Application of ANN and ANFIS models for reconstructing missing flow data

Hydrological yearbooks, especially in developing countries, are full of gaps in flow data series. Filling missing records is needed to make feasibility studies, potential assessment, and real-time decision making. In this research project, it was tried to predict the missing data of gauging stations using data from neighboring sites and a relevant architecture of artificial neural networks (ANN) as well as adaptive neuro-fuzzy inference system (ANFIS). To be able to evaluate the results produced by these new techniques, two traditionally used methods including the normal ratio method and the correlation method were also employed. According to the results, although in some cases all four methods presented acceptable predictions, the ANFIS technique presented a superior ability to predict missing flow data especially in arid land stations with variable and heterogeneous data. Comparing the results, ANN was also found as an efficient method to predict the missing data in comparison to the traditional approaches.     

Using a neural network approach and time series data from an international monitoring station in the Yellow Sea for modeling marine ecosystems

The international marine ecological safety monitoring demonstration station in the Yellow Sea was developed as a collaborative project between China and Russia. It is a nonprofit technical workstation designed as a facility for marine scientific research for public welfare. By undertaking long-term monitoring of the marine environment and automatic data collection, this station will provide valuable information for marine ecological protection and disaster prevention and reduction. The results of some initial research by scientists at the research station into predictive modeling of marine ecological environments and early warning are described in this paper. Marine ecological processes are influenced by many factors including hydrological and meteorological conditions, biological factors, and human activities. Consequently, it is very difficult to incorporate all these influences and their interactions in a deterministic or analysis model. A prediction model integrating a time series prediction approach with neural network nonlinear modeling is proposed for marine ecological parameters. The model explores the natural fluctuations in marine ecological parameters by learning from the latest observed data automatically, and then predicting future values of the parameter. The model is updated in a “rolling” fashion with new observed data from the monitoring station. Prediction experiments results showed that the neural network prediction model based on time series data is effective for marine ecological prediction and can be used for the development of early warning systems.     

Estimating soil temperature using neighboring station data via multi-nonlinear regression and artificial neural network models

The aim of this study is to estimate the soil temperatures of a target station using only the soil temperatures of neighboring stations without any consideration of the other variables or parameters related to soil properties. For this aim, the soil temperatures were measured at depths of 5, 10, 20, 50, and 100 cm below the earth surface at eight measuring stations in Turkey. Firstly, the multiple nonlinear regression analysis was performed with the “Enter” method to determine the relationship between the values of target station and neighboring stations. Then, the stepwise regression analysis was applied to determine the best independent variables. Finally, an artificial neural network (ANN) model was developed to estimate the soil temperature of a target station. According to the derived results for the training data set, the mean absolute percentage error and correlation coefficient ranged from 1.45% to 3.11% and from 0.9979 to 0.9986, respectively, while corresponding ranges of 1.685–3.65% and 0.9988–0.9991, respectively, were obtained based on the testing data set. The obtained results show that the developed ANN model provides a simple and accurate prediction to determine the soil temperature. In addition, the missing data at the target station could be determined within a high degree of accuracy.     

Groundwater levels time series sensitivity to pluviometry and air temperature: a geostatistical approach to Sfax region,Tunisia

In this paper, the pattern of groundwater level fluctuations is investigated by statistical techniques for 24 monitoring wells located in an unconfined coastal aquifer in Sfax (Tunisia) for a time period from 1997 to 2006. Firstly, a geostatistical study is performed to characterize the temporal behaviors of data sets in terms of variograms and to make predictions about the value of the groundwater level at unsampled times. Secondly, multivariate statistical methods, i.e., principal component analysis (PCA) and cluster analysis (CA) of time series of groundwater levels are used to classify groundwater hydrographs regard to identical fluctuation pattern. Three groundwater groups (A, B, and C) were identified. In group “A,” water level decreases continuously throughout the study periods with rapid annual cyclic variation, whereas in group “B,” the water level contains much less high-frequency variation. The wells of group “C” represents a steady and gradual increase of groundwater levels caused by the aquifer artificial recharge. Furthermore, a cross-correlation analysis is used to investigate the aquifer response to local rainfall and temperature records. The result revealed that the temperature is more affecting the variation of the groundwater level of group A wells than the rainfall. However, the second and the third groups are less affected by rainfall or temperature.     

Optimal Space-time Coverage and Exploration Costs in Groundwater Monitoring Networks

A method to determine the optimal subset of stations from a reference level groundwater monitoring network is proposed. The method considers the redundancy of data from historical time series, the times associated with the total distance required to run through the entire monitoring network, and the sum of the times for each monitoring station. The method was applied to a hypothetical case-study consisting of a monitoring network with 32 stations. Cost-benefit analysis was performed to determine the number of stations to include in the new design versus loss of information. This optimisation problem was solved with simulated annealing. Results showed that the relative reduction in exploration costs more than compensates for the relative loss in data representativeness.     

相似分析在空气连续监测缺测资料插补处理中的应用

空气连续自动监测中缺测资料的插补处理是环境监测与科研的一项基础性的技术工作,文章应用数理统计中的相似分析原理进行探讨,取得了较理想的结果.该方法对解决和处理因采样时间不足而造成的污染物浓度日均值缺失问题是十分有效的,对目前我国开展的城市空气质量日报工作有一定的实际意义.     

Selection of appropriate sampling stations in a lake through mapping

Much valuable information is obtained from water quality measurements and monitoring of lakes around the world. A powerful tool is the use of mapping techniques, as it offers potential use in water quality research. Both remote sensing techniques and traditional water quality monitoring are required to collect data at sampling stations. This study suggests another approach to determine the most appropriate distribution of sampling stations in water reservoirs that will be mapped for water quality parameters. Tests were conducted for the proposed approach for Secchi disc depth (SDD), chlorophyll-a, turbidity and suspended solids parameters in Lake Beysehir, Turkey. Results of analysis are available for a total of 30 sampling stations in August 2006. Ten sampling stations were used to model Lake Beysehir while the others were used for validation of the model. Sampling stations that offered the best representation of the lake for each parameter were determined. Then, the best representative sampling stations for all parameters in the study were determined. Moreover, in order to confirm the accuracy of these re-determined sampling stations, modelling was performed on the results of the analysis of June 2006, and it was found that the values obtained from the re-determined sampling stations were acceptable.     

Optimal extension of the rain gauge monitoring network of the Apulian Regional Consortium for Crop Protection

The goal of this paper is to provide a methodology for assessing the optimal localization of new monitoring stations within an existing rain gauge monitoring network. The methodology presented, which uses geostatistics and probabilistic techniques (simulated annealing) combined with GIS instruments, could be extremely useful in any area where an extension of whatever existing environmental monitoring network is planned. The methodology has been applied to the design of an extension to a rainfall monitoring network in the Apulia region (South Italy). The considered monitoring network is managed by the Apulian Regional Consortium for Crop Protection (ARCCP), and, currently consists of 45 gauging stations distributed over the regional territory, mainly located on the basis of administrative needs. Fifty new stations have been added to the existing monitoring network, split in two groups: 15 fixed and 35 mobile stations. Two different methods were applied and tested: the Minimization of the Mean of Shortest Distances method (MMSD) and Ordinary Kriging (OK) whose related objective function is estimation variance. The MMSD, being a purely geometric method, produced a spatially uniform configuration of the gauging stations. On the contrary, the approach based on the minimization of the average of the kriging estimation variances, produced a less regular configuration, though a more reliable one from a spatial standpoint. Nevertheless, the MMSD approach was chosen, since the ARCCP's intention was to create a new monitoring network characterized by uniform spatial distribution throughout the regional territory. This was the most important constraint given to the project by the ARCCP, whose main objective was to accomplish a territorial network capable of detecting hazardous events quickly. A seasonal aggregation of the available rainfall data was considered. The choice of the temporal aggregation in quarterly averages allowed four different optimal configurations to be determined per season. The overlapping of the four configurations allowed a number of new station locations, which tended to remain fixed season after season, to be identified. Other stations, instead, changed their coordinates considerably over the four seasons. Constraints were defined in order to avoid placing new monitoring locations either near existing stations, belonging to other Agencies, or near the coast line.     

A multi-variate methodology for analyzing pre-existing lake water quality data

Environmental agencies are given the task of monitoring water quality in rivers, lakes, and other bodies of water, for the purpose of comparing the results with regulatory standards. Monitoring follows requirements set by regulations, and data are collected in a systematic way for the intended purpose. Monitoring enables agencies to determine whether water bodies are polluted. Much effort is spent per monitoring event, resulting in hundreds of data points typically used solely for comparison with regulatory standards and then stored for little further use. This paper devises a data analysis methodology that can make use of the pre-existing datasets to extract more useful information on water quality trends, without new sample collection and analysis. In this paper, measured lake water quality data are subjected to statistical analyses including Principal Component Analysis (PCA) to deduce changes in water quality spatially and temporally over several years. It was found that the lake as a whole changed temporally by season, rather than spatially. Storm events caused the greatest shifts in water quality, though the shifts were fairly consistent across sampling stations. This methodology can be applied to similar datasets, especially with the recent emphasis by the U.S. EPA on protection of lakes as water sources. Water quality managers using these techniques may be able to lower their monitoring costs by eliminating redundant water quality parameters found in this analysis.     

Assessing temporal representativeness of water quality monitoring data

The effectiveness of different monitoring methods in detecting temporal changes in water quality depends on the achievable sampling intervals, and how these relate to the extent of temporal variation. However, water quality sampling frequencies are rarely adjusted to the actual variation of the monitoring area. Manual sampling, for example, is often limited by the level of funding and not by the optimal timing to take samples. Restrictions in monitoring methods therefore often determine their ability to estimate the true mean and variance values for a certain time period or season. Consequently, we estimated how different sampling intervals determine the mean and standard deviation in a specific monitoring area by using high frequency data from in situ automated monitoring stations. Raw fluorescence measurements of chlorophyll a for three automated monitoring stations were calibrated by using phycocyanin fluorescence measurements and chlorophyll a analyzed from manual water samples in a laboratory. A moving block bootstrap simulation was then used to estimate the standard errors of the mean and standard deviations for different sample sizes. Our results showed that in a temperate, meso-eutrophic lake, relatively high errors in seasonal statistics can be expected from monthly sampling. Moreover, weekly sampling yielded relatively small accuracy benefits compared to a fortnightly sampling. The presented method for temporal representation analysis can be used as a tool in sampling design by adjusting the sampling interval to suit the actual temporal variation in the monitoring area, in addition to being used for estimating the usefulness of previously collected data.     

Reproducibility and imputation of air toxics data

Ambient air quality datasets include missing data, values below method detection limits and outliers, and the precision and accuracy of the measurements themselves are often unknown. At the same time, many analyses require continuous data sequences and assume that measurements are error-free. While a variety of data imputation and cleaning techniques are available, the evaluation of such techniques remains limited. This study evaluates the performance of these techniques for ambient air toxics measurements, a particularly challenging application, and includes the analysis of intra- and inter-laboratory precision. The analysis uses an unusually complete-dataset, consisting of daily measurements of over 70 species of carbonyls and volatile organic compounds (VOCs) collected over a one year period in Dearborn, Michigan, including 122 pairs of replicates. Analysis was restricted to compounds found above detection limits in > or =20% of the samples. Outliers were detected using the Gumbell extreme value distribution. Error models for inter- and intra-laboratory reproducibility were derived from replicate samples. Imputation variables were selected using a generalized additive model, and the performance of two techniques, multiple imputation and optimal linear estimation, was evaluated for three missingness patterns. Many species were rarely detected or had very poor reproducibility. Error models developed for seven carbonyls showed median intra- and inter-laboratory errors of 22% and 25%, respectively. Better reproducibility was seen for the 16 VOCs meeting detection and reproducibility criteria. Imputation performance depended on the compound and missingness pattern. Data missing at random could be adequately imputed, but imputations for row-wise deletions, the most common type of missingness pattern encountered, were not informative. The analysis shows that air toxics data require significant efforts to identify and mitigate errors, outliers and missing observations, and that these steps are essential and should be performed prior to using these data in receptor, exposure, health and other applications.     

Frequency Analysis for Precipitation Events and Dry Durations of Virginia

Stormwater Control Measures (SCMs) are widely used to control and treat stormwater runoff pollution. The first step in SCM design is to evaluate the precipitation patterns at a site. SCMs are normally designed using a storm with a specific return period. A robust design process that uses frequency distribution of precipitation and monitoring of performance could improve our understanding of the behavior and limitations of a particular design. This is not the current norm in the design of SCMs. In this research, frequency analyses (FA) of precipitation events was conducted using hourly precipitation data from 1948 to 2010 for eight sites representing the four major physiographic regions of Virginia. The available data were treated using an inverse distance method to eliminate missing gaps before processing into events determined by minimum inter-event times. FA was at each site to develop frequency plots of precipitation and dry duration. FA of the eight locations indicates a range of rainfall depths from 22.9 mm in Bristol to 35.6 mm in Montebello, compared to the nominal “water quality storm” of 25.4 mm (i.e., 1 in.). Similarly, for dry duration, for a 10 % exceedance probability, the range is from 16.8 days in Richmond and Norfolk to 19.5 days in Montebello. Dry duration provides guidance for vegetation selection, which is important for some SCMs. The degree of variability in both parameters argues for consideration of site-specific information in design. FA was also used to provide guidance to improve monitoring programs. Monte Carlo simulations demonstrated that performance monitoring programs applied in different regions would likely encounter more than 30 % of precipitation events less than 6.35 mm, and 10 % over 25.4 mm under various sampling regimes. The percentages of precipitation events encountered in the Coastal Plain and Piedmont regions are not impacted by sampling regimes, however the Blue Ridge Mountains and Valley and Ridge regions are likely impacted. Anticipating event occurrences improves the chances of implementing a successful monitoring program. The use of these results could enhance the performance of SCMs with consideration of local conditions for both monitoring SCMs and their design basis.     

Application and validation of a new biotic index using data from several water systems

Protozoans of Lake Donghu were collected from five stations using the PFU method. The sampling was conducted for one year and two times a month. The aim of this research was to test the applicability of a new protozoa biotic index, species pollution value (SPV) and community pollution value (CPV), established by the authors using data from the River Hanjiang. Each station's CPV was calculated from the SPV and the correlation analysis between the CPV and the comprehensive chemical index of stations I, II, III showed a significant correlation between them. The pollution status of the five stations was correctly evaluated by the CPV. These results suggested that the biotic index could be applied in water systems other than the River Hanjiang. The SPV of some protozoa species in Lake Donghu, not observed in the River Hanjiang were established. In order to further test the applicability of the biotic index, protozoan and chemistry data from the Rivers Torrente Stirone and Parma of Italy were used. The results showed that the CPV for the two rivers had a close relationship with the chemical water quality, which indicated that the biotic index could be applied in other parts of the world for the monitoring and estimating of water quality. Since the results of testing and verifying the biotic index in some other water systems in China were also satisfactory, this indicated that the biotic index has an extensive suitability for freshwater ecosystems. As long as more than 50% of the species in a sample have a SPV, the CPV calculated from the SPV is reliable for monitoring and evaluating water quality.     

Effectiveness and potential ecological effects of offshore surface dispersant use during the Deepwater Horizon oil spill: a retrospective analysis of monitoring data

The Special Monitoring of Applied Response Technologies (SMART) program was used during the Deepwater Horizon oil spill as a strategy to monitor the effectiveness of sea surface dispersant use. Although SMART was implemented during aerial and vessel dispersant applications, this analysis centers on the effort of a special dispersant missions onboard the M/V International Peace, which evaluated the effectiveness of surface dispersant applications by vessel only. Water samples (n?=?120) were collected from background sites, and under naturally and chemically dispersed oil slicks, and were analyzed for polycyclic aromatic hydrocarbons (TPAHs), total petroleum hydrocarbons (TPH), and a chemical marker of Corexit® (dipropylene glycol n-butyl ether, DPnB). Water chemistry results were analyzed relative to SMART field assessments of dispersant effectiveness (“not effective,” “effective,” and “very effective”), based on in situ fluorometry. Chemistry data were also used to indirectly determine if the use of dispersants increased the risk of acute effects to water column biota, by comparison to toxicity benchmarks. TPAH and TPH concentrations in background, and naturally and chemically dispersed samples were extremely variable, and differences were not statistically detected across sample types. Ratios of TPAH and TPH between chemically and naturally dispersed samples provided a quantitative measure of dispersant effectiveness over natural oil dispersion alone, and were in reasonable agreement with SMART field assessments of dispersant effectiveness. Samples from “effective” and “very effective” dispersant applications had ratios of TPAH and TPH up to 35 and 64, respectively. In two samples from an “effective” dispersant application, TPHs and TPAHs exceeded acute benchmarks (0.81 mg/L and 8 μg/L, respectively), while none exceeded DPnB’s chronic value (1,000 μg/L). Although the primary goal of the SMART program is to provide near real-time effectiveness data to the response, and not to address concerns regarding acute biological effects, the analyses presented here demonstrate that SMART can generate information of value to a larger scientific audience. A series of recommendations for future SMART planning are also provided.     

Development of a software package for trend detection in temporal series: Application to water and industrial effluent quality data for the St. Lawrence River

Despite the considerable amount of effort and resources involved in monitoring water quality, water quality assessment and environmental follow-up are sometimes carried out with simple statistics, the main reason being the lack of appropriate statistical methods adapted to the nature of sampled water quality data.A survey of the classical methods used for trend detection and of their limitations is first presented, including the most recent non-parametric techniques adapted to the structure of the sampled data and to the possible types of trends occuring. This paper then presents an interactive user-friendly software package developed for microcomputers making use of these latest adapted techniques. Afterwards, some applications of the software are described pertaining to the concentrations measured at long-term stations on the St. Lawrence River and to the mass loadings discharged by regulated industries. Finally, conclusions are drawn about the assumptions, performance and limitations of the package as well as about the research needs to improve the usefulness and applicability of the software.     

中欧环境空气臭氧评价对比与启示

欧盟臭氧(O₃)监测与评价起步相对较早。对比中国和欧盟O₃例行评价,欧盟在O₃标准限值、保护对象、评价指标、评价时间尺度、参评点位类型的设定和选取,以及O₃浓度与前体物排放量的关联性分析等方面,均对中国O₃评价具有一定的借鉴意义。以2017—2020年石家庄市8个国控站点O₃观测数据为分析案例,采用欧盟常用的日最大8 h滑动平均浓度(MDA8)第4高值,以及O₃暴露指标SOMO35和AOT40等3项评价指标,开展了尝试性评价应用和浓度对比。对照欧盟O₃评价指标应用经验,未来可考虑从兼顾两类功能区、丰富评价指标、扩展参评点位类型、纳入暴露影响评估、关联前体物排放变化等方面,进一步完善中国环境空气O₃评价方式,以更好地发挥其对空气质量精细化管理的数据支撑作用。     

Spatiotemporal analysis of the PM10 concentration over the Taranto area

In this paper, an analysis of air quality data is provided for the municipal area of Taranto (southern Italy) characterized by high environmental risks as formally decreed by the Italian government in the 1990s with two administrative measures. This is due to the massive presence of industrial sites with elevated environmental impact activities along the NW boundary of the city conurbation. The aforementioned activities have effects on the environment and on public health, as a number of epidemiological researches concerning this area reconfirm. The present study is focused on particulate matter as measured by PM10 concentrations at 13 monitoring stations, equipped with analogous instruments based on the Beta absorption technology, either reporting hourly, two-hourly, or daily measurements. Daily estimates of the PM10 concentration surfaces are obtained in order to identify areas of higher concentration (hot spots), possibly related to specific anthropic activities. Preliminary analysis involved addressing several data problems: (1) due to the use of two different validation techniques, a calibration procedure was devised to allow for data comparability; (2) imputation techniques were considered to cope with the large number of missing data, due to both different working periods and occasional malfunctions of PM10 sensors; and (3) reliable weather covariates (wind speed and direction, pressure, temperature, etc.) were obtained and considered within the analysis. Spatiotemporal modelling was addressed by a Bayesian kriging-based model proposed by Le and Zidek (2006) characterized by the use of time varying covariates and a semiparametric covariance structure. Advantages and disadvantages of the model are highlighted and assessed in terms of fit and performance. Estimated daily PM10 concentration surfaces are suitable for the interpretation of time trends and for identifying concentration peaks within the urban area.     

LaSVM-based big data learning system for dynamic prediction of air pollution in Tehran

Due to critical impacts of air pollution, prediction and monitoring of air quality in urban areas are important tasks. However, because of the dynamic nature and high spatio-temporal variability, prediction of the air pollutant concentrations is a complex spatio-temporal problem. Distribution of pollutant concentration is influenced by various factors such as the historical pollution data and weather conditions. Conventional methods such as the support vector machine (SVM) or artificial neural networks (ANN) show some deficiencies when huge amount of streaming data have to be analyzed for urban air pollution prediction. In order to overcome the limitations of the conventional methods and improve the performance of urban air pollution prediction in Tehran, a spatio-temporal system is designed using a LaSVM-based online algorithm. Pollutant concentration and meteorological data along with geographical parameters are continually fed to the developed online forecasting system. Performance of the system is evaluated by comparing the prediction results of the Air Quality Index (AQI) with those of a traditional SVM algorithm. Results show an outstanding increase of speed by the online algorithm while preserving the accuracy of the SVM classifier. Comparison of the hourly predictions for next coming 24 h, with those of the measured pollution data in Tehran pollution monitoring stations shows an overall accuracy of 0.71, root mean square error of 0.54 and coefficient of determination of 0.81. These results are indicators of the practical usefulness of the online algorithm for real-time spatial and temporal prediction of the urban air quality.     

基于大数据监管平台的通信基站监督性监测技术模式

提出一种基于大数据监管平台的通信基站监督监测技术模式,利用大数据监管平台实现监督监测对象的自动筛选、开展线上全流程监测、自动分析比对监测结果,并将该技术模式用于2019年和2020年广东省10.5万个通信基站的监督监测。结果表明,通信基站备案基础信息的相符率为75.3%~98.6%;社会化监测机构关键点位电磁环境监测结果相符率为60.0%~92.3%。该结果可用于评估广东省通信基站建设单位备案的基础信息相符性结果和社会化监测机构监测质量。