基于CEEMD-RF模型的渣土边坡地下水埋深预测

地下水是影响渣土边坡稳定性的关键因素之一,地下水埋深预测对分析渣土边坡稳定性具有重要意义。考虑渣土边坡地下水水位的高度非平稳和非线性特点,提出了一种基于相空间重构的互补集合经验模态分解-随机森林（CEEMD-RF）的地下水埋深预测模型。以广州市某渣土边坡SW2水文观测孔为例,将基于相空间重构的CEEMD-RF模型应用于该渣土边坡的地下水埋深预测,并与相空间重构的RF模型预测结果进行对比分析。结果表明:利用CEEMD-RF模型对地下水埋深预测的拟合优度为0.997,均方根误差为0.03 m,优于相空间重构的RF模型预测结果;基于相空间重构的CEEMD-RF模型预测的地下水埋深序列能很好地反映地下水埋深的尖变点。     

Groundwater Level Forecast Via a Discrete Space-State Modelling Approach as a Surrogate to Complex Groundwater Simulation Modelling

Reliable and precise forecasts of future groundwater level fluctuations are crucial constituents of sustainable management of scarce water resources and design of remediation plans. Groundwater simulations and predictions are often performed by employing physically based models, which are not applicable in a majority of water scarce areas around the globe, particularly in the developing countries like Bangladesh due to data limitations. On the other hand, data-driven statistical forecast models have demonstrated their suitability to model nonlinear and complex hydrogeological processes to forecast short- and long-term groundwater level fluctuations. The purpose of this effort is to propose a non-physical based approach by utilizing a discrete Space-State model as a prediction tool to forecast future scenarios of groundwater level fluctuations. The present study utilizes the prediction focused approach of the system identification process in which the overall objective is to develop a pragmatic dynamic system model. The performance of the proposed approach is evaluated for groundwater level data at three observation wells of Tanore upazilla in Rajshahi district, Bangladesh. Historical weekly time series data of groundwater level fluctuations from the three observation wells for 39 (1980–2018) years is used to develop the time series model, which is used for future groundwater level predictions for a period of next 22 years (up to 2040). The findings demonstrate the conceivable applicability of the proposed discrete Space-State modelling approach in forecasting future scenarios of groundwater level fluctuations in the selected observation wells.

     

Application of New Hybrid Optimization Technique for Parameter Estimation of New Improved Version of Muskingum Model

The Muskingum method is one of the most utilized lumped flood routing model in which calibration of its parameters provides an active area of research in water resources engineering. Although various techniques and versions of Muskingum model have been presented to estimate the parameters of different versions of Muskingum model, more rigorous approaches and models are still required to improve the computational precision of calibration process. In this study, a new hybrid technique was proposed for Muskingum parameter estimation which combines the Modified Honey Bee Mating Optimization (MHBMO) and Generalized Reduced Gradient (GRG) algorithms. According to the conducted literature-review on the improvement of Muskingum flood routing models, a new six-parameter Muskingum model was proposed. The hybrid technique was successfully applied for parameter estimation of this new version of Muskingum model for three case studies selected from literature. The obtained results were compared with those of other methods using several common performance evaluation criteria. The new hybrid method with the new proposed Muskingum model perform the best among all the considered approaches based on most of utilized criteria. The new Muskingum model significantly reduces the SSQ value for the double-peak case study. Finally, the achieved results demonstrate that not only the hybrid MHBMO-GRG algorithm overcomes the shortcomings of both phenomenon-mimicking and mathematical optimization techniques, but also the presented Muskingum model is appeared to be the most reliable version of Muskingum model comparing with other considered models in this research.     

A Probabilistic Nonlinear Model for Forecasting Daily Water Level in Reservoir

Accurate prediction and monitoring of water level in reservoirs is an important task for the planning, designing, and construction of river-shore structures, and in taking decisions regarding irrigation management and domestic water supply. In this work, a novel probabilistic nonlinear approach based on a hybrid Bayesian network model with exponential residual correction has been proposed for prediction of reservoir water level on daily basis. The proposed approach has been implemented for forecasting daily water levels of Mayurakshi reservoir (Jharkhand, India), using a historic data set of 22 years. A comparative study has also been carried out with linear model (ARIMA) and nonlinear approaches (ANN, standard Bayesian network (BN)) in terms of various performance measures. The proposed approach is comparable with the observed values on every aspect of prediction, and can be applied in case of scarce data, particularly when forcing parameters such as precipitation and other meteorological data are not available.     

基于PSR和PSO的区域地下水埋深ELM预测模型

针对传统区域地下水埋深预测方法精度不高问题,提出一种基于相空间重构(PSR)、粒子群算法(PSO)的极限学习机(ELM)的非线性预测模型。首先利用C-C法对地下水埋深原始时序数据进行相空间重构(PSR),然后利用PSO-ELM对地下水埋深进行预测。将模型应用于中国黑龙江省红兴隆管理局红旗岭农场地下水埋深预测,结果表明:该模型取得了较好的预测效果,后验差比值C为0.074,小误差频率p为1,相对均方误差E1为6.36%,拟合准确率E2达到92.66%,试预报效果指标E3达到95.80%;与PSR-ELM、PSR-RBF等模型相比,PSR-PSO-ELM在试预报方面可使RMSE分别降低49%和70%,使误差区间分别降低28.2%和68.6%,证明PSO能够有效改善ELM模型的预测性能;分析了气候因素和人类活动对当地地下水埋深动态变化的影响。     

渭北旱塬区典型测井地下水埋深的灰色预测研究

地下水埋深变化是地下水系统动态变化最主要的表现形式之一,通过预测地下水埋深分析地下水系统未来演变趋势,对合理开发、持续利用地下水资源有着重要的现实意义。本文选取2000-2010年渭北旱塬区的两个典型监测井的地下水埋深数据,用灰色GM(1,1)理论建立预测模型,并对该监测井的地下水埋深进行短期预测。经检验,该模型具有较高的预测精度,说明采用灰色理论预测渭北旱塬区监测井地下水埋深的方法可行。     

基于ARMA-GMDH的水利工程变形预测模型

变形监测数据是定量评价水利工程结构安全的重要依据.水利工程变形数据是一种典型的非平稳信号,同时包含线性成分与非线性成分.针对水利工程变形的线性成分和非线性成分特征,分别利用针对线性信号的自回归移动平均模型和非线性信号的数据分组处理方法,构建了一种基于ARMA-GMDH的组合预测模型对水利工程的变形进行预测.工程实例表明...     

基于EMD-LSTM耦合模型的趵突泉岩溶地下水水位预测应用

由于岩溶地下水具有强烈的非线性及非平稳波动特征,水位预测结果容易产生较大误差。针对岩溶地下水水位预测精度较差的问题,提出一种EMD-LSTM耦合模型,首先采用经验模态分解（EMD）将趵突泉岩溶地下水水位分解为5个分量（4个本征模函数项和1个残余项）,以此消除水位数据的非平稳波动性;同时构建长短期记忆（LSTM）神经网络模型,并将与地下水水位动态变化密切相关的降水量（表征含水层补给项）和月平均气温值、月最高气温值、月最低气温值、水汽压值（表征含水层排泄项）作为输入项分别对5个分量进行预测,最终将分量预测结果累加获得地下水水位预测值。结果表明：EMD能够显著消除岩溶地下水水位的非平稳波动特征;EMD-LSTM耦合模型可有效提高岩溶地下水水位的预测精度,其均方根误差相比于LSTM神经网络模型、ARIMA模型分别减小了27.86%和59.94%。总体来说,本文所提出的EMD-LSTM耦合模型具有较强的可靠性和稳定性,可为岩溶地下水水位的精确预测提供借鉴。     

基于高斯过程的混凝土强度预测

针对混凝土强度与其各种影响因素之间存在着复杂的高度非线性关系,传统方法难以准确地预测出混凝土的强度值,本文将具有参数自适应获得,对处理高维数非线性复杂问题具有良好适应性的高斯过程机器学习方法引入到混凝土强度预测领域,并提出相应的预测模型。通过实验数据验证表明,利用高斯过程机器学习模型预测混凝土强度是科学可行的,且预测精度高。利用该模型可以早期预测出混凝土28d的抗压强度,对提高和控制混凝土施工质量具有重要的实际意义。     

年径流预测的Shepard插值模型

年径流现象是多种因子综合作用的结果,各预测因子与年径流之间是复杂的非线性关系。目前提出的年径流预测模型大多用显式函数来表示,其具体的函数形式需随研究地区的不同而作相应的改变,求解这些函数一般较复杂。实际预测工作则常常是把本次年径流的预测因子值与当地年径流预测因子历史样本系列逐个进行比较分析,实践表明这种方法行之有效。为此,提出用Shepard插值方法构建年径流预测的新模型（SP模型）。实例研究的结果说明,SP模型简便、实用性强,可在径流中长期预测中广泛应用。     

地下水动态预测的自记忆性模型及其应用研究

地下水位动态变化是一个复杂的水文过程，准确地预测地下水位变化情况在水资源开发利用中有着重要意义。本文运用反演建模和自记忆性方程相结合的方法，建立了地下水位动态预测模型。实例表明，该模型具有简洁实用的优点，且有显著的拟合精度和预报准确率。     

基于克里金代理模型的富水砂砾石层深基坑地表沉降预测

针对沉降监控预测等大型深基坑施工风险控制难点,为确保工程及周边环境安全,解决基坑监测中的空白现象和揭示基坑开挖监测点后期的沉降趋势,引入克里金代理模型预测深基坑开挖的地表沉降变形规律。以长沙晚报大道地铁站深基坑为例,基于MATLAB编制的Kriging工具箱DACE,对监测到的数据进行前期处理,采用相应的非线性克里金代理模型计算分析了两个监测点的沉降变形值。通过现场实测数据对比,结果表明:预测结果能够满足工程要求,误差均在5%以内。随基坑开挖深度和监测数据样本量不断增加,相应计算结果的误差逐步降低,表明该方法是合理可行的,能够以监测点数据对基坑监测盲点进行模拟预测,相对准确地计算出沉降变形。研究成果为高地下水位区域基坑、隧洞工程安全施工提供科学依据。     

陕西省吴堡县岔上水源地地下水允许开采量评价

根据陕西省吴堡县岔上水源地水文地质条件,确定了研究范围和边界条件,建立了研究区水文地质概念模型和地下水二维非稳定流数学模型,利用基于有限差分法的Visual MODFLOW进行地下水流数值模拟计算。经过模型的识别和验证,获取可靠的水文地质参数,然后对水源地地下水资源进行定量评价。通过对比设计了9种开采方案,选取了最为合理的开采方案,最终得到岔上水源地平枯期允许开采量均为6 880m3/d。根据模型预报结果,水源地目前的设计开采量是可行的。研究结果为研究区地下水资源的合理开发利用提供了依据。     

Identification of Groundwater Contamination Sources Using Meshfree RPCM Simulation and Particle Swarm Optimization

In this study, a simulation-optimization (SO) model is presented by coupling a meshfree based simulator using radial point collocation method (RPCM) and particle swarm optimization (PSO) as optimizer to identify the unknown groundwater contaminant sources from the measured/simulated contaminant concentration data in the aquifer. To demonstrate the approach, two case studies have been presented. The first example is a hypothetical case which simulates the contaminant releases from several disposal sites in an aquifer during four years release period. The second case considered is a field study where leaching of contaminant, during their storage, from disposal sites at several locations in the aquifer leads to contamination of the groundwater. The goal in both cases was to reconstruct the contaminant release history from the disposal sites and their magnitudes from the given historical concentration data at a few observation wells in the aquifer. It was observed that the source identification model could reconstruct the release histories from the waste disposal sites in both the cases accurately. This study demonstrated that PSO based optimization model with a meshfree flow and transport simulator can be effectively used for groundwater contaminant source identification problems.     

小波-神经网络混合模型预测地下水水位

由于过量开采地下水,华北平原的许多城市出现地下水水位持续下降趋势,由此导致了许多严重的环境问题,如地下水枯竭、地面沉降和海水入侵等。为了准确预测城市地下水水位变化,利用小波变换的多尺度分析特征,建立了小波-神经网络混合模型(以下简称"混合模型"),并研究了其在地下水水位预测中的精度。利用北京市平谷区地下水水位观测资料,分别用BP网络和混合模型对该区地下水水位进行了预测。采用均方根误差(RMSE)、平均绝对误差(MAE)和线性相关系数(R)对模型预测的精度进行度量。预测结果表明:混合模型第1至第3个月的地下水水位平均绝对误差分别是0.535,0.598和0.634 m;而BP模型的平均绝对误差分别为0.566,0.824和0.940 m。混合模型的预测误差分别为BP模型的95%,73%和67%。使用混合模型能明显提高预测的精度,显著增加有效预测时段长度。     

基于MODFLOW的地下水Cr(VI)污染水动力场模拟预测研究

随着社会和经济的快速发展,我国地下水污染问题已日益突出,地下水中Cr(Ⅵ)的污染已成为危害环境和人类健康的危险物质.由于Cr(Ⅵ)的毒性高、易迁移等特点,给地下水环境带来严重的安全隐患.在对某市城区水文地质及工程地质条件进行分析的基础上,依据2005年的资料用Visual Modflow进行参数率定,确定水文地质参数,建立了第四系地下水系统准三维非稳定流模型;再用2005-2009年的资料验证了模型的可靠性,利用此模型进行地下水流场模拟预测,并将现状条件下(2010年)Cr(Ⅵ)污染晕与预测的地下水流场形态进行叠加来预测Cr(Ⅵ)污染晕的发展趋势,为今后当地政府部门应对Cr(Ⅵ)污染地下水治理提供相关政策建议与决策参考,具有重要意义.     

地下水补给影响下的河流水质模糊模拟

摘 要：基于河流水环境系统的模糊性、不精确性，采用三角模糊数描述和表征沿岸地下水水文地质参数，建立了计算地下水补给量和补给强度的模糊模型。在将水质模型参数定义为三角模糊数的基础上，构建了考虑地下水补给影响的一维稳态河流水质模糊模拟模型。作为案例，将上述模型应用于淮河流域某支流水质模拟研究。采用-截集技术，计算得到各控制断面模糊数形式的污染物浓度值，并与确定性模型计算结果进行比较。实例研究表明，以三角模糊数原理模拟和表征考虑地下水补给影响的河流水体污染物浓度变化规律，理论上可行，计算结果可信，较好地弥补了传统确定性模型的不足。     

Optimal Operation of Artificial Groundwater Recharge Systems Considering Water Quality Transformations

In water limited areas as water demand increases alternative sustainable water sources must be identified. One supply augmentation practice, that is already being applied in the arid southwest U.S., is artificial groundwater recharge usingwastewater effluent. The objective of a recharge facility is to supplement the available groundwater resources by storing water for the future. The resulting reclaimed water is used primarily for non-potable purposes but under increasing stressesshifting to potable use is likely to happen. Water quality thenbecomes a more pressing concern. Water quality improvements during infiltration and groundwater transport are significant and are collectively described as soil-aquifer treatment (SAT). To meet user needs, the recharge operation must be efficiently managed considering monetary, water quality and environmental concerns. In this paper, a SAT management model is developed that considers all of these concerns. Within the SAT management model, the shuffled complex evolution algorithm (SCE) is used as the optimization tool. SCEis a relatively new meta-heuristic search technique for continuousproblems that has been used extensively for hydrologic model calibration. In this application, SCE is integrated with the simulation models (MODFLOW, MT3D, and MODPATH) to represent movement and quality transformations. Two steady state case studies on a general hypothetical aquifer (modeled after a field site) were examined using the management model.     

砂砾石地基上水闸底板弯矩预测的多元非线性回归模型

为了简捷地确定初步设计阶段水闸结构设计参数,加快设计进度,综合考虑砂砾石地基的弹性模量、闸墩荷载、闸孔宽度、底板厚度、闸墩高度、地基厚度等影响底板应力的主要因素,通过大量的有限元计算,分析了水闸参数对底板弯矩的影响规律,建立了基于多元非线性回归的底板中心弯矩预测模型。结果表明:底板中心弯矩与底板厚度、闸孔宽度、砂砾石地基厚度呈非线性关系,与闸墩高度总体呈线性关系;所建立的预测模型拟合效果较好,预测精度较高。     

A Framework for Ground Water Management Based on Bayesian Network and MCDM Techniques

Groundwater resources are steadily subjected to increasing water demands. The aquifers are considered as the most accessible source of fresh water. In recent years, they have been faced with severe water withdrawal in arid and semi-arid countries like Iran and thus some aquifers was considered as forbidden aquifers that it means the water withdrawal from these aquifers is unauthorized. Given a critical situation, groundwater resources management in the form of tools such as monitoring the level of the aquifers and developing the restoring scenarios is essential. Therefore, for this purpose, a framework has been developed based on prediction of groundwater level using Bayesian Networks (BNs) model. Furthermore, Multi Criteria Decision Making methods (MCDM) techniques proposed and employed for ranking of proposed groundwater management scenarios. This framework was evaluated for restoring the Birjand aquifer in Iran in different hydrological conditions. A probabilistic Dynamic BN was proposed for groundwater level prediction under uncertainties. After analyzing the obtained results, the applicable short term scenarios for groundwater management as well as appropriate economic, social and technical criteria were defined for decision making procedure. Then, using elicitation of decision makers’ opinions on the relative importance and performance of criteria, SAW, TOPSIS and PROMETHEE-II techniques were applied to rank the scenarios and the obtained results were aggregated by Borda method for final ranking of the scenarios. Lastly, the final results demonstrates the capability of the proposed framework for groundwater resources planning and management which can be employed for reducing the risk of aquifer level declining.