Simulating monthly streamflow using a hybrid feature selection approach integrated with an intelligence model

ABSTRACT

Streamflow prediction is useful for robust water resources engineering and management. This paper introduces a new methodology to generate more effective features for streamflow prediction based on the concept of “interaction effect”. The new features (input variables) are derived from the original features in a process called feature generation. It is necessary to select the most efficient input variables for the modelling process. Two feature selection methods, least absolute shrinkage and selection operator (LASSO) and particle swarm optimization-artificial neural networks (PSO-ANN), are used to select the effective features. Principal components analysis (PCA) is used to reduce the dimensions of selected features. Then, optimized support vector regression (SVR) is used for monthly streamflow prediction at the Karaj River in Iran. The proposed method provided accurate prediction results with a root mean square error (RMSE) of 2.79 m³/s and determination coefficient (R² ) of 0.92.     

Seasonal description of the quality and quantity of snowmelt in a mountainous region using an integrated model

Abstract

An integrated model for the simulation and prediction of both snowmelt quantity and quality from seasonal snow cover in a mountain basin has been developed at the Institute of Hydrology and Hydraulics SAS in cooperation with the Geological Institute of Dionyz ?tur. The model will be used for both the simulation and forecast of snow accumulation and the accumulation of SO^2- ₄ washout. At the present time it is mostly used for simulation of the SO^2- ₄ concentration and water supply in snow. In this paper the results of SO^2- ₄ modelling in a brook are also presented.     

Water quality management in a wetland system using an inexact left-hand-side chance-constrained fuzzy multi-objective approach

Water quality management is a significant item in the sustainable development of wetland system, since the environmental influences from the economic development are becoming more and more obvious. In this study, an inexact left-hand-side chance-constrained fuzzy multi-objective programming (ILCFMOP) approach was proposed and applied to water quality management in a wetland system to analyze the tradeoffs among multiple objectives of total net benefit, water quality, water resource utilization and water treatment cost. The ILCFMOP integrates interval programming, left-hand-side chance-constrained programming, and fuzzy multi-objective programming within an optimization framework. It can both handle multiple objectives and quantify multiple uncertainties, including fuzziness (aspiration level of objectives), randomness (pollutant release limitation), and interval parameters (e.g. water resources, and wastewater treatment costs). A representative water pollution control case study in a wetland system is employed for demonstration. The optimal schemes were analyzed under scenarios at different probabilities (p _i , denotes the admissible probability of violating the constraint i). The optimal solutions indicated that, most of the objectives would decrease with increasing probability levels from scenarios 1 to 3, since a higher constraint satisfaction probability would lead to stricter decision scopes. This study is the first application of the ILCFMOP model to water quality management in a wetland system, which indicates that it is applicable to other environmental problems under uncertainties.     

利用Nagvis插件实现网络设备可视化监控

安徽省地震局建成1套服务于本省地震行业高速信息网络系统,各类设备500余套。为保障设备运转正常,需要及时发现并排除故障。实现网络设备监控信息可视化成为亟需解决的问题。Nagvis作为Nagios的展示组件,可采用多种模式对Nagios系统中的监控对象进行图形化展示。通过该技术实现安徽省地震局网络设备监控信息可视化,为运维人员及时提供网络设备运行状态,提高了网络运行质量和效率。     

Water quality monitoring at a virtual watershed monitoring station using a modified deep extreme learning machine

ABSTRACT

A new deep extreme learning machine (ELM) model is developed to predict water temperature and conductivity at a virtual monitoring station. Based on previous research, a modified ELM auto-encoder is developed to extract more robust invariance among the water quality data. A weighted ELM that takes seasonal variation as the basis of weighting is used to predict the actual value of water quality parameters at sites which only have historical data and no longer generate new data. The performance of the proposed model is validated against the monthly data from eight monitoring stations on the Zengwen River, Taiwan (2002–2017). Based on root mean square error, mean absolute error, mean absolute percentage error and correlation coefficient, the experimental results show that the new model is better than the other classical spatial interpolation methods.     

地震地下流体台网日常质量监控现状分析

介绍了地震地下流体台网概况、日常数据质量监控的流程与方法,总结了地震地下流体台网2017—2019年日常质量监控效果,以及在数据预处理、观测日志填写工作中出现的各种问题,并对典型问题进行了简要分析,旨在为监测人员的数据预处理和观测日志记录工作提供参考.     

Hydrogeochemistry and quality of groundwater in a part of Damodar Valley,Eastern India: an integrated geochemical and statistical approach

The influence of geochemical processes and quality of groundwater in a rural tract of Damodar Valley region were investigated. The study has distinguished the groundwater as fresh, soft to moderately hard and mainly CaHCO₃ type. The paired samples student’s t test shows the significant seasonal variations of pH, HCO₃^?, and Fe. Amphoteric exchange has lessened HCO₃^? concentration in post-monsoon which subsequently has caused to drop pH. Quite the reverse, the monsoon precipitation has triggered the additional release of Fe from iron-bearing sediments. The contaminant Cl^? is from the domestic wastewater as is evidenced by field observations. The inter-variable relations, cation and anion mechanisms, and mineral saturation indices reveal that the dissolutions of silicate and carbonate minerals are the primary sources of major ions in groundwater. The chloro-alkaline indices showed the role of ion exchange too in water chemistry. The R-mode factor analysis also successfully identified two dominant processes regulating water chemistry—geogenic sources (Ca²⁺, Mg²⁺, Na⁺, and HCO₃^?) and anthropogenic inputs (mainly Cl^?). The groundwater is found unsuitable for drinking at 82 and 93% of wells in pre- and post-monsoon seasons, respectively mainly due to elevated Fe content. The water from more than 90% of wells is appropriate for irrigation uses. The study recommends the proper treatment of contaminated water for consumption and measures to protect the groundwater from the waste water infiltration.     

An integrated fuzzy-stochastic modeling approach for assessing health-impact risk from air pollution

High concentrations of air pollutants in the ambient environment can result in breathing problems with human communities. Effective assessment of health-impact risk from air pollution is important for supporting decisions of the related detection, prevention, and correction efforts. However, the quality of information available for environmental/health risk assessment is often not satisfactory enough to be presented as deterministic numbers. Stochastic method is one of the methods for tackling those uncertainties, by which uncertain information can be presented as probability distributions. However, if the uncertainties can not be presented as probabilities, they can then be handled through fuzzy membership functions. In this study, an integrated fuzzy-stochastic modeling (IFSM) approach is developed for assessing air pollution impacts towards asthma susceptibility. This development is based on Monte Carlo simulation for the fate of SO₂ in the ambient environment, examination of SO₂ concentrations based on the simulation results, quantification of evaluation criteria using fuzzy membership functions, and risk assessment based on the combined fuzzy-stochastic information. The IFSM entails (a) simulation for the fate of pollutants in ambient environment, with the consideration of source/medium uncertainties, (b) formulation of fuzzy air quality management criteria under uncertain human-exposure pathways, exposure dynamics, and SPG-response variations, and (c) integrated risk assessment under complexities of the combined fuzzy/stochastic inputs of contamination level and health effect (i.e., asthma susceptibility). The developed IFSM is applied to a study of regional air quality management. Reasonable results have been generated, which are useful for evaluating health risks from air pollution. They also provide support for regional environmental management and urban planning.     

Modelling coastal ground‐ and surface‐water interactions using an integrated approach

Beach water table fluctuations have an impact on the transport of beach sediments and the exchange of solute and mass between coastal aquifer and nearby water bodies. Details are given of the refinement of a dynamically integrated ground‐ and surface‐water model, and its application to study ground‐ and surface‐water interactions in coastal regions. The depth‐integrated shallow‐water equations are used to represent the surface‐water flow, and the extended Darcy's equation is used to represent the groundwater flow, with a hydrostatic pressure distribution being assumed to apply for both these two types of flows. At the intertidal region, the model has two layers, with the surface‐water layer being located on the top of the groundwater layer. The governing equations for these two types of flows are discretized in a similar manner and they are combined to give one set of linear algebraic equations that can be solved efficiently. The model is used to predict water level distributions across sloping beaches, where the water table in the aquifer may or may not decouple from the free water surface. Five cases are used to test the model for simulating beach water table fluctuations induced by tides, with the model predictions being compared with existing analytical solutions and laboratory and field data published in the literature. The numerical model results show that the integrated model is capable of simulating the combined ground‐ and surface‐water flows in coastal areas. Detailed analysis is undertaken to investigate the capability of the model. Copyright © 2009 John Wiley & Sons, Ltd.     

Kriging with external drift for functional data for air quality monitoring

Functional data featured by a spatial dependence structure occur in many environmental sciences when curves are observed, for example, along time or along depth. Recently, some methods allowing for the prediction of a curve at an unmonitored site have been developed. However, the existing methods do not allow to include in a model exogenous variables that, for example, bring meteorology information in modeling air pollutant concentrations. In order to introduce exogenous variables, potentially observed as curves as well, we propose to extend the so-called kriging with external drift—or regression kriging—to the case of functional data by means of a three-step procedure involving functional modeling for the trend and spatial interpolation of functional residuals. A cross-validation analysis allows to choose smoothing parameters and a preferable kriging predictor for the functional residuals. Our case study considers daily PM₁₀ concentrations measured from October 2005 to March 2006 by the monitoring network of Piemonte region (Italy), with the trend defined by meteorological time-varying covariates and orographical constant-in-time variables. The performance of the proposed methodology is evaluated by predicting PM₁₀ concentration curves on 10 validation sites, even with simulated realistic datasets on a larger number of spatial sites. In this application the proposed methodology represents an alternative to spatio-temporal modeling but it can be applied more generally to spatially dependent functional data whose domain is not a time interval.     

A two-phase grey fuzzy optimization approach for water quality management of a river system

An extension of the Grey Fuzzy Waste Load Allocation Model (GFWLAM) developed in an earlier work is presented here to address the problem of multiple solutions. Formulation of GFWLAM is based on the approach for solving fuzzy multiple objective optimization problems with max–min as the operator, which usually may not result in a unique solution. The multiple solutions of fuzzy multiobjective optimization model should be obtained as parametric equations or equations that represent a subspace. A two-phase optimization technique, two-phase GFWLAM, is developed to capture all alternative or multiple solutions of GFWLAM. The optimization model in Phase 1 is exactly same as the optimization model described in GFWLAM. The optimization model in Phase 2 maximizes the upper bounds of fractional removal levels of pollutants and minimizes the lower bounds of fractional removal levels of pollutants keeping the value of goal fulfillment level same as obtained from Phase 1. The widths of the interval-valued fractional removal levels play an important role in decision-making as these can be adjusted within their intervals by the decision-maker considering technical and economic feasibility in the final decision scheme. Two-phase GFWLAM widens the widths of interval-valued removal levels of pollutants, thus enhancing the flexibility in decision-making. The methodology is demonstrated with a case study of the Tunga-Bhadra river system in India.     

An approach to analyses of periphytic ciliate colonization for monitoring water quality using a modified artificial substrate in Korean coastal waters

Structural and functional parameters of periphytic ciliate communities were studied for monitoring water quality in Korean coastal waters during April 2007. The PFES (polyurethane foam enveloped slide) system, a modified glass slide method, was used to analyze periphytic ciliate colonization in marine ecosystems. A total of 27 ciliate species were identified using living observation and silver impregnation method with this system. Although the ciliate colonizations had similar species composition, they represented considerable differences in both structural and functional parameters between the PFES system and the conventional slide system. The species diversity, evenness and the colonization rate (G) were distinctly higher, but the time for reaching 90% equilibrium species number (T_90%) was shorter in the PFES system than those on the naked slides. Results suggest that the PFES system is more effective than the conventional slide method for periphytic ciliate colonization with high species diversity, evenness, and colonization rate in marine ecosystems.     

Mapping water quality and substrate cover in optically complex coastal and reef waters: an integrated approach

Sustainable management of coastal and coral reef environments requires regular collection of accurate information on recognized ecosystem health indicators. Satellite image data and derived maps of water column and substrate biophysical properties provide an opportunity to develop baseline mapping and monitoring programs for coastal and coral reef ecosystem health indicators. A significant challenge for satellite image data in coastal and coral reef water bodies is the mixture of both clear and turbid waters. A new approach is presented in this paper to enable production of water quality and substrate cover type maps, linked to a field based coastal ecosystem health indicator monitoring program, for use in turbid to clear coastal and coral reef waters. An optimized optical domain method was applied to map selected water quality (Secchi depth, Kd PAR, tripton, CDOM) and substrate cover type (seagrass, algae, sand) parameters. The approach is demonstrated using commercially available Landsat 7 Enhanced Thematic Mapper image data over a coastal embayment exhibiting the range of substrate cover types and water quality conditions commonly found in sub-tropical and tropical coastal environments. Spatially extensive and quantitative maps of selected water quality and substrate cover parameters were produced for the study site. These map products were refined by interactions with management agencies to suit the information requirements of their monitoring and management programs.     

A Kriging-based approach for locating a sampling site—in the assessment of air quality

Air quality assessment studies have either high sampling or analyses costs. In these studies the representation of a city by a single sampling point is still a serious problem, especially in the metropolitans of developing countries, because of the absence of equipments required for sampling at different locations. In this paper, the smoke data measurements of long years are used in the determination of the region for the representation of the city by drawing contours through the Kriging method. Then, the selection of the sampling site in this region is done on the basis of the criteria recommended by the EPA. By this way, the data taken from this sampling point are used for assessing the average city concentrations with lower sampling and analyses costs. This information is valuable for monitoring the air quality and defining environmental policies, although the local distribution and the extreme concentration values over the city are not measurable.     

利用卷积神经网络检测地震的方法与优化

本文以西昌台阵观测的8 321次近震数据为例,详细介绍了利用深度卷积神经网络检测地震的数据处理流程,包括数据预处理、模型训练、波形长度、网络层数、学习率和概率阈值等关键参数对检测结果的影响,并将训练得到的最优模型,应用于事件波形和连续波形的检测。研究表明,数据预处理和数据增强可以提升模型的检测精度和抗干扰能力。用于模型训练的波形窗口长度可近似于S-P到时差的最大值。不同网络层数(5—8层)的检测结果差别不大。对于地震检测,学习率设为10-4—10-3较为合适。卷积神经网络检测出的地震数量与选择的概率阈值有关,通过绘制精确率-召回率变化曲线,可以为选择合适的概率阈值提供参考。本文为进一步利用深度学习算法提高地震检测效果提供了参考。     

A soft hydrological monitoring approach for comparing runoff on a network of small poorly gauged catchments

Catchments in many parts of the world are either ungauged or poorly gauged, and the dominant processes governing their streamflow response are still poorly understood. The analysis of runoff coefficients provides essential insight into catchment response, particularly if both range of catchments and a range of events are compared. This paper investigates how well the hydrological runoff of 11 small, poorly gauged catchments with ephemeral streams (0·1‐0·6 km²) can be compared using estimated runoff with the associated uncertainty. Data of rainfall and water depth at a catchment's outlet were recorded using automatic logging equipment during 2008‐2009. The hydrological regime is intermittent and the annual precipitation ranged between 569 and 727 mm. Discharge was estimated using Manning's equation and channel cross‐section measurements. Innovative work has been performed under controlled experimental conditions to estimate Manning's coefficient values for the different cover types observed in studied streams: non‐aquatic vegetations (giant reed, bramble and thistle), grass and coarse granular deposits. The results show that estimates derived using roughness coefficients differ from those previously established for larger streams with aquatic vegetation. Catchment runoff was compared at both the event and the annual scale. The results indicate significant variability between the catchment's responses. This variability allows for classification in spite of all the uncertainty associated with runoff estimation. This study highlights the potential of using a network of poorly gauged catch ments. From almost no catchment understanding the proposed methodology allows to compare poorly gauged catchments and highlights similarity/dissimilarity between catchment responses. Copyright © 2011 John Wiley & Sons, Ltd.     

Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization

Abstract

Artificial neural networks (ANNs) have recently been used to predict the hydraulic head in well locations. In the present work, the particle swarm optimization (PSO) algorithm was used to train a feed-forward multi-layer ANN for the simulation of hydraulic head change at an observation well in the region of Agia, Chania, Greece. Three variants of the PSO algorithm were considered, the classic one with inertia weight improvement, PSO with time varying acceleration coefficients (PSO-TVAC) and global best PSO (GLBest-PSO). The best performance was achieved by GLBest-PSO when implemented using field data from the region of interest, providing improved training results compared to the back-propagation training algorithm. The trained ANN was subsequently used for mid-term prediction of the hydraulic head, as well as for the study of three climate change scenarios. Data time series were created using a stochastic weather generator, and the scenarios were examined for the period 2010–2020.

Editor Z.W. Kundzewicz; Associate editor L. See

Citation Tapoglou, E., Trichakis, I.C., Dokou, Z., Nikolos, I.K., and Karatzas, G.P., 2014. Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization. Hydrological Sciences Journal, 59(6), 1225–1239. http://dx.doi.org/10.1080/02626667.2013.838005     

基于微服务架构的地震站网全流程一体化监控平台设计与实现

地震站网全流程一体化监控平台是基于微服务框架,应用数据库、通信、并行计算等传统信息技术,结合新兴的云计算、大数据进行建设的信息服务平台。该平台采用Hadoop分布式处理方案,应用Spring Cloud框架搭建,进行Docker容器封装,以标准RESTful API作为服务接口的微服务架构,实现了各应用服务模块之间的高内聚、低耦合及灵活、可扩展的特性,最终实现对地震台站运行的实时监测、高效运维和一体化管理。     

我国地震地下流体观测台网调整与优化方案探讨

本文首先简要介绍了我国地震地下流体观测台网的现状,然后针对其存在的主要问题提出了调整与优化的建议: ① 调整布局,重点加强我国中西部地区(105°E以西)的监测; ② 扩大规模,观测井(泉)数要达到1000个左右; ③ 全面提高观测井质量,淘汰不符合规范要求的观测井(泉),改造不完全符合规范要求的观测井,新建一批完全符合规范的观测井; ④ 优化观测项目的组合,大力发展观测井(泉)水流量观测,强化以H₂、 He、 CO₂等为主测项的断层带土壤气观测,建立断层带土壤气观测网; ⑤ 优化现有的观测模式,开展平面上的台阵式观测与垂向的多层次立体化观测; ⑥ 完善与提升现有数字化观测技术水平.