Artificial neural network technique for modeling of groundwaterlevel in Langat Basin, Malaysia (original) (raw)
Related papers
Forecasting groundwater level using artificial neural networks
2009
The performance of the artificial neural network (ANN) model, i.e. standard feed-forward neural network trained with Levenberg-Marquardt algorithm, was examined for forecasting groundwater level at Maheshwaram watershed, Hyderabad, India. The model efficiency and accuracy were measured based on the root mean square error (RMSE) and regression coefficient (R 2). The model provided the best fit and the predicted trend followed the observed data closely (RMSE = 4.50 and R 2 = 0.93). Thus, for precise and accurate groundwater level forecasting, ANN appears to be a promising tool.
Groundwater level forecasting using artificial neural networks
Journal of Hydrology, 2005
A proper design of the architecture of Artificial Neural Network (ANN) models can provide a robust tool in water resources modeling and forecasting. The performance of different neural networks in a groundwater level forecasting is examined in order to identify an optimal ANN architecture that can simulate the decreasing trend of the groundwater level and provide acceptable predictions up to 18 months ahead. Messara Valley in Crete (Greece) was chosen as the study area as its groundwater resources have being overexploited during the last fifteen years and the groundwater level has been decreasing steadily. Seven different types of network architectures and training algorithms are investigated and compared in terms of model prediction efficiency and accuracy. The different experiment results show that accurate predictions can be achieved with a standard feedforward neural network trained with the Levenberg-Marquardt algorithm providing the best results for up to 18 months forecasts.
Groundwater Level Forecasting Using Artificial Neural Network
Ground water plays major role in meeting the demands of water for various sectors in India. The ever increasing demand for ground water to satisfy the needs of a spiraling population has resulted in severe stress on the limited resources available, leading to progressive decline of water levels. In India, ground water has played the pivotal role in fulfilling the demands of domestic, industrial and agricultural sectors. Design of architecture of Artificial Neural Network a rebust tool in water resource modeling and forecasting. The performance of different neural networks in groundwater level forecasting is examined in order to identify an optimal ANN architecture that can simulate the trend of groundwater level and provide predictions. Five different criteria were used in order to evaluate the effectiveness of each network and its ability to make precise predictions. They are Coefficient of Efficiency (CE), Root Mean Square Error (RMSE), Mean absolute error (MAE), R2 Efficiency, and Correlation Coefficient (CC). The different experimental results show that accurate prediction can be achieved with a standard feed forward neural network trained with Conjugate gradient algorithm providing best results of prediction.
A review: Groundwater level forecasting using artificial neural network
2018
As groundwater resources are more intensively used, there is increasing demand for monitoring of groundwater systems. Precise prediction of groundwater level is important for management of groundwater source. Out of the various methods available, ANN is a very useful tool for predicting groundwater level. In Artificial neural network also different models were used for forecasting of groundwater level but most accurate predictions was achieved with a standard feed forward neural network trained with the Leven berg-Marquardt algorithm.
2019
Groundwater plays an important role in providing water supply especially in arid and semi-arid regions such as Iran. Given globally water crisis, monitoring and analyzing water levels can help water resources managers and planners for sustainable utilization and management of water supplies. On the other hand, groundwater processes exhibit dynamic, temporal and spatial patterns; making groundwater fluctuation modeling a complex and challenging task. Among different modeling methods, artificial neural networks (ANNs) are regularly used for complicated problems due to their distinctive and powerful properties. Qom plain in Iran is an arid region whose groundwater utilization in the last decades has led to downfall in water table. In this study groundwater level fluctuations were investigated in two distinct wells in this region using monthly groundwater level data recorded for 11 years. For modeling, the ground water time series of each studied well were entered as the input and outpu...
Civil Engineering and Architecture, 2022
Accurate and reliable groundwater level prediction is a critical component in water resources management. This paper developed two methods to predict forty-six months of groundwater level fluctuation. The approaches of Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) were compared for predicting groundwater levels. MLR and ANN approaches were performed at two monitoring wells, Ubung and Ngurah Rai, in the Denpasar region of Bali, Indonesia, considering all significant inputs of hydrometeorological time series data: barometric pressure, evaporation, temperature, wind, bright sunshine, rainfall, and groundwater level. The model’s performance was assessed statistically and graphically. The ANN-predicted groundwater levels agreed better with the observed groundwater levels than the MLR-predicted groundwater levels at all sites. The results show the ANN performs better than MLR in terms of statistical errors, notably mean square error (MSE) value of 0.6325; root mean square error (RMSE) value of 0.7953; mean absolute error (MAE) value of 0.6122 based on the MLR in the Ubung monitoring well, while ANN models got an MSE value of 0.143; RMSE value of 0.379, and MAE value of 0.311. For the Ngurah Rai monitoring well, the MSE value is of 1.3406, RMSE value of 1.1579, and MAE value of 0.9152 for MLR, while ANN models obtained MSE value of 0.0483, RMSE value of 0.2198, and MAE value of 0.1266.
PREDICTION OF GROUNDWATER LEVEL USING ARTIFICIAL NEURAL NETWORK AND MULTIVARIATE TIME SERIES MODELS
ICCESD 2020 Conference, 2020
Groundwater is the major source of potable water supply in Bangladesh. The overextraction of groundwater and as a consequence, the continued depletion of groundwater level are causes numerous problems such as reducation in freshwater supply, increase in water scarcity, reduction in crop yields, degradation of water quality and impact on human health. Therefore, accurate prediction of grounwater level is of great importance for the efficient management of groundwater resources in Bangladesh. In this study, a framework of predicting the groundwater level fluctuations in the shallow aquifer of Bangladesh using is presented and demonstrated through a case study (Kushtia district of Bangladesh). For this purpose, a groundwater level observation station in each upazilla (sub-district) is selected under the study area. The time series groundwater level data collected on a weekly basis during the period from 1999 to 2006 from the observation station is used for the analysis, model development and prediction. Since most shallow aquifers in Bangladesh is unconfined in nature, the fluctuation of groundwater level is highly influenced by rainfall. With this consideration, both groundwater level and rainfall information are required to be taken into account for accurate prediction of groundwater level fluctuations. In the current study, artificial neural network (ANN) and autoregressive integrated moving average with exogenous variable (ARIMAX) time series models are adopted in MATLAB platform for modelling and prediction of groundwater level fluctuations. In order to develop ANN and autoregressive integrated moving average (ARIMA) based univariate time series models, only groundwater level data is used. However, the rainfall data is used as an exogenous input to both ANN and ARIMAX based multivariate time series models. Finally, one-week-ahead groundwater level prediction is carried out using the adopted models and the performance of each model is checked through a number of performance evaluation criteria. The results indicate that ANN and ARIMAX based multivariate models give better prediction compared to the ANN and ARIMA based univariate time series models. It is also found that ANN based models generate the best prediction over the ARIMA and ARIMAX time series models and proves its superiority over the time series models for groundwater fluctuation modelling and prediciton. Overall, this study proves the fact that the inclusion of exogenous input is highly effective to achieve the enhanced prediction of groundwater level fluctuations in the field of groundwater hydrology.
Groundwater level forecasting in a shallow aquifer using artificial neural network approach
Water resources management, 2006
Forecasting the ground water level fluctuations is an important requirement for planning conjunctive use in any basin. This paper reports a research study that investigates the potential of artificial neural network technique in forecasting the groundwater level fluctuations in an unconfined coastal aquifer in India. The most appropriate set of input variables to the model are selected through a combination of domain knowledge and statistical analysis of the available data series. Several ANN models are developed that forecasts the water level of two observation wells. The results suggest that the model predictions are reasonably accurate as evaluated by various statistical indices. An input sensitivity analysis suggested that exclusion of antecedent values of the water level time series may not help the model to capture the recharge time for the aquifer and may result in poorer performance of the models. In general, the results suggest that the ANN models are able to forecast the water levels up to 4 months in advance reasonably well. Such forecasts may be useful in conjunctive use planning of groundwater and surface water in the coastal areas that help maintain the natural water table gradient to protect seawater intrusion or water logging condition.
MATEC Web of Conferences, 2017
Groundwater tables forecasting during implemented river bank infiltration (RBI) method is important to identify adequate storage of groundwater aquifer for water supply purposes. This study illustrates the development and application of artificial neural networks (ANNs) to predict groundwater tables in two vertical wells located in confined aquifer adjacent to the Langat River. ANN model was used in this study is based on the long period forecasting of daily groundwater tables. ANN models were carried out to predict groundwater tables for 1 day ahead at two different geological materials. The input to the ANN models consider of daily rainfall, river stage, water level, stream flow rate, temperature and groundwater level. Two different type of ANNs structure were used to predict the fluctuation of groundwater tables and compared the best forecasting values. The performance of different models structure of the ANN is used to identify the fluctuation of the groundwater table and provide acceptable predictions. Dynamics prediction and time series of the system can be implemented in two possible ways of modelling. The coefficient correlation (R), Mean Square Error (MSE), Root Mean Square Error (RMSE) and coefficient determination (R 2) were chosen as the selection criteria of the best model. The statistical values for DW1 are 0.8649, 0.0356, 0.01, and 0.748 respectively. While for DW2 the statistical values are 0.7392, 0.0781, 0.0139, and 0.546 respectively. Based on these results, it clearly shows that accurate predictions can be achieved with time series 1-day ahead of forecasting groundwater table and the interaction between river and aquifer can be examine. The findings of the study can be used to assist policy marker to manage groundwater resources by using RBI method.
Ground water level prediction using artificial neural network
International Journal of Hydrology Science and Technology, 2016
In this paper, the feedforward neural network was used to predict the groundwater level at Chandpur District of Bangladesh. Levenberg-Marquardt (LM) algorithm was used as network training algorithm and sigmoid function as the transfer function. Weekly groundwater level data of six measuring wells from 1998 to 2007 were used to train and test the neural network. Prediction accuracy of each network structure was tested using mean square error (MSE), root mean square error (RMSE), and efficiency criterion (R 2). Results showed that the artificial neural network (ANN) predicted groundwater level up to ten weeks ahead with reasonable errors. The accuracy of the network decreases rapidly after that limit. The maximum root mean square error was 0.328 metre N-E-A. Husna et al. and 0.193 metre for ten-week and one-week lead prediction respectively. As the one-week lead prediction was found almost similar to the actual field value, this could be useful in missing value analysis.