基于小波分析与BP神经网络的PM_(10)浓度预测模型

应用小波分析和BP神经网络相结合的方法,建立大气污染物浓度预测模型。首先,利用静态小波分解将原始的大气污染物浓度序列分解为不同频段的小波系数序列;其次,将重要的气象因子和各尺度上的小波系数序列作为BP神经网络的输入;最后,对输出的各序列预测值重构,得到最终的预测结果。使用该模型对重庆市主城区某国控监测站点的PM_(10)浓度预测,结果表明,与传统的BP神经网络模型相比,该预测模型的推广能力强、预测精密度高,具有良好的应用前景。     

基于信号改进深度学习网络的京津冀城市群二氧化氮浓度预测

在中国华北地区,二氧化氮污染仍旧不容忽视,尤其是在机动车辆密集和工业生产相对集中的京津冀城市群。运用小波分解(WD)和长短期记忆(LSTM)神经网络建立了W-LSTM组合模型,用于预测未来京津冀地区二氧化氮日均浓度和分指数。使用2014年1月—2018年5月主要大气污染物数据对组合预测模型进行训练试验,在获得最优模型参数后,使用2018年6月—2019年6月数据进行模型预测性能测试试验。结果表明,相较于传统的LSTM预测模型,W-LSTM组合预测模型具有更好的预测性能,预测结果的平均绝对百分误差为9.21%。在此基础上,使用最优预测模型对京津冀城市群2019年7月—2020年12月二氧化氮日均浓度进行了预测,并描绘了时空分布图用以表征其时空变化特征。     

应用递推GM（1,1）模型预测废气排放量

一、概述灰色系统理论中的一阶单变量预测模型GM(1,1),目前在环境预测实践中异常活跃,仅最近一段时间就有多种杂志刊登了多篇此类文章.总的来说,这些文章有以下两个特点:1.应用领域的拓广.如应用于港口油污染预测,降水pH值预测,城市环境综合整治定量考核指标预测,工业废渣产生量预测,大气悬浮颗粒物浓度预测,水污染控制系统中应用等等.2.预测方法的应用.如采用残差再度建模修正的方法,新陈代谢模型(等维信息模型)方法,拓扑预测方法,灾变预测方法等等.从根本上而言,这些应用实践均基于同样的建模原理及辨识方法(本文称之为普通GM(1,1)模型),即为连续的微分模型.本文将这种建模原理及辨识方法作适当的改变,介绍一种递推的差分模型,并应用于     

污水处理厂还原硫化物和臭气浓度的电子鼻监测技术探究

用电子鼻监测技术探究污水处理厂还原硫化物质量浓度和臭气质量浓度预测方法。结果表明,使用响应面分析法(RSM)建立还原硫化物质量浓度与电子鼻响应值关系,构建还原硫化物质量浓度预测模型,准确率可达95%。使用偏最小二乘法(PLS)建立不同质量浓度还原硫化物的传感器响应值与对应臭气质量浓度之间的关系,构建臭气浓度预测模型,并用实际样品验证。     

基于BP神经网络的儿童卧室内灰尘PAEs浓度预测

在实测数据的基础上,以邻苯二甲酸酯(PAEs)的各类影响因素为自变量,PAEs浓度为因变量,采用Back-propagation(BP)神经网络建立儿童卧室内PAEs浓度预测模型.结果表明,该模型的预测效果较理想,其中,STD比值均＞0.5,NMB均接近0,EMR均＜19％.以室内环境与儿童健康(CCHH)课题组天津地...     

基于决策树技术及在线监测的水质预测

利用北方某城市水源的水质在线监测系统,建立了基于决策树技术,具有较强可视性和实际应用,以及能预测次日源水中叶绿素水平的决策树模型.该模型将某城市水源在线监测的溶解氧和太阳辐射照度数据转换计算为每日平均标准偏差及均值,并与每日定时取样测定的叶绿素含量一起作为预测因子,通过将115组数据的前100组数据作为训练集建立预测次日叶绿素水平决策树模型,并采用后15组数据进行模型的仿真预测检验,结果只有3 d的预测出错,预测准确率达80%.并讨论了模型建立对数据的要求及解读预测规则等问题.     

1976-2005年唐山地区降水变化规律及干旱预测

利用唐山市1976-2005年各县年降水序列，分析了该市降水的空间分布规律和时间变化特点。采用灰色系统的灾变预测方法，对各县分别建立了GM（1，1）模型，进行未来25年唐山市各站的干旱年预测。利用残差检验、后验差检验和关联度检验对各模型分别进行了精度检验。结果表明，预测模型精度较高，可以对唐山市各县未来的干旱年进行预测，从而为科学决策提供依据。     

中红外光谱法快速测定车内空气中多组分有机污染物

随着汽车进入家庭,车内空气质量越来越受到人们的重视,亟需建立一种车内空气中有机污染物的快速测定方法以满足日常监测需要。将中红外光谱技术与化学计量学方法相结合,建立了一种快速测定车内空气中苯系物的方法。以偏最小二乘法(PLS)建立分析预测模型,并对光谱预处理方法、主因子数进行了优化。最佳校正模型对苯、甲苯、二甲苯浓度的校正均方差、预测均方差和交叉验证均方差分别为0.0089、0.0200和0.1115,0.0116、0.0011 和0.1398以及0.0137、0.0037和0.1390。研究表明,该方法具有较高的准确度和较好的适用性,用于测定车内空气中苯系物的浓度是可行的,并能大大提高车内空气质量监测的效率。     

灰色模型在岩溶地下水水质预测中的应用研究

运用灰色理论建立水质预测模型,通过对水质指标拟合值与实测值差异性分析,判断模型精密度,并预测山东省东阿县下马头水源地未来2年的水质变化趋势,结果表明:在4项水质指标预测模型中,总硬度、氟化物指标的GM(1,1)时间响应预测模型拟合结果较好;溶解性总固体、硝酸盐指标的GM(1,1)时间响应预测模型精密度均为3级,不适合指标的预测;未来2年下马头水源地岩溶地下水水质良好。     

基于KZ滤波法的江淮地区PM2.5浓度变化影响分析

基于2018—2020年合肥、芜湖和马鞍山3个城市国控站点的PM_2.5逐日监测数据和同期地面气象观测资料，利用Kolmogorov-Zurbenko(KZ)滤波对PM_2.5日浓度的原始时间序列进行分解，获取短期分量、季节分量和长期分量，并进行多元线性逐步回归构建各分量与气象因子的模型，最后依据短期分量和基线分量的回归模型和残差分析，对序列进行重建，获取消除气象条件影响的PM_2.5长期分量。KZ滤波分析结果表明：2018—2020年气象条件对江淮区域PM_2.5污染改善影响存在波动，在2018—2019年为负贡献，而在2020年秋冬季则变为正贡献；江淮地区3个城市2018年和2020年PM_2.5修正后的长期分量均值表明气象条件对各市PM_2.5改善影响存在差异较大，气象条件对合肥PM_2.5改善的贡献仅为1.0%,芜湖为7.8%,马鞍山为21.0%;NAQPMS数值模式情景分析结果显示，减排措施对江淮之间PM_2.5浓度改...     

釜溪河自贡城区段季节性低氧成因研究

釜溪河为沱江一级支流,在自贡城区段设有国考碳研所断面。收集碳研所断面近10年来水质自动站数据,分析溶解氧(DO)变化特征,采样调查釜溪河自贡城区段水质及河道底泥污染状况,采用相关性分析、数值模拟等,研究分析釜溪河自贡城区段溶解氧分布特征及碳研所断面季节性低氧成因。研究结果表明,碳研所断面的溶解氧质量浓度变化特征呈现春末夏初最低,白天高晚上低的特征。釜溪河碳研所断面河水耗氧类污染物质量浓度较沱江流域内其他断面高,耗氧强度较大,溶解氧质量浓度较沱江流域其他断面偏低;其次,研究河段中釜溪河污水厂以下河段受污水厂低氧水排入和金子凼堰底层低氧水下泄影响,其溶解氧水平整体较污水厂以上河段低;最后,河段底泥有机质含量较高,春夏季气温升高将导致微生物分解活性增强大量消耗溶解氧,同时,闸坝和外来水体排入的水文扰动造成污水厂以下河段水温梯度弱,表层溶解氧易受底层低氧水影响,促使断面形成季节性低氧现象。溶解氧预测模型结果也进一步证实了温度变化和垂向温度梯度弱是碳研所断面溶解氧质量浓度季节性偏低的主要因素。     

A2/O工艺脱氮除磷运行效果分析

采用统计学方法对新疆某污水处理厂A2/O工艺进行进水水质数据分析,发现数据存在严重自相关现象,运用主成分消除法和岭回归消除法以消除自相关性。结果表明：TN和TP是污水厂提标改造的关键;碳源匮乏和缺氧区存在溶解氧(DO)是TN去除不佳的主要原因;适当提高污泥浓度(MLSS)和水力停留时间(HRT)是强化TP去除的措施;温度是影响脱氮除磷的主要因素。将温度模型与自相关磷模型相结合,可提高磷模型精度,有利于出水TP的预测。降低DO、增加外碳源,控制MLSS为3 500 mg/L~4 500 mg/L、HRT为5.4 h~8.0 h、厌氧区和好氧区DO为0.3 mg/L和2 mg/L、污泥龄（SRT）为11 d~12 d,可提升工艺脱氮除磷效果。     

Soil water content forecasting by ANN and SVM hybrid architecture

Soil water content prediction is essential to the development of advanced agriculture information systems. Because soil water content series are inherently noise and non-stationary, it is difficult to get an accurate forecasting result. Considering the problems, in this paper, a novel hybrid learning architecture is proposed according to divide-and-conquer principle, the forecasting accuracy is improved. This novel hierarchical architecture is composed of ANN (Kohonen neural network) and SVM (support vector machine). The Kohonen network is used as a classifier, which partitions the whole input space into several distinct feature regions. Then, the best SVM predictor combined with an appropriate kernel function can be achieved for correspondence regions. The experimental results based on the hybrid model exhibit good agreement with actual soil water content measurements and outperform ANN and SVM single-stage models.     

Soil Water Content Estimated by Support Vector Machine for the Assessment of Shallow Landslides Triggering: the Role of Antecedent Meteorological Conditions

Soil water content is a key parameter for representing water dynamics in soils. Its prediction is fundamental for different practical applications, such as identifying shallow landslides triggering. Support vector machine (SVM) is a machine learning technique, which can be used to predict the temporal trend of a quantity since training from past data. SVM was applied to a test slope of Oltrepò Pavese (northern Italy), where meteorological parameters coupled with soil water content at different depths (0.2, 0.4, 0.6, 1.0, 1.2, 1.4 m) were measured. Two SVM models were developed for water content assessment: (i) model 1, considering rainfall amount, air temperature, air humidity, net solar radiation, and wind speed; (ii) model 2, considering the same predictors of model 1 together with antecedent condition parameters (cumulated rainfall of 7, 30, and 60 days; mean air temperature of 7, 30, and 60 days). SVM model 2 showed significantly higher satisfactory results than model 1, for both training and test phases and for all the considered soil levels. SVM models trends were implemented in a methodology of slope safety factor assessment. For a real event occurred in the tested slope, the triggering time was correctly predicted using data estimated by SVM model based on antecedent meteorological conditions. This confirms the necessity of including these predictors for building a SVM technique able to estimate correctly soil moisture dynamics in time. The results of this paper show a promising potential application of the SVM methodologies for modeling soil moisture required in slope stability analysis.     

南京市地表水溶解氧分布特征及低氧成因初探——以外秦淮河七桥瓮为例

于2018—2021年对南京市及国考断面七桥瓮进行水质调查,分析其溶解氧变化特征,采用水质水量联合评价及皮尔逊相关分析法,并结合水文气象等相关信息,对南京市地表水溶解氧分布特征及国考七桥瓮断面低氧成因进行研究分析。结果表明,南京市地表水溶解氧浓度夏季最低,中心主城区及附近区域溶解氧浓度均相对较低。七桥瓮断面溶解氧浓度在2.25~11.07 mg/L,其中5—9月溶解氧易出现超标波动。溶解氧浓度昼间高于夜间,与pH值呈正相关关系,与水温、高锰酸盐指数、氨氮、总磷均呈负相关关系。水温和上游来水带入的耗氧污染物是七桥瓮断面溶解氧偏低的主要成因,其中,溶解氧浓度与水温相关性最为显著。研究结论可为七桥瓮断面稳定达标提供基础支撑,为秦淮河流域精准治污提供技术依据,为南京市水环境多源同治提供治理思路。     

Monitoring sediment oxygen demand for assessment of dissolved oxygen distribution in river

Sediment oxygen demand (SOD) has become an integral part of modeling dissolved oxygen (DO) within surface water bodies. Because very few data on SOD are available, it is common for modeler to take SOD values from literature for use within DO models. SOD is such an important parameter in modeling DO that this approach may lead to erroneous results. This paper reported on developing an approach for monitoring sediment oxygen demand conducted with undisturbed sediment core samples, where the measured results were incorporated into a water quality model for simulating and assessing dissolved oxygen distribution in the Xindian River of northern Taiwan. The measured results indicate that a higher freshwater discharge results in a lower SOD. Throughout a 1-year observation in 2004, the measured SOD ranged from 0.367 to 1.246 g/m(2)/day at the temperature of 20°C. The mean values of the measured SOD at each station were adopted in a vertical two-dimensional water quality model to simulate the DO distribution along the Xindian River. The simulating results accurately depict the field-measured DO distribution during the low and high flow conditions. Model sensitivity analyses were also conducted with increasing and decreasing SOD values for the low and high flow conditions and revealed that SOD had a significant impact on the DO distribution along the Xindian River. The present work combined with field measurements and numerical simulation should assist in river water quality management.     

右江百色水库下游断面低溶解氧形成原因分析

广西右江东笋断面溶解氧(DO)呈现5—11月浓度较低,12月及1—4月浓度较高的变化规律。从水温、藻类呼吸、沉积物耗氧、有机物耗氧、上游来水等方面分析了东笋断面低DO形成的原因。结果表明,5—11月东笋断面DO浓度较低,主要是受夏季高温和水利工程运行等非污染型因素的影响。右江流域夏秋季水温较高,限制了水体DO浓度的上限。热分层现象导致百色水库中层水体DO浓度较低,而水利枢纽发电时的下泄水正是中层水体,因此,下泄水DO浓度低是导致5—11月东笋断面DO浓度低的主要原因。东笋河段沉积物和有机物耗氧对DO浓度的影响很小,藻类呼吸作用对DO浓度的影响有限。     

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.     

Estimation of suspended sediment concentration in rivers using acoustic methods

Acoustic Doppler current meters (ADV, ADCP, and ADP) are widely used in water systems to measure flow velocities and velocity profiles. Although these meters are designed for flow velocity measurements, they can also provide information defining the quantity of particulate matter in the water, after appropriate calibration. When an acoustic instrument is calibrated for a water system, no additional sensor is needed to measure suspended sediment concentration (SSC). This provides the simultaneous measurements of velocity and concentration required for most sediment transport studies. The performance of acoustic Doppler current meters for measuring SSC was investigated in different studies where signal-to-noise ratio (SNR) and suspended sediment concentration were related using different formulations. However, these studies were each limited to a single study site where neither the effect of particle size nor the effect of temperature was investigated. In this study, different parameters that affect the performance of an ADV for the prediction of SSC are investigated. In order to investigate the reliability of an ADV for SSC measurements in different environments, flow and SSC measurements were made in different streams located in the Aegean region of Turkey having different soil types. Soil samples were collected from all measuring stations and particle size analysis was conducted by mechanical means. Multivariate analysis was utilized to investigate the effect of soil type and water temperature on the measurements. Statistical analysis indicates that SNR readings ob tained from the ADV are affected by water temperature and particle size distribution of the soil, as expected, and a prediction model is presented relating SNR readings to SSC mea surements where both water temperature and sediment characteristics type are incorporated into the model. The coefficients of the suggested model were obtained using the multivariate anal ysis. Effect of high turbidity conditions on ADV performance was also investigated during and after rain events.     

Water Quality Assessment and Modeling of an Effluent-Dominated Stream, the Notwane River, Botswana

In an effort to assess current and future water quality of the only perennial river in southeastern Botswana, this study presents water quality monitoring and modeling results for the effluent-dependent Notwane River. The water quality along the Notwane River, pre- and post-implementation of secondary wastewater treatment, was compared and results demonstrated that water quality improved after the new wastewater treatment plant (WWTP) went online. However, stream standards for chemical oxygen demand, total dissolved phosphorous, and fecal coliform were exceeded in most locations and the critical dissolved oxygen (DO) reached concentrations of less than 4 mg L⁻¹. High dissolved P concentrations and intense macrophyte growth at the impounding ponds and at sites within 30 km of the effluent waste stream confluence suggest that eutrophication was a function of P release from the ponds. Results of DO modeling demonstrated that an unpolluted inflow at approximately 10 km downstream of the confluence was responsible for raising DO concentrations by 2.3 mg L⁻¹, while SOD was responsible for a decline in DO concentrations of 1.4 mg L⁻¹ at 6 km downstream of the confluence. Simulations also showed higher DO concentrations during winter months, when water temperatures were lower. Simulations, in which the distributed biochemical oxygen demand (BOD) loading from cattle excrement was decreased, produced nominal increases in DO concentrations. An increase in WWTP BOD loadings to projected 2020 values resulted in a 1.3 mg L⁻¹ decrease in the critical DO concentration. Furthermore, a decrease in treatment plant efficiency, from 94% to 70% BOD removal, produced critical DO concentrations and anoxia along much of the modeled reach. This has significant implications for Gaborone, especially if decreased WWTP efficiency occurs as a result of the expected future increase in pollutant loadings.