Modeling of Sediment Yield Prediction Using M5 Model Tree Algorithm and Wavelet Regression

The forecast of the sediment yield generated within a watershed is an important input in the water resources planning and management. The methods for the estimation of sediment yield based on the properties of flow and sediment have limitations attributed to the simplification of important parameters and boundary conditions. Under such circumstances, soft computing approaches have proven to be an efficient tool in modelling the sediment yield. The focus of present study is to deal with the development of decision tree based M5 Model Tree and wavelet regression models for modeling sediment yield in Nagwa watershed in India. A comparison is also performed with the artificial neural network (ANN) model for streamflow forecasting. The root mean square errors (RMSE), Nash-Sutcliff efficiency index (N-S Index), and correlation coefficient (R) statistics are used for the statistical criteria. A comparative evaluation of the performance of M5 Model Tree and wavelet regression versus ANN clearly shows that M5 Model Tree and wavelet regression can prove more useful than ANN models in estimation of sediment yield. Further, M5 model tree offers explicit expressions for use by design engineers.     

Modeling Nonlinear Monthly Evapotranspiration Using Soft Computing and Data Reconstruction Techniques

The objective of this study is to develop soft computing and data reconstruction techniques for modeling monthly California Irrigation Management Information System (CIMIS) evapotranspiration (ET_o) at two stations, U.C. Riverside and Durham, in California. The nonlinear dynamics of monthly CIMIS ET_o is examined using autocorrelation function, phase space reconstruction, and close returns plot. The generalized regression neural networks and genetic algorithm (GRNN-GA) conjunction model is developed for modeling monthly CIMIS ET_o. Among different input variables considered, solar radiation (RAD) is found to be the most effective variable for modeling monthly CIMIS ET_o using GRNN-GA for both stations. Adding other input variables to the best 1-input combination improves the model performance. The generalized regression neural networks and backpropagation algorithm (GRNN-BP) conjunction model is compared with the results of GRNN-GA for modeling monthly CIMIS ET_o. Two bootstrap resampling methods are implemented to reconstruct the training data. Method 1 (1-BGRNN-GA) employs simple extensions of training data using the bootstrap resampling method. For each training data, method 2 (2-BGRNN-GA) uses individual bootstrap resampling of original training data. Results indicate that Method 2 (2-BGRNN-GA) improves modeling of monthly CIMIS ET_o and is more stable and reliable than are GRNN-GA, GRNN-BP, and Method 1 (1-BGRNN-GA).     

Quadratic Discriminant Analysis Based Ensemble Machine Learning Models for Groundwater Potential Modeling and Mapping

In this study, the AdaBoost, MultiBoost and RealAdaBoost methods were combined with the Quadratic Discriminant Analysis method to develop three new GIS-based Machine Learning ensemble models, i.e., ABQDA, MBQDA, and RABQDA for groundwater potential mapping in the Dak Nong Province, Vietnam. In total, 227 groundwater wells and 12 conditioning factors (infiltration, rainfall, river density, topographic wetness index, sediment transport index, stream power index, elevation, aspect, curvature, slope, soil, and land use) were used for this study. Performance of the models was evaluated using the Area Under the Receiver Operating Characteristics Curve AUC (AUC) and several other performance metrics. The results showed that the ABQDA model that achieved AUC?=?0.741 was superior to the other models in producing an accurate map of groundwater potential for the Dak Nong Province. The models and potential maps produced here can help policymakers and water resources managers to preserve an optimal exploit from these vital resources.

     

基于决策树算法的洪水预报模型

结合现有决策树技术的研究结果,在已有决策树方法的基础上,从积累的大量数据资料和信息反馈形成的水文相关数据库出发,基于决策树C4.5算法设计合理的计算流程来建立了洪水预报模型,并以预报太湖水位为例进行了实例研究.结果表明,基于决策树的洪水预报模型结构清晰,最终生成的预报规则简单明了,模型在率定期与检验期内均具有很高的精度...     

机器学习算法在大坝安全监控系统中的集成方法

为方便在大坝安全监控系统中灵活应用新型机器学习算法,提出了一种应用组件对象模型(COM)技术将机器学习算法集成到大坝安全监控系统中的方法,相比于在开发系统中直接对机器学习算法进行编程,该方法可节省大量的编程时间,缩短开发周期,效果较好.     

Failure Prediction of Municipal Water Pipes Using Machine Learning Algorithms

Pipe failure prediction has become a crucial demand of operators in daily operation and asset management due to the increase in operation risks of water distribution networks. In this paper, two machine learning algorithms, namely, random forest (RF) and logistic regression (LR) algorithms are employed for pipe failure prediction. RF algorithm consists of a group of decision trees that predicts pipe failure independently and makes the final decision by voting together. For the LR algorithm, the mapping relationship between existing data and decision variables is expressed by the logistic function. Then, the prediction is made by comparing the conditional probability with the fixed threshold value. The proposed algorithms are illustrated using an actual water distribution network in China. Results indicate that the RF algorithm performs better than the LR algorithm in terms of accuracy, recall, and area under the receiver operating characteristic curve. The effects of seven characteristics on pipe failures are analyzed, and diameter and length are identified as the top two influential factors.

Graphical Abstract

     

基于互补相关的乌江流域实际蒸散量分布式模拟

为了提高气候变化下估算乌江流域陆面实际蒸散量的精度,利用乌江流域气象和水文数据,在蒸散互补原理基础上建立用常规气象资料估算流域实际蒸散量的模型。模拟结果显示:该模型能将乌江流域多年平均实际蒸散量的相对误差控制在5%以内;在充分考虑地形起伏等下垫面不均匀的条件下,将估算模型中各分量的分布式模拟结果与估算模型耦合,实现了乌江流域实际蒸散量的分布式模拟;该模型更加精细地表现了流域实际蒸散量的空间变化情况,发现其在空间分布上呈显著的西高东低的分布趋势;在时间变化上,1961-2010年间乌江流域实际蒸散量在总体上表现为下降趋势,降幅为5.08 mm/(10 a),但是2000年以后实际蒸散量有较为明显的上升趋势;日照时数及相对湿度的上升是造成实际蒸散量产生以上变化的主要原因。研究结果可为水资源评价、农业气候区划制定等提供参考。     

Evaluating Different Machine Learning Models for Runoff and Suspended Sediment Simulation

Water Resources Management - In the present study, prediction of runoff and sediment at Polavaram and Pathagudem sites of the Godavari basin was carried out using machine learning models such as...     

Forecasting Daily Flood Water Level Using Hybrid Advanced Machine Learning Based Time-Varying Filtered Empirical Mode Decomposition Approach

Water Resources Management - Accurate water level forecasting is important to understand and provide an early warning of flood risk and discharge. It is also crucial for many plants and animal...     

River Stage Forecasting Using Wavelet Packet Decomposition and Machine Learning Models

Water Resources Management - This study develops and applies three hybrid models, including wavelet packet-artificial neural network (WPANN), wavelet packet-adaptive neuro-fuzzy inference system...     

基于极限学习机的边坡可靠度分析

对于边坡极限状态函数无法显式表达的情况,传统可靠度分析方法存在求解困难或计算量大的弊端。提出了一种基于FLAC^3D和极限学习机的边坡可靠度分析方法。利用均匀试验设计构造随机变量样本,基于FLAC^3D强度折减法计算随机变量样本对应的安全系数;通过极限学习机强大的数据拟合能力映射出安全系数与随机变量之间的关系,构造响应面功能函数;将蒙特卡罗模拟生成的大量随机数代入响应面获得安全系数,在此基础上,计算边坡的失效概率与可靠度指标。通过具体算例分析,并与其他方法对比,发现本文方法结果可靠、易于实现,为边坡可靠度分析提供了一种新途径,具有广泛的应用前景。     

Using Optimized Deep Learning to Predict Daily Streamflow: A Comparison to Common Machine Learning Algorithms

From a watershed management perspective, streamflow need to be predicted accurately using simple, reliable, and cost-effective tools. Present study demonstrates the first applications of a novel optimized deep-learning algorithm of a convolutional neural network (CNN) using BAT metaheuristic algorithm (i.e., CNN-BAT). Using the prediction powers of 4 well-known algorithms as benchmarks – multilayer perceptron (MLP-BAT), adaptive neuro-fuzzy inference system (ANFIS-BAT), support vector regression (SVR-BAT) and random forest (RF-BAT), the CNN-BAT model is tested for daily streamflow (Q_t) prediction in the Korkorsar catchment in northern Iran. Fifteen years of daily rainfall (R_t) and streamflow data from 1997 to 2012 were collected and used for model development and evaluation. The dataset was divided into two groups for building and testing models. The correlation coefficient (r) between rainfall and streamflow with and without antecedent events (i.e., R_t-1, R_t-2, etc.) (as the input variables) and Q_t (as the output variable) served as the basis for constructing different input scenarios. Several quantitative and visually-based evaluation metrics were used to validate and compare the model’s performance. The results indicate that R_t was the most effective input variable on Q_t prediction and the integration of R_t, R_t-1, and Q_t-1 was the optimal input combination. The evaluation metrics show that the CNN-BAT algorithm outperforms the other algorithms. The Friedman and Wilcoxon signed-rank test indicates that the prediction power of CNN-BAT algorithm is significantly/statistically different from the other developed algorithms.

     

Performance Evaluation of Reference Evapotranspiration Estimation Using Climate Based Methods and Artificial Neural Networks

This study is an attempt to find best alternative method to estimate reference evapotranspiration (ET_o) for the Mahanadi reservoir project (MRP) command area located at Raipur (Chhattisgarh) in India, when input climatic parameters are insufficient to apply standard Food and Agriculture Organization (FAO) of the United Nations Penman–Monteith (P–M) method. To identify the best alternative climatic based method that yield results closest to the P–M method, performances of four climate based methods namely Blaney–Criddle, Radiation, Modified Penman and Pan evaporation were compared with the FAO-56 Penman–Monteith method. Performances were evaluated using the statistical indices. The statistical indices used in the analysis were the standard error of estimate (SEE), raw standard error of estimate (RSEE) and the model efficiency. Study was extended to identify the ability of Artificial Neural Networks (ANNs) for estimation of ET_o in comparison to climatic based methods. The networks, using varied input combinations of climatic variables have been trained using the backpropagation with variable learning rate training algorithm. ANN models were performed better than the climatic based methods in all performance indices. The analyses of results of ANN model suggest that the ET_o can be estimated from maximum and minimum temperature using ANN approach in MPR area.     

基于机器学习模型的福州地区滑坡易发性评价

开展滑坡易发性评价是开展区域地质灾害风险管理的基础性工作,以福州主要陆域区为对象,基于植被覆盖度、高程、坡度、坡向、岩性、距断裂距离和距水系距离共7个影响因子,采用逻辑回归模型和随机森林模型进行滑坡易发性评价,并将模型评价结果分为低、较低、中、较高和高共5个易发性等级区划。研究表明,随机森林模型满足较高和高风险区的面积小、区内滑坡密度大的预测模型评判标准,预测精度更高且泛化能力更好,从而验证研究区基于机器学习模型的滑坡易发性评价的可行性;研究还表明植被覆盖度和高程是研究区滑坡易发性评价的高重要性影响因子,而坡向是最低重要性的影响因子,可以为该区域滑坡灾害风险评估的信息获取提供参考。     

Probabilistic Event Based Rainfall-Runoff Modeling Using Copula Functions

Multivariate probability analysis of hydrological elements using copula functions can significantly improve the modeling of complex phenomena by considering several dependent variables simultaneously. The main objectives of this study were to: (i) develop a stand-alone and event-based rainfall-runoff (RR) model using the common bivariate copula functions (i.e. the BCRR model); (ii) improve the structure of the developed copula-based RR model by using a trivariate version of fully-nested Archimedean copulas (i.e. the FCRR model); and (iii) compare the performance of the developed copula-based RR models in an Iranian watershed. Results showed that both of the developed models had acceptable performance. However, the FCRR model outperformed the BCRR model and provided more reliable estimations, especially for lower joint probabilities. For example, when joint probabilities were increased from 0.5 to 0.8 for the peak discharge (q_p) variable, the reliability criteria value increased from 0.0039 to 0.8000 in the FCRR model, but only from 0.0010 to 0.6400 in the BCRR model. This is likely because the FCRR considers more than one rainfall predictor, while the BCRR considers only one.

     

Pan Evaporation Modeling Using Neural Computing Approach for Different Climatic Zones

The purpose of this study was to develop and apply the neural networks models to estimate daily pan evaporation (PE) for different climatic zones such as temperate and arid climatic zones, Republic of Korea and Iran. Three kinds of the neural networks models, namely multilayer perceptron-neural networks model (MLP-NNM), generalized regression neural networks model (GRNNM), and support vector machine-neural networks model (SVM-NNM), were used to estimate daily PE. The available climatic variables, consisted of mean air temperature (T_mean), mean wind speed (U_mean), sunshine duration (SD), mean relative humidity (RH_mean), and extraterrestrial radiation (R_a) were used to estimate daily PE using the various input combinations of climate variables. The measurements for the period of January 1985?CDecember 1990 (Republic of Korea) and January 2002?CDecember 2008 (Iran) were used for training and testing the employed neural networks models. The results obtained by SVM-NNM indicated that it performs better than MLP-NNM and GRNNM for estimating daily PE. A comparison was also made among the employed models, which demonstrated the superiority of MLP-NNM, GRNNM, and SVM-NNM over Linacre model and multiple linear regression model (MLRM).     

Prediction of Water-Level in the Urmia Lake Using the Extreme Learning Machine Approach

Predicting the dynamics of water-level in lakes plays a vital role in navigation, water resources planning and catchment management. In this paper, the Extreme Learning Machine (ELM) approach was used to predict the daily water-level in the Urmia Lake. Daily water-level data from the Urmia Lake in northwest of Iran were used to train, test and validate the employed models. Results showed that the ELM approach can accurately forecast the water-level in the Urmia Lake. Outcomes from the ELM model were also compared with those of genetic programming (GP) and artificial neural networks (ANNs). It was found that the ELM technique outperforms GP and ANN in predicting water-level in the Urmia Lake. It also can learn the relation between the water-level and its influential variables much faster than the GP and ANN. Overall, the results show that the ELM approach can be used to predict dynamics of water-level in lakes.     

Sustainable Conjunctive Water Use Modeling Using Dual Fitness Particle Swarm Optimization Algorithm

Water Resources Management - In any meta-heuristic algorithm, each search agent must move to the high-fitness areas in the search space while preserving its diversity. At first glance, there is no...     

Layout and Component Size Optimization of Sewer Network Using Spanning Tree and Modified PSO Algorithm

In the paper, a new method is introduced for optimally solve the problem of the layout and component size determination of sewer network. Simultaneously Layout and component size optimization of sewer network problem consists of many hydraulic constraints which are generally nonlinear and discrete; which creates a challenge even to the modern heuristic search methods. An algorithm generation of a predefined number of spanning trees is introduced to generate a predefined number of sewer layouts of a base sewer network in order of increasing length. These generated layouts are sorted in ascending order of total cumulative flow and sorted layouts are individually optimized for sewer components sizing. It has been found that the optimal sewer layout for total system optimization is one where the total cumulative flow has the minimal value. The modified particle swarm optimization (MPSO) algorithm has been used to optimally determine the component sizes of the selected layouts. The proposed method is applied to the Sudarshanpura sewer network (situated in Jaipur, India) design problem. The results are presented for optimal cost vs cumulative flow of the layouts. Further results of MPSO has been compared with the original PSO algorithm.