Wenxi Lu

Monthly Rainfall Forecasting Using EEMD-SVR Based on Phase-Space Reconstruction

Rainfall links atmospheric and surficial processes and is one of the most important hydrologic variables. We apply support vector regression (SVR), which has a high generalization capability, to construct a rainfall forecasting model. Before construction of the model, a self-adaptive data analysis methodology called ensemble empirical mode decomposition (EEMD) is used to preprocess a rainfall data series. In addition, the phase-space reconstruction method is implemented to design input vectors for the forecasting model. The proposed hybrid model is applied to forecast the monthly rainfall at a weather station in Changchun, China as a case study. To demonstrate the capacity of the proposed hybrid model, a typical three-layer feed-forward artificial neural network model, an auto-regressive integrated moving average model, and a support vector regression model are constructed. Predictive performance of the models is evaluated based on normalized mean squared error (NMSE), mean absolute percent error (MAPE), Nash–Sutcliffe efficiency (NSE), and the coefficient of correlation (CC). Results indicate that the proposed hybrid model has the lowest NMSE and MAPE values of 0.10 and 14.90, respectively, and the highest NSE and CC values of 0.91 and 0.83, respectively, during the validation period. We conclude that the proposed hybrid model is feasible for monthly rainfall forecast and is better than the models currently in common use.

Surrogate model application to the identification of an optimal surfactant-enhanced aquifer remediation strategy for DNAPL-contaminated sites

A surrogate model is introduced for identifying the optimal remediation strategy for Dense Non-Aqueous Phase Liquids (DNAPL)-contaminated aquifers. A Latin hypercube sampling (LHS) method was used to collect data in the feasible region for input variables. A surrogate model of the multi-phase flow simulation model was developed using a radial basis function artificial neural network (RBFANN). The developed model was applied to a perchloroethylene (PCE)-contaminated aquifer remediation optimization problem. The relative errors of the average PCE removal rates between the surrogate model and simulation model for 10 validation samples were lower than 5%, which is high approximation accuracy. A comparison of the surrogate-based simulation optimization model and a conventional simulation optimization model indicated that RBFANN surrogate model developed in this paper considerably reduced the computational burden of simulation optimization processes.

Ecological Compensation Estimation of Soil and Water Conservation Based on Cost-Benefit Analysis

Soil and water conservation ecological compensation can be simply defined as a monetary payment to offset the environmental loss. An illustration is given in this study describing the payment compensation to water resource conservation and soil losses in Erlongshan reservoir catchment, China. A semi-distributed hydrological SWAT model was applied to establish compensation standard considering six scenarios of land use changes by combined application of remote sensing and geographic information systems. Cost-benefit analysis (CBA) method is applied to evaluate the function of soil and water conservation, of which marginal opportunity cost and market value methods have been explored calculate the cost and benefit of water and soil conservation ecological function from provider and beneficiaries. Finally the ecological compensation of soil and water conservation for different land-use scenarios is calculated incorporating benefit apportion coefficient. The results provide an economically evaluated and market-oriented standard for the study of eco-compensation of environmental services and will be of great benefit to the implementation of soil and water conservation at a mesoscale catchment scale.

Chance-constrained multi-objective optimization of groundwater remediation design at DNAPLs-contaminated sites using a multi-algorithm genetically adaptive method

In this paper, a multi-algorithm genetically adaptive multi-objective (AMALGAM) method is proposed as a multi-objective optimization solver. It was implemented in the multi-objective optimization of a groundwater remediation design at sites contaminated by dense non-aqueous phase liquids. In this study, there were two objectives: minimization of the total remediation cost, and minimization of the remediation time. A non-dominated sorting genetic algorithm II (NSGA-II) was adopted to compare with the proposed method. For efficiency, the time-consuming surfactant-enhanced aquifer remediation simulation model was replaced by a surrogate model constructed by a multi-gene genetic programming (MGGP) technique. Similarly, two other surrogate modeling methods-support vector regression (SVR) and Kriging (KRG)-were employed to make comparisons with MGGP. In addition, the surrogate-modeling uncertainty was incorporated in the optimization model by chance-constrained programming (CCP). The results showed that, for the problem considered in this study, (1) the solutions obtained by AMALGAM incurred less remediation cost and required less time than those of NSGA-II, indicating that AMALGAM outperformed NSGA-II. It was additionally shown that (2) the MGGP surrogate model was more accurate than SVR and KRG; and (3) the remediation cost and time increased with the confidence level, which can enable decision makers to make a suitable choice by considering the given budget, remediation time, and reliability.

Surrogate Model Application to the Identification of Optimal Groundwater Exploitation Scheme Based on Regression Kriging Method—A Case Study of Western Jilin Province

This paper introduces a surrogate model to identify an optimal exploitation scheme, while the western Jilin province was selected as the study area. A numerical simulation model of groundwater flow was established first, and four exploitation wells were set in the Tongyu county and Qian Gorlos county respectively so as to supply water to Daan county. Second, the Latin Hypercube Sampling (LHS) method was used to collect data in the feasible region for input variables. A surrogate model of the numerical simulation model of groundwater flow was developed using the regression kriging method. An optimization model was established to search an optimal groundwater exploitation scheme using the minimum average drawdown of groundwater table and the minimum cost of groundwater exploitation as multi-objective functions. Finally, the surrogate model was invoked by the optimization model in the process of solving the optimization problem. Results show that the relative error and root mean square error of the groundwater table drawdown between the simulation model and the surrogate model for 10 validation samples are both lower than 5%, which is a high approximation accuracy. The contrast between the surrogate-based simulation optimization model and the conventional simulation optimization model for solving the same optimization problem, shows the former only needs 5.5 hours, and the latter needs 25 days. The above results indicate that the surrogate model developed in this study could not only considerably reduce the computational burden of the simulation optimization process, but also maintain high computational accuracy. This can thus provide an effective method for identifying an optimal groundwater exploitation scheme quickly and accurately.

A comparative research of different ensemble surrogate models based on set pair analysis for the DNAPL-contaminated aquifer remediation strategy optimization

Surrogate-based simulation-optimization technique is an effective approach for optimizing the surfactant enhanced aquifer remediation (SEAR) strategy for clearing DNAPLs. The performance of the surrogate model, which is used to replace the simulation model for the aim of reducing computation burden, is the key of corresponding researches. However, previous researches are generally based on a stand-alone surrogate model, and rarely make efforts to improve the approximation accuracy of the surrogate model to the simulation model sufficiently by combining various methods. In this regard, we present set pair analysis (SPA) as a new method to build ensemble surrogate (ES) model, and conducted a comparative research to select a better ES modeling pattern for the SEAR strategy optimization problems. Surrogate models were developed using radial basis function artificial neural network (RBFANN), support vector regression (SVR), and Kriging. One ES model is assembling RBFANN model, SVR model, and Kriging model using set pair weights according their performance, and the other is assembling several Kriging (the best surrogate modeling method of three) models built with different training sample datasets. Finally, an optimization model, in which the ES model was embedded, was established to obtain the optimal remediation strategy. The results showed the residuals of the outputs between the best ES model and simulation model for 100 testing samples were lower than 1.5%. Using an ES model instead of the simulation model was critical for considerably reducing the computation time of simulation-optimization process and maintaining high computation accuracy simultaneously.

Hydrological impacts of climate change on streamflow of Dongliao River watershed in Jilin Province, China

The impacts of future climate change on streamflow of the Dongliao River Watershed located in Jilin Province, China have been evaluated quantitatively by using a general circulation model (HadCM3) coupled with the Soil and Water Assessment Tool (SWAT) hydrological model. The model was calibrated and validated against the historical monitored data from 2005 to 2009. The streamflow was estimated by downscaling HadCM3 outputs to the daily mean temperature and precipitation series, derived for three 30-year time slices, 2020s, 2050s and 2080s. Results suggest that daily mean temperature increases with a changing rate of 0.435°C per decade, and precipitation decreases with a changing rate of 0.761 mm per decade. Compared with other seasons, the precipitation in summer shows significant downward trend, while a significant upward trend in autumn. The annual streamflow demonstrates a general downward trend with a decreasing rate of 0.405 m3/s per decade. The streamflow shows significant downward and upward trends in summer and in autumn, respectively. The decreasing rate of streamflow in summer reaches 1.97 m3/s per decade, which contributes primarily to the decrease of streamflow. The results of this work would be of great benifit to the design of economic and social development planning in the study area.

Application of Back-Propagation Artificial Neural Network Models for Prediction of Groundwater Levels: Case study in Western Jilin Province, China

Evaluation and forecast of groundwater levels through specific model helps in forecasting of groundwater resources. Among the different robust tools available, the back-propagation artificial neural network (BPANN) model is commonly used to empirically forecast hydrological variables. Here, we discuss the modeling process and accuracy of this method based on the root mean squared error (RMSE), the mean absolute error (MAE) and coefficient of efficiency (R2). The arid and semi-arid areas of western Jilin province (China) were chosen as study area owing to the decline of groundwater levels during the past decade mainly due to over exploitation. The simulations results indicated that BPANN is accurate in reproducing (fitting) and forecasting the groundwater levels time series based on the R2 are 0.97 and 0.74, respectively. The RMSE, MAE for BPANN model in the predicting stage are 0.08, 0.066, respectively. It is evident that the BPANN is able to predict the groundwater levels reasonable well.

A quantitative model to evaluate mine geological environment and a new information system for the mining area in Jilin province, mid-northeastern China

The reliability of mine geological environment quality assessment highly depends on a large amount of survey data, a comprehensive evaluation system and an effective evaluation model. Using computer technology to integrate large amount of data can help to ensure the valid management and the effective assessment. Compared with previous studies, this study has improved and enriched the evaluation system and optimized the traditional evaluation method. Moreover, combining geology with computer science, it has developed the evaluation function of mine geological environment and realized the intersection and innovation of the discipline. The specific research content has the following three parts. First, a new design for an evaluation system which can synthetically describe the mine geological environment is presented. Second, a particle swarm optimization (PSO)-support vector machine (SVM) model is established as an alternative to traditional approaches that avoid interference from artificial factors. Third, a new mine geological environmental information system (MGEIS) is presented to efficiently manage data. Then, PSO-SVM evaluation model is embedded in it, and the mine geological environment in Jilin province is assessed by using MGEIS. Decisions can be presented based on the evaluation results in this study to better support the recovery of the local mine geological environment.

Approach to the Relation of Mutual-Feed Joint-Variation in Groundwater Management Model

In groundwater management, the exchanges between groundwater and other water such as surface water and spring water need to be considered. Some exchange is dependent on the groundwater level, which is called covariate. The pumping rate, groundwater level, and covariate interact and the relation of mutual-feed joint-variation is used to describe their interaction. This article presents a new approach of dealing with the relation in groundwater management model. The mathematical formulation of the relation, as an additional equality constraint in the optimization model, is developed using response matrix method. Thereby the groundwater management model with covariate is set up. The code for the simulation and management of groundwater system with covariate is programmed with Fortran 90, and the optimal pumping rate, groundwater level, and covariate are obtained. The approach is verified with a hypothetical case. Finally, the approach is applied to the groundwater management of Qianguo (前郭) area in western Jilin (吉林) Province. The results indicate that the approach is feasible. It provides a universal solution for various covariates and reduces the computational complexity compared to iteration method. The approach is proven to be very efficient to solve groundwater management problem with covariate.