Field‐Scale Application of Three Types of Neural Networks to Predict Ground‐Water Levels1

Abstract: In this paper, a field‐scale applicability of three forms of artificial neural network algorithms in forecasting short‐term ground‐water levels at specific control points is presented. These algorithms are the feed‐forward back propagation (FFBP), radial basis networks (RBN), and generalized regression networks (GRN). Ground‐water level predictions from these algorithms are in turn to be used in an Optimized Regional Operations Plan that prescribes scheduled wellfield production for the coming four weeks. These models are up against each other for their accuracy of ground‐water level predictions on lead times ranging from a week to four weeks, ease of implementation, and execution times (mainly training time). In total, 208 networks of each of the three algorithms were developed for the study. It is shown that although learning algorithms have emerged as a viable solution at field scale much larger than previously studied, no single algorithm performs consistently better than others on all the criteria. On average, FFBP networks are 20 and 26%, respectively, more accurate than RBN and GRN in forecasting one week ahead water levels and this advantage drops to 5 and 9% accuracy in forecasting four weeks ahead water levels, whereas GRN posted a training time that is only 5% of the training time taken by that of FFBP networks. This may suggest that in field‐scale applications one may have to trade between the type of algorithm to be used and the degree to which a given objective is honored.     

高温取热炉的水循环与安全运行

主要从水循环和循环倍率的角度，谈高温取热炉的安全性，并特别强调开工5天内是高温取热炉的危险期。     

Fate and transport of fragrance materials in principal environmental sinks

Fragrance materials are widely present in the environment, such as air, water, and soil. Concerns have been raised due to the increasing utilization and suspected impact on human health. The bioaccumulating property is considered as one of the causes of the toxicity to human beings. The removal of fragrance materials from environmental sinks has not been paid enough attention due to the lack of regulation and research on their toxicity. This paper provides systematic information on how fragrance materials are transferred to the environment, how do they affect human lives, and what is their fate in water, wastewater, wastewater sludge, and soil.     

含镉的铬废水处理方法

对电镀镉工艺流程中出光、钝化及退镉进行了原理分析,得出上述工序必然会导致含镉的铬废水的产生。并提出了采用按铬废水处理后再通过添加重金属捕捉剂的方式,有效控制了电镀废水的处理质量,达到了标准的排放要求。     

固相萃取富集水中痕量有机污染物的技术探讨

结合固相萃取预处理技术原理和操作流程,通过大量研究,提出固相萃取预处理操作过程中的技术关键并总结经验.对如何做好实验室空白,提高加标回收率和重现性等多方面进行阐述,并结合实验室数据进行论证.     

伊犁地区部分河流的水质标识指数

通过2004 - 2006年对伊犁地区的特克斯河、伊犁河的水质调查及水质标识指数和综合指数(WQI)的计算发现,DO、COD、TN、NH3-N、TP 5项指标在10个断面的空间分布上伊宁市区的2个断面水质最差,在时间上属8月最差,水质主要污染指标的排序依次为TP、TN、COD和NH3-N.     

新疆水环境质量影响因素浅析

由于新疆各类水体所处的地理环境不同,以及所在地域的气候、水文、人类活动强度等条件不同,使各类水体的水环境质量有很大差异.本文主要分析阐述了影响新疆河流、湖泊、水库、城市饮用水等水质特性的各类因素,并提出了较为可行的对策建议.     

东伶仃洋海域水质调查

选择出11项评价因子,采用单项分指数法和平均分指数法,在涨潮、落潮、涨落潮时分别对伶仃洋东部海域水质进行监测,并与历史资料进行对比,对评价因子超标进行评价和原因分析,提出了补救与预防措施.     

Monitoring Water Quality and Quantity of National Watersheds in Turkey

National data from the hydrological network for 38 rivers out of 25 watersheds were used to detect spatial and temporal trends in water quality and quantity characteristics between 1995 and 2002. Assessment of water quality and quantity included flow rate, water temperature, pH, electrical conductivity, sodium adsorption rate, Na, K, Ca+Mg, CO₃, HCO₃, Cl, SO₄, and boron. Among the major ions assessed on a watershed basis, Turkish river waters are relatively high in Ca+Mg, Na and HCO₃, and low in K and CO₃. The watersheds in Turkey experienced a general trend of 16% decrease in flow rates between 1995 and 2002 at a mean annual rate of about 4 m³ s^?1, with a considerable spatial variation. Similarly, there appeared to be an increasing trend in river water temperature, at a mean annual rate of about 0.2°C. A substantial proportion of watersheds experienced an increase in pH, in particular, after 1997, with a maximum increase from 8.1 to 8.4 observed in Euphrates (P?R ² values in accounting for variations of pH and water temperature only. The findings of the study can provide a useful assessment of controls over water quality and quantity and assist in devising integrated and sustainable management practices for watersheds at the regional scale in Turkey.     

Does seston size structure reflect fish-mediated effects on water quality in a degraded semiarid wetland?

This study evaluates whether the size structure of seston (the sum of living and nonliving particles in the water column) reflects the effects of fish on wetland water quality. Using enclosures, we measured water quality and zooplankton community structure in the presence and absence of two fish species with distinct foraging strategies [benthivorous carp (Cyprinus carpio) and planktivorous mosquitofish (Gambusia holbrooki)]. Seston collected from the enclosures was counted and sized automatically with a Coulter counter, and the size structure in the range of 1–60 μm was modelled using the underlying Pareto distribution of particles. Only Cyprinus contributed to a loss of water quality (increased nutrient levels, algal and non-algal turbidity, hypoxia), while both fish species changed zooplankton community composition compared to fishless controls. However, these changes were not reflected in parameters [goodness of fit (r ²) and parameter c (slopes)] of Pareto models. Multivariate statistics suggest that seston size structure responded more to environmental gradients related to water depth but the relationships were also weak. Our overall result contrasts with the regulation of size spectra constructed from living organisms. Although seston integrates many structural and functional features of the water column, the lack of strong relationships between Pareto model parameters and water quality suggests that a size-based approach to characterise seston structure has a limited potential for assessing biota-mediated effects in wetlands in a straightforward manner.