A Comparative Study of Data-driven Models for Groundwater Level Forecasting

Water Resources Management - Irregular rainfall patterns and limited freshwater availability have driven humans to increase their dependence on groundwater resources. An essential aspect of...     

Comparative Study of Hybrid-Wavelet Artificial Intelligence Models for Monthly Groundwater Depth Forecasting in Extreme Arid Regions,Northwest China

Prediction of groundwater depth (GWD) is a critical task in water resources management. In this study, the practicability of predicting GWD for lead times of 1, 2 and 3 months for 3 observation wells in the Ejina Basin using the wavelet-artificial neural network (WA-ANN) and wavelet-support vector regression (WA-SVR) is demonstrated. Discrete wavelet transform was applied to decompose groundwater depth and meteorological inputs into approximations and detail with predictive features embedded in high frequency and low frequency. WA-ANN and WA-SVR relative of ANN and SVR were evaluated with coefficient of correlation (R), Nash-Sutcliffe efficiency (NS), mean absolute error (MAE), and root mean squared error (RMSE). Results showed that WA-ANN and WA-SVR have better performance than ANN and SVR models. WA-SVR yielded better results than WA-ANN model for 1, 2 and 3-month lead times. The study indicates that WA-SVR could be applied for groundwater forecasting under ecological water conveyance conditions.     

时间序列分析在地下水位预报中的应用

依据北京市地下水位观测井月平均水位资料,运用逐步自回归模型、指数平滑模型、季节性模型3种时间序列模型分别建立地下水位动态模拟和预测模型,并对模型的模拟和预测精度进行对比分析。通过应用实例分析反映,时间序列模型可较全面地反映地下水位动态变化规律,且计算简单,所需资料较少且易于获得,可以作为一种简易快速的地下水位模拟预测模型,能为地下水资源合理开发利用和科学管理提供参考依据。     

A Wavelet-ANFIS Hybrid Model for Groundwater Level Forecasting for Different Prediction Periods

Artificial neural network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) have an extensive range of applications in water resources management. Wavelet transformation as a preprocessing approach can improve the ability of a forecasting model by capturing useful information on various resolution levels. The objective of this research is to compare several data-driven models for forecasting groundwater level for different prediction periods. In this study, a number of model structures for Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Wavelet-ANN and Wavelet-ANFIS models have been compared to evaluate their performances to forecast groundwater level with 1, 2, 3 and 4 months ahead under two case studies in two sub-basins. It was demonstrated that wavelet transform can improve accuracy of groundwater level forecasting. It has been also shown that the forecasts made by Wavelet-ANFIS models are more accurate than those by ANN, ANFIS and Wavelet-ANN models. This study confirms that the optimum number of neurons in the hidden layer cannot be always determined by using a specific formula but trial-and-error method. The decomposition level in wavelet transform should be determined according to the periodicity and seasonality of data series. The prediction of these models is more accurate for 1 and 2 months ahead (for example RMSE?=?0.12, E?=?0.93 and R ²?=?0.99 for wavelet-ANFIS model for 1 month ahead) than for 3 and 4 months ahead (for example RMSE?=?2.07, E?=?0.63 and R ²?=?0.91 for wavelet-ANFIS model for 4 months ahead).     

Synchronizing Artificial Intelligence Models for Operating the Dam and Reservoir System

It is remarkable that several hydrological parameters have a significant effect on the reservoir operation. Therefore, operating the reservoir system is complex issue due to existing the nonlinearity hydrological variables. Hence, determining modern model has high ability in handling reservoir operation is crucial. The present study developed artificial intelligence model, called Shark Machine Learning Algorithm (SMLA) to provide optimal operational rules. The major objective for the proposed model is minimizing the deficit volume between water releases and the irrigation water demand. The current study compared the performance of the SML model with popular evolutionary computing methods, namely Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The proposed models have been utilized of finding the optimal policies to operate Timah Tasoh Dam, which is located in Malaysia. The study utilized considerable statistical indicators to explore the efficiency of the models. The simulation period showed that SMLA approach outperforms both of conventional algorithms. The SMLA attained high Reliability and Resilience (Rel. = 0.98%, Res. = 50%) and minimum Vulnerability (Vul. = 21.9 of demand). It is demonstrated that shark machine learning algorithm would be a promising tool in handling the long-term optimization problem in operation a reservoir system.     

Ensemble Boosting and Bagging Based Machine Learning Models for Groundwater Potential Prediction

Water Resources Management - Due to the rapidly increasing demand for groundwater, as one of the principal freshwater resources, there is an urge to advance novel prediction systems to more...     

地下水中溶解性有机物吸收光谱模型的对比研究

以往对于溶解性有机物(DOM)吸收光谱的研究主要集中在地表水体,为了了解地下水样品的光吸收特性、探索能够方便有效地表征地下水中DOM光吸收性质的理想模型,收集了某河湖相沉积的含水层中62个地下水样品的DOM吸收光谱,对线性指数模型、非线性指数模型、加背景项指数模型和幂函数模型等四种光吸收模型进行了拟合和对比分析。统计检验发现,传统的线性指数模型拟合效果不如其它三种模型好;幂函数模型的精度和实用性相比最佳,平均决定系数为0.991 8,在250～450nm光谱范围内拟合DOM吸收光谱斜率为(5.93±0.40)nm-1。幂函数模型为DOM化学性质及组分信息与模型参数之间的关系的研究提供了一种可行有效的方法。另外,还建立了更为一般的吸收光谱的幂函数模型,以期对地下水DOM快速分析和野外地下水现场调查起到积极作用。     

Learning from Multiple Models Using Artificial Intelligence to Improve Model Prediction Accuracies: Application to River Flows

An investigation is presented in this paper to study the performance of Artificial Intelligence running Multiple Models (AIMM) using time series of river flows. This is a modelling strategy, which is formed by first running two Artificial Intelligence (AI) models: Support Vector Machine (SVM) and its hybrid with the Fire-Fly Algorithm (FFA) and they both form supervised learning at Level 1. The outputs of Level 1 models serve as inputs to another AI Model at Level 2. The AIMM strategy at Level 2 is run by Artificial Neural Network (MM-ANN) and this is compared with the Simple Averaging (MM-SA) of both inputs. The study of the performances of these models (SVM, SVM-FFA, MM-SA and MM-ANN) in the paper shows that the ability of SVM-FFA in matching observed values is significantly better than that of SVM and that of MM-ANN is considerably better than each SVM and/or SVM-FFA but the performances are deteriorated by using the MM-SA strategy. The results also show that the residuals of MM-ANN are less noisy than those shown by the models at  Level 1 and those at Level 2 do not display any trend.     

哈头才当水源地地下水位模拟与预测

采用MODFLOW软件对哈头才当水源地地下位进行数值模拟,经数值模型识别与验证,所取参数基本合理,水位拟合情况良好,模型能够真实地反映水源地地下水位的变化特征。在模型识别与验证的基础上,给出预测模型的初始条件、边界条件及其源汇项,对2009年10月—2029年10月地下水位进行了预测。结果表明:水源地按照设计开采方案开采,地下水位不会持续下降,计算区内大部分区域水位降深小于6 m,总体降深较小,不会对生态造成明显的影响。     

Processing Modflow在地下水位预测中的应用

数值模拟软件逐渐成为预测地下水演化更普遍的工具,并且广泛应用于地下水动态变化研究.以乌苏市平原区为例,结合区域水文地质条件及钻井资料,利用Processing Modflow建立三维水流数值模拟模型,并对该模型进行平面流场拟合,验证出模拟值基本符合2018年实测地下水位,通过模型模拟2018—2027年不同条件地下水位...     

Artificial Neural Network (ANN) Based Modeling for Karstic Groundwater Level Simulation

A relatively new method of addressing different hydrological problems is the use of artificial neural networks (ANN). In groundwater management ANNs are usually used to predict the hydraulic head at a well location. ANNs can prove to be very useful because, unlike numerical groundwater models, they are very easy to implement in karstic regions without the need of explicit knowledge of the exact flow conduit geometry and they avoid the creation of extremely complex models in the rare cases when all the necessary information is available. With hydrological parameters like rainfall and temperature, as well as with hydrogeological parameters like pumping rates from nearby wells as input, the ANN applies a black box approach and yields the simulated hydraulic head. During the calibration process the network is trained using a set of available field data and its performance is evaluated with a different set. Available measured data from Edward??s aquifer in Texas, USA are used in this work to train and evaluate the proposed ANN. The Edwards Aquifer is a unique groundwater system and one of the most prolific artesian aquifers in the world. The present work focuses on simulation of hydraulic head change at an observation well in the area. The adopted ANN is a classic fully connected multilayer perceptron, with two hidden layers. All input parameters are directly or indirectly connected to the aquatic equilibrium and the ANN is treated as a sophisticated analogue to empirical models of the past. A correlation analysis of the measured data is used to determine the time lag between the current day and the day used for input of the measured rainfall levels. After the calibration process the testing data were used in order to check the ability of the ANN to interpolate or extrapolate in other regions, not used in the training procedure. The results show that there is a need for exact knowledge of pumping from each well in karstic aquifers as it is difficult to simulate the sudden drops and rises, which in this case can be more than 6 ft (approx. 2 m). That aside, the ANN is still a useful way to simulate karstic aquifers that are difficult to be simulated by numerical groundwater models.     

软基沉降预测模型的比较分析与应用

公路软基沉降预测是目前高速发展的软土地区公路建设中亟待解决的一大技术难题,预测模型也有多种,预测精度不尽相同。对工程中基于经验公式法预测沉降的传统模型(指数模型、双曲线模型)和成长曲线模型(Logistic模型、Gompertz模型、Weibull模型)给予介绍,并分别对各模型进行了数学比较分析。结果表明:传统模型不能利用施工期间的观测数据,只能用工后资料预测工后沉降,且对工后资料的要求较高;成长曲线模型能较好的反映沉降全过程的变化规律。Weibull模型较其它两种成长模型有较广泛的适应性,其对沉降的预测与实际吻合较好。     

Artificial Neural Network Modeling for Groundwater Level Forecasting in a River Island of Eastern India

Forecasting of groundwater levels is very useful for planning integrated management of groundwater and surface water resources in a basin. In the present study, artificial neural network models have been developed for groundwater level forecasting in a river island of tropical humid region, eastern India. ANN modeling was carried out to predict groundwater levels 1 week ahead at 18 sites over the study area. The inputs to the ANN models consisted of weekly rainfall, pan evaporation, river stage, water level in the drain, pumping rate and groundwater level in the previous week, which led to 40 input nodes and 18 output nodes. Three different ANN training algorithms, viz., gradient descent with momentum and adaptive learning rate backpropagation (GDX) algorithm, Levenberg–Marquardt (LM) algorithm and Bayesian regularization (BR) algorithm were employed and their performance was evaluated. As the neural network became very large with 40 input nodes and 18 output nodes, the LM and BR algorithms took too much time to complete a single iteration. Consequently, the study area was divided into three clusters and the performance evaluation of the three ANN training algorithms was done separately for all the clusters. The performance of all the three ANN training algorithms in predicting groundwater levels over the study area was found to be almost equally good. However, the performance of the BR algorithm was found slightly superior to that of the GDX and LM algorithms. The ANN model trained with BR algorithm was further used for predicting groundwater levels 2, 3 and 4 weeks ahead in the tubewells of one cluster using the same inputs. It was found that though the accuracy of predicted groundwater levels generally decreases with an increase in the lead time, the predicted groundwater levels are reasonable for the larger lead times as well.     

Estimation of the Change in Lake Water Level by Artificial Intelligence Methods

In this study, five different artificial intelligence methods, including Artificial Neural Networks based on Particle Swarm Optimization (PSO-ANN), Support Vector Regression (SVR), Multi- Layer Artificial Neural Networks (MLP), Radial Basis Neural Networks (RBNN) and Adaptive Network Based Fuzzy Inference System (ANFIS), were used to estimate monthly water level change in Lake Beysehir. By using different input combinations consisting of monthly Inflow - Lost flow (I), Precipitation (P), Evaporation (E) and Outflow (O), efforts were made to estimate the change in water level (L). Performance of models established was evaluated using root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R²). According to the results of models, ε-SVR model was obtained as the most successful model to estimate monthly water level of Lake Beysehir.     

A Novel Method to Water Level Prediction using RBF and FFA

Water Resources Management - Water level prediction of rivers, especially in flood prone countries, can be helpful to reduce losses from flooding. A precise prediction method can issue a...     

基于多元回归分析的宝鸡市区地下水位动态预报

在简要介绍回归模型的建立、求解及检验的基础上,以1990年~2007年宝鸡市区年降水量、年开采量和天然河道渗漏量作为自变量,宝鸡市地下水水位埋深为因变量,建立了宝鸡市区地下水位动态预报模型。通过对2008年的地下水位埋深进行预测,精度较为理想;并应用F检验法、相关系数r的评价和p值检验法对模型进行检验,结果表明所建立的模型能够反映因变量与自变量的线性关系,因而,可以应用于宝鸡市区地下水位动态预报。     

A New Method for Pore Pressure Prediction on Malfunctioning Cells Using Artificial Neural Networks

Embankment rockfill dams are the most common dam construction types used in the world today. One third of all embankment dam failures are caused by dam slope instability. The dam is stable when the slopes are stable. Slope safety of the dam is assessed through pore and total pressure data analysis registered on pressure measurement cells installed in the dam. During the service life of a dam, one or more cells may malfunction after years of operation. Cell replacement implies economically unjustified high costs and is usually technically impossible and high risk. In this paper, the problem of a malfunctioning cell with a small available dataset is analysed. A new method for pore pressure prediction on malfunctioning cells has been developed using several successive artificial neural networks (ANNs) to obtain high accuracy of the predicted values. The results show that these predicted values are more precise than values we could have obtained using only one artificial neural network for prediction.

     

A GIS Based Design of Groundwater Level Monitoring Network Using Multi-Criteria Analysis and Geostatistical Method

Groundwater systems are dynamic and hence, an effective and optimally designed groundwater level (GWL) monitoring network is very essential to minimize monitoring, time and long term expenses. Groundwater scarcity is a big challenge in regions where excessive extraction takes place and GWL monitoring from observation wells (OWs) is the principal source of information. Hence, proper observation and management is necessary to ensure continual availability of water supplies. This study proposes a new and simplified approach using multi-criteria analysis (weighted overlay, analytical hierarchical process, fuzzy) and geostatistical (ordinary kriging) method to design GWL monitoring network of the Wainganga sub-basin, India. Several parameters considered for the analysis include command area (CA) and non command area (NCA), geology, geomorphologic unit, land use/land cover (LU/LC), lineament density, Groundwater level fluctuation (GWLF), recharge, slope and soil media. The study identifies representative or priority zones using multi-criteria analysis and optimum number of OW was determined within the representative zones using geostatistical method. Combination of two approaches helps overcome shortcomings of previously suggested methods of which analytical hierarchical process (AHP)-geostatistical approach gives more accurate results. Sensitivity analysis was carried out to identify importance of each parameter considered for analysis. The study concludes that minimum 80 wells are required for proper monitoring of GWL in the study area. It also reveals that a combination of these two approaches is effective and easy to implement in the regions where data availability is not constrained.     

Optimum Abstraction of Groundwater for Sustaining Groundwater Level and Reducing Irrigation Cost

Adaptation to increasing irrigation cost due to declination of groundwater level is a major challenge in groundwater dependent irrigated region. The objective of this study is to estimate the optimum abstraction of groundwater for irrigation for sustainable management of groundwater resources in Northwest Bangladesh. A data-driven model using a support vector machine (SVM) has been developed to estimate the optimum abstraction of groundwater for irrigation and a multiple-linear regression (MLR)-based model has been developed to estimate the reduction of the irrigation cost due to the elevation of the groundwater level. The application of the SVM model revealed that the groundwater level in the area can be kept within the suction lift of a shallow tube-well by reducing pre-monsoon groundwater-dependent irrigated agriculture by 40%. Adaptive measures, such as reducing the overuse of water for irrigation and rescheduling harvesting, can keep the minimum level of groundwater within the reach of shallow tube-wells by reducing only 10% of groundwater-based irrigated agriculture. The elevation of the groundwater level through those adaptive measures can reduce the irrigation cost by 2.07 × 10³ Bangladesh Taka (BDT) per hectare in Northwest Bangladesh, where the crop production cost is increasing due to the decline of the groundwater level. It is expected that the study would help in policy planning for the sustainable management of groundwater resources in the region.