LSTM model has an average mean square error of 0.12, and a model performance of 0.9451, with minimal losses and high accuracy, resulting in the best-predicted dam seepage result. Damage was projected using a deep learning system that addressed the limitations of the model, the difficulties of calculating human activity schedules, and the need for a different set of input data to make good predictions.

Prediction method of permeability of textile-reinforced concrete based on fractal dimension theory

Water in the external environment of textile-reinforced concrete (TRC) migrates along the direction of internal directional fiber bundles, thereby damaging the TRC and thus increasing the permeability of the internal matrix. This paper studies the effects of concrete water–cement ratios of concrete, grid sizes and fiber bundle Tex content on the permeability of TRC on the macro and micro scales, and the roughness of concrete was evaluated by fractal dimension through a nuclear magnetic resonance test. Results show that the permeability of TRC increases with the decrease in the grid size of the textile, the increase in the Tex content and the increase in the water–cement ratio of concrete. In this paper, a TRC seepage prediction model is established based on the dimensional analysis method and permeability test. The increase of permeability will seriously affect the durability of building materials and will be unsuitable for strengthening and repairing buildings. Therefore, studying the increase of the permeability of TRC under the action of external pressure water is important.

Improving Dam Seepage Prediction Using Back-Propagation Neural Network and Genetic Algorithm

Statistical model is a traditional safety diagnostic model for dam seepage. It can hardly display the nonlinear relationship between dam seepage and the load sets and has the disadvantage of poor extension prediction. In this paper, the theories of Back Propagation Neural Network (BPNN) combined with Genetic Algorithm (GA) are applied to the seepage prediction model. Taking a typical dam in China as an example, the prediction results of BPNN-GA model and statistical model are compared with the monitoring values. The results show that the improved dam seepage model enhances the ability of nonlinear mapping and generalization and makes the seepage prediction more accurate and reasonable in the near future. According to the established criterion, the safety state of the dam in flood season is evaluated.

Dam Seepage Prediction Using RBF and GFF Models of Artificial Neural Network; Case Study: Boukan Shahid Kazemi's Dam

Dams have been always considered as the important infrastructures and their critical values measured. Hence, evaluation and avoidance of dams’ destruction have a specific importance. In this study seepage of the embankmentof Boukan Shahid Kazemi’s dam in Iran has been analyzed via RBF (radial basis function network) and GFF (Feed-Forward neural networks) models of Artificial Neural Network (ANN). RBF and GFF of ANN models were trained and verified using each piezometer’s data and the water levels difference of the dam. To achieve this goal,based on the number of data and inputs,864piezometric data set were used, of which 80% (691 data) was used for the training and 20% (174 data) for the testing the network.The results showed good agreement between observed and predicted values and concluded the RBF model has high potential in estimating seepage with Levenberg Marquardt training and 4 hidden layers. Also the values of statistical parameters R2 and RMSE were 0.81 and the 33.12.

Combining imaging techniques with nonparametric modelling to predict seepage hotspots in irrigation channels

Using the Murrumbidgee Irrigation Area, Australia as a case study, we present an integrated approach for identifying seepage hotspots and predicting seepage losses from open channel. The approach is particularly important to facilitate investments for improving irrigation conveyance efficiencies, thus enabling sustainable agricultural water use. A qualitative assessment is used for capturing seepage hotspots with electromagnetic inductance (EM31) imaging techniques, followed by actual seepage measurements. Based on data from major irrigation systems in the southern Murrumbidgee Irrigation Area, a case is made for cost-effective methodology to locate seepage hotspots and quantify seepage losses in channels. In particular, a predictive model was developed based on EM31 survey and direct measured channel seepage data. The main input data for the model were EM values, soil types, water depth in channels, wetted perimeter of channels and whether water is flowing in channels. The output from the model was a seepage loss value in channels. The three different modelling techniques considered were the Generalised Linear Mixed (GLM) model, Random Forest (RF) model and Generalized Boosted Regression Model (GBM), and a best performing model for seepage prediction was identified. The RF model was found to the most reliable, explaining 60% of the variability in the data and with the least mean absolute error. The study indicated that the RF model can be used to locate seepage hotspots in channels and determine the magnitude of seepage losses.

Effect of upstream semi-impervious blanket of embankment dams on seepage

A provision of impervious blanket is investigated aiming to reduce seepage and to increase embankment dam’s stability. The investigation generates sufficient data for typical 2D embankment dam cross-sections by numerically solving a wide range of configurations of a provision of upstream blanket. The generated data comprise the correlation between seepage and the various configuration parameters in terms of upstream blanket thickness and length, effects of anisotropy of bed material, foundation depth, and permeability. These data-sets were used to develop design charts, regression, and ANN models. Results showed that application of impervious of blanket in upstream of the earthen dam at appropriate length and thickness is effective in reducing seepage and thereby increasing dam stability. Performance of ANN was excellent in prediction of seepage.

Application of Numerical Modelling and Genetic Programming in Hydrocarbon Seepage Prediction and Control for Crude Oil Storage Unlined Rock Caverns

Seepage control is a prerequisite for hydrocarbon storage in unlined rock caverns (URCs) where the seepage of stored products to the surrounding host rock and groundwater can cause serious environmental and financial problems. Practically seepage control is performed by permeability and hydrodynamic control methods. This paper employs numerical modelling and genetic programming (GP) for the purpose of seepage prediction and control method determination for the crude oil storage URCs based on the effective parameters including hydrogeologic characteristic of the rock and physicochemical properties of the hydrocarbons. Several levels for each parameter were considered and all the possible scenarios were modelled numerically for the two-phase mixture model formulation. The corresponding seepage values were evaluated to be used as genetic programming data base to generate representative equations for the hydrocarbon seepage value. The coefficients of determination (R2) and relative percent errors of the proposed equations show their ability in the seepage prediction and permeability or hydrodynamic control method determination and design. The results can be used for crude oil storage URCs worldwide.

The influences of row grade, ridge height and field slope on the seepage hydraulics of row sideslopes in contour ridge systems

Seepage plays an important role in soil erosion in contour ridge systems. Seepage generated from subsurface flow causes hillslope instability by reducing the soil shear strength and mobilizing soil particles and can produce cave-like features called seepage undercuts that can lead to contour failure. As the main threat to contour plowing, seepage results in large amounts of soil erosion due to row grade. Models used to predict seepage over a time series will provide a basis for modeling soil erosion resulting from seepage in contour ridging systems. Understanding seepage and its effects will advance our knowledge regarding seepage erosion mechanisms in contour ridge systems. In this study, 23 treatments were arranged using an orthogonal rotatable central composite design to model a seepage time series, build a simple seepage prediction model and investigate the effects of row grade, field slope and ridge height on seepage discharge.Most of the seepage discharge time series followed an S-shaped curve. The seepage discharge processes were fit by an exponential model with a determination coefficients (R2) greater than 0.995. Furthermore, the physical meaning of the exponential model was consistent with the experimental results. The seepage discharge continuously increased before the inflection point and then decreased. Finally, the seepage discharge approached a steady value. The maximum seepage discharge growth rate was achieved within 14 min, and the seepage discharge became steady within 106 min. Second-order polynomial regression models were used to determine the total and predicted steady seepage discharge using independent variables of row grade, field slope and ridge height, which produced R2 values of 0.66 (p < 0.05) and 0.68 (p < 0.05), respectively. Ridge height and row grade significantly affected (p < 0.05) the total and predicted steady seepage discharge. Field slope (and its related factors) was ignored because it had no significant effects on seepage discharge. The effects of row grade resulted in a concave curve with an increasing factor value, and ridge height exerted a positive linear effect on seepage discharge.

Influence of Nano Materials in the Distressed Domain during Maintenance

In irrigation structures, seepage through the body wall and foundation play a major role for the assessment of failures in the structures. To design any kind of structure for the proper irrigation, the effect due to seepage should be considered widely. Many methods have been suggested for the prediction of seepage. Seepage analysis ofirrigation structures works mainly on the basis of two dimensional Laplace equation. The Partial Differential Equation Toolbox in MATLAB provides a powerful and flexible environment for the study and solution of partial differential equations in two space dimensions and time. The equations are discretized by the Finite Element Method (FEM). Fluid flow through porous media particularly in the case of irrigation and hydraulic structures like dams and weirs is the focus of the current study and here flaws or cracks which occur in the domain cause variations and need remedial ones to improve or bring back to the original flow pattern. Since flaws in terms of fissures are very small injecting nanomaterial mixed mortar can provide significant improvements and modifications. Here in a rectangular domain the flow is studied throw finite element modeling with and without different sizes and location of flaws. Later these flaws are filled with nanomaterial mortars whose properties are based on test results and the flow is again studied to bring out the changes and improvements. Results are given for different nanomaterial mortars with different flaw sizes.

Prediction of Seepage and Slope Stability in a Flume Test and an Experimental Field Case

As a participant to round robin test, Middle East Technical University (METU) team performed infiltration and slope stability analyses to simulate a laboratory flume infiltration test and a field experiment, and calculated, for both cases, changes in the suction distribution and in slope stability due to rainfall and evaporation. The overall methodology, the details of the numerical model, calibrations to assess accurate soil properties and estimation procedure for both cases are explained and presented in this study. Use of separate wetting and drying soil hydraulic properties are found to be necessary for proper infiltration simulations. For field cases, it is concluded that evaporation and its duration also plays a critical role and must be considered in numerical analyses.