Effects of eutrophication and organic loading on the occurrence of profundal harpacticoids in a lake in southern Finland

Harpacticoids made up 19 and 30% of the meiobenthos proper by number and 39 and 55% by biomass at maximum depths and a depth of 20 m, respectively, in Lake Päijänne. Harpacticoids accounted for higher proportions of the total meiobenthos in oligotrophic and unpolluted areas than in polluted areas. Seven species were identified, with Canthocamptus staphylinus confined to semi-lotic areas influenced by organic pollution from a pulp mill. Other species exhibited somewhat different distributions in oligotrophic and mesotrophic areas. Harpacticoid densities were most closely correlated with oxygen content and phytoplankton biomass, and correlations with environmental values were closer at maximum depths than at 20 m. Attheyella crassa densities in the deepest zone had most marked negative correlation with total phosphorus, phytoplankton biomass, dissolved organic matter and organic sedimentation, while Paracamptus schmeili had the closest positive correlation with oxygen content. High densities of these species could be classified as an indicator of oligotrophic conditions. Similar correlations, although weaker, were evident for Bryocamptus minutus and still weaker for Bryocamptus echinatus and Moraria brevipes. Clustering of the stations based on harpacticoid abundances gave a similar result to clustering based on environmental data, particularly in the 20 m zone.     

太湖蓝藻水华暴发程度年度预测

近年来,尽管太湖主要水质指标有所改善,但蓝藻水华暴发的频次和面积并未明显减少。为了探讨太湖蓝藻水华暴发的环境驱动因子,统计了2012—2020年历年4—10月预警期间的太湖蓝藻水华发生规模与频次,结合同步浮标自动监测数据和实验室分析数据,构建了蓝藻水华预测模型。以太湖蓝藻水华综合指数(I_c)表征蓝藻水华强度,并通过I_c与环境因子的相关性分析,筛选出1月水温、1月电导率、1月生化需氧量和3月总氮浓度4项环境指标,最终构建了以该4项环境指标为自变量、I_c为因变量的太湖年度蓝藻水华强度多元线性回归预测模型。该预测模型的决定系数达到了0.908,平均相对误差为10.35%,预测精度总体表现较好。     

Multivariate Analysis of Interactions Between Phytoplankton Biomass and Environmental Variables in Taihu Lake, China

Phytoplankton variation in large shallow eutrophic lakes is characterized by high spatial and temporal heterogenity. Understanding the pattern of phytoplankton variation and the relationships between it and environmental variables can contribute to eutrophic lakes management. In this study Taihu Lake, one of the largest eutrophic fresh water lake in China, was taken as study area. The water body of Taihu Lake was divided into five regions viz. Wuli bay (WB), Meilian Bay (MB), West Taihu Lake (WTL), Main Body of Taihu Lake (MBTL) and East Taihu Lake (ETL). Concentrations of chlorophyll-a and the related environmental variables were determined in each region in the period 2000–2003. Factor analysis and multivariate analysis were applied to evaluate the interactions between phytoplankton variation and environmental variables. Results showed that the highest average concentrations of TN, TP and Chl-a were observed in WB, followed in a descending order by MB and WTL, and the lowest concentrations of TN, TP and Chl-a were observed in MBTL and ETL. Chl-a and TP concentrations in most regions (except ETL) declined during the study period. It suggested that to some extent the lake was recovering from eutrophication. However, persistent ascending of TN and NH₄–N in all five regions indicated the deteriorating of water quality in the study period. Results of multivariate showed that the relationships between phytoplankton biomass and environmental variables varied among regions. TP illustrated itself a controlling role on phytoplankton in WB, MB, WTL and MBTL according to the significant positive relations to phytoplankton biomass in these regions. Nitrogen could be identified as a limiting factor to phytoplankton biomass in ETL in view of the positive correlations between TN and phytoplankton and between NH₄–N and phytoplankton. Spatial variation of interactions between phytoplankton and environmental parameters suggested proper eutrophication control measures were needed to restore ecological system in each region of Taihu Lake.     

SPATIAL ANALYSIS AND EUTROPHICATION ASSESSMENT FOR CHLOROPHYLL a IN TAIHU LAKE

Spatial structure analysis and kriging analysis have been identified to be useful tools in illustrating the spatial patterns of variables. Taihu Lake is one of the largest fresh water lakes in China, and has suffered serious eutrophication in recent years due to the rapid economic development and growing environmental pollution in the Taihu Catchment. In this paper, spatial structural analysis, kriging interpolation and eutrophication assessment were carried out for chlorophyll a in the lake. Studies show that spherical model could be applied to fit all experimental variograms. Positive nuggets were observed for three directions except NE–SW direction. The variograms show some anisotropy with anisotropic ratio falling within 1.76. The spatial structural patterns of chlorophyll a in the lake were affected by factors such as distribution of pollution sources, water flow and wind. Two-dimensional ordinary block kriging was applied for interpolation process. An eutrophication assessment map was also made based on a water-quality evaluation standard. Results show that the content of chlorophyll a in Taihu Lake was quite high. The whole lake has suffered serious eutrophication. However, the eutrophic situation varied in space. Higher contents of chlorophyll a appeared mainly in the northern part of the lake.     

2012—2019年松花江干流底栖动物群落变化及其对水环境因子的响应

底栖动物是水生态系统的重要组成部分,其群落特征通常用来评价水生态环境质量。研究了2012—2019年松花江干流水生态环境质量状况、变化趋势,并应用冗余分析(RDA)探究底栖动物群落结构特征与水环境因子之间的响应关系。结果表明:8年间共鉴定出底栖动物246个分类单元,隶属于4门、9纲、25目、58科、69属,其中水生昆虫的EPT物种为99个分类单元,占总物种数的40.24%;水生昆虫的其他物种为68个分类单元,占总物种数的27.64%;软体动物为36个分类单元,占总物种数的14.63%;环节动物为25个分类单元,占总物种数的10.16%;甲壳动物为18个分类单元,占总物种数的7.32%。底栖动物密度总体呈上升趋势,种类组成总体有所增多,其中环节动物、软体动物和甲壳动物有向水生昆虫转变的趋势,群落结构相对稳定且主要以水生昆虫占比最多,底栖动物密度平均值为5.97×10³个/m²,变化范围为2.86×10³~8.98×10³个/m²,优势科(属)主要为小蜉属Ephemerella、小寡脉蜉属Oligoneuriella、扁蜉属Heptagenia、等蜉属Isonychia、纹石蛾科Hydropsychidae、缺叉多距石蛾属Polycentropus、摇蚊科Chironomidae和圆田螺属Cipangopaludina等。生物指数评价结果多数为"中等"及以上,评价结果趋于稳定,且下游评价结果好于上游。松花江干流的水环境质量变化阶段性明显,溶解氧含量升高,氨氮呈下降趋势,其余指标呈波动变化。冗余分析(RDA)结果表明:影响松花江干流底栖动物群落结构变化的主要环境因子是随时间推移而变化的,其中溶解氧、生化需氧量、化学需氧量、总磷、氨氮和总氮等指标是影响该监测区域底栖动物群落分布的重要环境因子。     

Biological Indicators of Marine Environmental Health: Meiofauna – A Neglected Benthic Component?

This paper considers the use of meiofauna (benthic metazoa 45 to 500 m in size) as biological indicators for monitoring marine environmental health. To date, this abundant and ubiquitous group of invertebrates has been largely neglected in applied sampling programmes; instead, emphasis has been placed upon more conspicuous biological components such as seagrass, macrofauna and epiphytes. In an attempt to redress this balance, this paper sets out three objectives: (1) to explain the reasons for selecting biological response indicators from across the whole spectrum of phylogenetic organisation, (2) to summarise those aspects of meiofaunal life-history and demography that render this group suitable for monitoring anthropogenic pollution and disturbance, (3) to suggest how to optimise the inclusion of meiofauna in monitoring programmes so that they provide maximum information for management purposes. To achieve these objectives the environmental impact assessment framework of Ward and Jacoby (1992) is adopted as a matrix into which the relevant components of meiofaunal ecology are fitted. Using this matrix, meiofauna are shown to have advantages that include their sessile habit, high species diversity, short generation time, direct benthic development and ubiquitous distribution. Disadvantages include their small size, high level of spatial and temporal variability, the potential cost of sample processing and the limited taxonomic literature accessible to non-specialist workers. The paper concludes with a discussion of sampling strategies and methods of analysis that may be used to efficiently incorporate meiofauna as biological response indices into environmental monitoring. Emphasis is placed on cost-effective techniques such as taxonomic minimalism.     

A Multivariate Analysis of Biophysical Parameters of Tallgrass Prairie Among Land Management Practices and Years

Six treatments of eastern Kansas tallgrass prairie – native prairie, hayed, mowed, grazed, burned and untreated – were studied to examine the biophysical effects of land management practices on grasslands. On each treatment, measurements of plant biomass, leaf area index, plant cover, leaf moisture and soil moisture were collected. In addition, measurements were taken of the Normalized Difference VegetationIndex (NDVI), which is derived from spectral reflectance measurements. Measurements were taken in mid-June, mid-July and late summer of 1990 and 1991. Multivariate analysis of variance was used to determine whether there were differences in the set of variables among treatments and years. Follow-up tests included univariate t-tests to determine whichvariables were contributing to any significant difference. Results showed a significant difference (p < 0.0005) among treatments in the composite of parameters during each of the months sampled. In most treatment types, there was asignificant difference between years within each month. The univariate tests showed, however, that only some variables, primarily soil moisture, were contributing to this difference. We conclude that biomass and % plant cover show the best potential to serve as long-term indicators of grassland condition as they generally were sensitive to effects ofdifferent land management practices but not to yearlychange in weather conditions. NDVI was insensitive to precipitation differences between years in July for most treatments, but was not in the native prairie. Choice of sampling time is important for these parameters to serve effectively as indicators.     

European Farmland Bird Distribution Explained by Remotely Sensed Phenological Indices

Birds are important components of biodiversity conservation since they are capable of indicating changes in the general status of wildlife and of the countryside. The Pan-European Common Bird Monitoring Scheme (PECBM) has been launched by the BirdLife Partnership in Europe, where the European Bird Census Council has been collecting data from 20 independent breeding bird survey programs across Europe over the last 25 years. These data show dramatic declines in European farmland birds. We suggest that seasonal characteristics of vegetation cover derived from high temporal resolution remote sensing images could facilitate the monitoring the suitability of farmland bird habitats, and that these indicators may be a better choice for monitoring than climate data. We used redundancy analysis to link the PECBM data of the estimated number of farmland birds in Europe to a set of phenological and climatic indicators and to the biogeographic regions of Europe. Variance partitioning was used to account for the variation explained by the phenological and climate variables and by the area of the environmental strata individually, to define the pure effect of the variables, and to extract the total explained variance. The analysis revealed high statistical significance (p < 0.001) of the correlations between species and environment. Phenological indices explained 38% of the variance in community composition of the 23 farmland bird species, whereas climate explained 30% of the variance. After partitioning the other variables as covariables, the pure effect of phenology, climate, and environmental strata were 16%, 8%, and 16%, respectively. Based on the probability results, we suggest that phenological indicators derived from remote sensing may supply better indicators for continental scale biodiversity studies than climate only. In addition, these indicators are cost and time effective, are on continuous scale, and are readily repeatable on a large spatial coverage while supplying standardized results.     

滇池浮游藻类群落构成调查

对滇池浮游藻类群落组成和空间分布开展了2次调查,鉴定出藻类8门66属159种及变种,绿藻种类最多,蓝藻次之。5、12月滇池全湖平均藻类密度分别为1.398×108、2.180×108个/升,蓝藻门微囊藻属为优势藻类。5月的调查中滇池外海藻类生物量呈北高南低的格局,而12月则呈现南部和中部高,北部低。外海的藻类生物量明显高于草海,草海藻类群落构成与外海明显不同,主要表现为绿藻门藻类所占比例较高。12月滇池外海及全湖藻类生物量都显著高于5月。与上一次(2006—2007年)滇池浮游藻类的系统调查相比,滇池(主要是外海)浮游藻类在物种数量、常见藻类、优势藻类及生物量水平方面与之接近。     

Seasonal baseline of nutrients and stable isotopes in a saline lake of Argentina: biogeochemical processes and river runoff effects

The seasonal variability of inorganic and organic nutrients and stable isotopes and their relations with plankton and environmental conditions were monitored in Lake Chasicó. Principal component analysis evidenced the strong influence of the river runoff on several biogeochemical variables. Silicate concentrations were controlled by diatom biomass and river discharge. Higher values of nitrate and soluble reactive phosphorus (SRP) indicated agricultural uses in the river basin. Elevated pH values (～9) inhibiting nitrification in the lake explained partially the dominance of ammonium: ～83 % of dissolved inorganic nitrogen (DIN). The low DIN/SRP ratio inferred nitrogen limitation, although the hypotheses of iron and CO₂ limitation are relevant in alkaline lakes. Particulate organic matter (POM) and dissolved organic matter (DOM) were mainly of autochthonous origin. The main allochthonous input was imported by the river as POM owning to the arid conditions. Dissolved organic carbon was likely top-down regulated by the bacterioplankton grazer Brachionus plicatilis. The δ¹³C signature was a good indicator of primary production and its values were influenced probably by CO₂ limitation. The δ¹⁵N did not evidence nitrogen fixation and suggested the effects of anthropogenic activities. The preservation of a good water quality in the lake is crucial for resource management.     

基于环境DNA宏条形码的太湖流域底栖动物监测与生态健康评价

大型底栖动物是生态环境监测和评估的主要目标生物类群之一。环境DNA宏条形码技术的发展为提高底栖动物多样性监测的通量、精准性、标准化程度提供了新的机遇,但该方法在我国尚未有流域尺度的应用先例,其结果的可靠性和对生态环境健康状况的指示性有待检验。率先将环境DNA宏条形码技术用于太湖流域65个点位的底栖动物监测和流域生态健康评价,并与同步进行的形态学监测结果进行了比较。结果表明:①环境DNA方法能检出更多的底栖动物类群,在科、属、种水平上检出的分类单元数分别是形态学监测结果的106%、132%、155%;②基于环境DNA技术的检测方法能够很好地识别形态学监测结果中的优势物种,检出的科级、属级分类阶元能够覆盖形态学监测结果中90%以上的生物量和个体数,同时包含60%以上的物种数;③两种方法对同一物种的检出频次显著相关(R²>0.7,P<0.0001),总体检出一致率达72.3%;④在底栖动物完整性指数(B-IBI)方面,环境DNA方法与形态学方法的计算结果显著相关(R²=0.235,P<0.0001),94%的点位的B-IBI等级划分误差在1级以内,且两种方法的计算结果在底栖动物完整性的流域空间格局描绘上高度重合。综上所述,环境DNA宏条形码技术在太湖流域底栖动物群落监测和评价中的整体应用结果表明,环境DNA监测方法结果可靠,将其进一步规模化应用有望显著提高我国水生态系统生物监测结果的准确性和生态健康评价的技术水平。     

A mixed model-based Johnson's relative weights for eco-efficiency assessment: The case for global food consumption

Eco-efficiency composite indicators are widely accepted as the ratio of environmental impact to created economic value. These indicators are realistic measures for assessing sustainability performance considering the economy and environment. The weights reflect the importance of indicators to the aggregated environmental impacts. Estimating the relative weight of indicators is highly subjective, and therefore the search for a single unique weighting method has been going on for years. The regression-based weights are one of the most recent trends in sustainability modeling. Since these methods are designed initially to investigate the impact of multiple variables on a response variable rather than to estimate weights, some drawbacks are associated with their potential to provide proper weights. This paper presents a novel weighting approach integrating linear mixed-effect models with Johnson's relative weights to address these drawbacks and provide meaningful relative weights for eco-efficiency composite indicators. The proposed approach's operational and computational procedures are illustrated using a real example, and the eco-efficiency of food consumption of 38 countries is estimated for the period between 1990 and 2012 using a consumption-based sustainability accounting method. The findings have shown that energy use and GHG indicators are the most critical contributor to global food consumption's environmental impacts. The country-based eco-efficiency performance in this work has shown that China, India, and Russia are located in the low eco-efficiency score class. The Spatio-temporal analysis downgraded the geographical location's significance on the trends of eco-efficiency behavior in time and space. On the other hand, it revealed the different types of emerging hot spots over the world.     

Importance of eating habits and sample size in the estimation of environmental mercury contamination using biological indicators

The importance of eating habits and the number of fish sampled in the estimation of mercury environmental contamination through biological indicators was studied. The species used were one with piscivorous habits (Anguilla anguilla) and another with omnivorous habits (Ciprinus carpio). From one original sample for each species, randomized samples were generated using the subroutine GGSRS from the mathematics library IMSL, and later the statistical significance of Pearson's correlation coefficient for the relationship between fish weight and mercury concentrations in muscle was obtained for each random sample. The results show that the use of omnivorous species such as Ciprinus carpio as a biological indicator of contamination enables us to carry out estimations with a greater degree of confidence than when piscivorous species such as Anguilla anguilla are used.     

Selecting Variables for Habitat Suitability of <Emphasis Type="Italic">Asellus</Emphasis> (Crustacea,Isopoda) by Applying Input Variable Contribution Methods to Artificial Neural Network Models

This study aimed to compare different methods to analyse the contribution of individual river characteristics to predict the abundance of Asellus (Crustacea, Isopoda). Six methods which provide the relative contribution and/or the contribution profile of the input variables of artificial neural network models were therefore compared: (1) the ‘partial derivatives’ method; (2) the ‘weights’ method; (3) the ‘perturb’ method; (4) the ‘profile’ method; (5) the ‘classical stepwise’ method; (6) the ‘improved stepwise’ method. Consequently, the key variables which affect the habitat preferences of Asellus could be identified. To evaluate the performance of the artificial neural network model, the model predictions were compared with the results of a multiple linear regression analysis. The dataset consisted of 179 samples, collected over a 3-year period in the Zwalm catchment in Flanders, Belgium. Twenty-four environmental variables as well as the log-transformed abundance of Asellus were used in this study. The different contribution methods seemed to give similar results concerning the order of importance of the input variables. Nevertheless, their diverse computation led to differences in sensitivity and stability of the methods and the derived outcomes on the habitat preferences. From an ecological point of view, the environmental variables describing the stream type (width, depth, stream order and distance to mouth) were the most significant variables for Asellus in the Zwalm catchment during the period 2000–2002 for all applied methods. Indirectly, one can conclude that the water quality is not the limiting factor for the survival of Asellus in the Zwalm catchment.     

Application Of Artificial Neural Network Models To Analyse The Relationships Between Gammarus pulex L. (Crustacea, Amphipoda) And River Characteristics

This study aimed at analysing the relationship between river characteristics and abundance of Gammarus pulex. To this end, four methods which can identify the relative contribution and/or the contribution profile of the input variables in neural networks describing the habitat preferences of this species were compared: (i) the ‘PaD‘ (‘Partial Derivatives‘) method consists of a calculation of the partial derivatives of the output in relation to the input variables; (ii) the ‘Weights‘method is a computation using the connection weights of the backpropagation Artificial Neural Networks; (iii) the ‘Perturb‘method analyses the effect of a perturbation of the input variables on the output variable; (iv) the ‘Profile‘ method is a successive variation of one input variable while the others are kept constant at a fixed set of values. The dataset consisted of 179 samples, collected over a three-year period in the Zwalm river basin in Flanders, Belgium. Twenty-four environmental variables as well as the log-transformed abundance of Gammarus pulex were used in this study. The different contribution methods gave similar results concerning the order of importance of the input variables. Moreover, the stability of the methods was confirmed by gradually removing variables. Only in a limited number of cases a shift in the relative importance of the remaining input variables could be observed. Nevertheless, differences in sensitivity and stability of the methods were detected, probably as a result of the different calculation procedures. In this respect, the ‘PaD‘method made a more severe discrimination between minor and major contributing environmental variables in comparison to the ‘Weights‘, ‘Profile‘ and ‘Perturb‘ methods. From an ecological point of view, the input variables ‘Ammonium‘ and to a smaller extent ‘COD‘, were selected by these methods as dominant river characteristics for the prediction of the abundance of Gammarus pulex in this study area.     

A survey of Pb,Cu, Zn,Cd, Cr,As, and Se in earthworms and soil from diverse sites

Earthworms and soils were collected from 20 diverse sites in Maryland, Pennsylvania, and Virginia, and were analyzed for Pb, Cu, Zn, Cd, Cr, As, and Se. Correlation coefficients relating concentrations of the elements in earthworms to concentrations in soil were low (–0.20<r<+0.57). Species differences and ecological variables contributed to the variability in concentrations of these elements in earthworms. The maximum concentrations of Pb (2100 ppm), Zn (1600 ppm), Cd (23 ppm) and Se (7.6 ppm) detected in earthworms were in the range reported to be toxic to animals fed diets containing these elements; however, even in the absence of any environmental contamination, some species of earthworms may contain high concentrations of Pb, Zn, and Se. Earthworms of the genus Eisenoides, for example, were exceptional in their ability to concentrate Pb. When earthworms are used as indicators of environmental contamination, it is important to identify the species, to report the soil characteristics, and to collect similar earthworms from very similar but uncontaminated soil.     

空间关联随机森林模型结合Sentinel-2影像估算潍北地区裸土期土壤盐分

土壤盐分含量(SSC)是评价土地退化和肥力水平的重要指标,实现SSC状态和空间分异的快速准确监测对区域环境的优化管理极为关键。选取潍北平原为研究区,野外采集233处土壤样品并获取同时相Sentinel-2多光谱影像,进一步将特征光谱波段和构建的最优光谱指数作为输入自变量,测试得到的SSC实测值为因变量,最后将空间关联函数引入到随机森林中去建立基于空间关联随机森林算法的SSC遥感估算模型,完成区域尺度上的SSC反演估算与空间制图。结果表明：影像的B3、B8和B11是SSC的特征波段,通过波段比值变换能够增强卫星光谱信号对SSC的吸收响应,筛选得到的最优光谱指数分别为RI₃₄(波段3和波段4的反射率比值)、RI₇₁₁(波段7和波段11的反射率比值)、ND₆₁₁(波段6和波段11的反射率归一化值)和D₄₅(波段4和波段5的反射率差值);仅用特征波段或最优光谱指数来构建模型不能取得满意的SSC估算精度,空间关联随机森林模型的SSC估算精度要高于随机森林模型;在将上述特征波段和最优光谱指数共同输入空间关联随机...     

农村环境质量综合评价技术体系区域适用性验证

长期以来,中国农村环境保护工作基础相对薄弱,国家环保部门于2014年出台《农村环境质量综合评价技术规定(试行)》。研究利用2015—2016年安徽省域的农村环境监测数据,将安徽省重点生态功能区考核县域的数据与其他县域监测数据进行分类整理,采用该技术规定开展农村环境质量综合评价,对评价体系的3个级别指标层面的评价结果进行对比,并通过2组数据的差异性分析,深度剖析评价体系各级指数的结果合理性,验证该评价技术规定的区域适用性;同时,根据各级指标对比中发现的问题,对评价体系的相关指标提出修改完善建议。     

基于“天-空-地”一体化的生态保护红线区监管评价体系构建及应用ADDINCNKISM.UserStyle

科学监管评价生态保护红线区生态环境是合理利用自然资源和充分保护生态环境的基础,对推动国家生态文明建设具有重要意义。该研究基于“天-空-地”一体化获取多源数据,结合GIS和RS空间分析,从生态系统格局和质量、人类活动、环境限制4个方面选取25个指标,构建了生物多样性维护生态保护红线区监管评价体系,并以泰山生态保护红线区为例进行分析研究。结果表明:2000—2015年,研究区生态系统格局、生态系统质量、人类活动状况3个分指数得分及生态环境综合得分均呈现先降后升的趋势,就综合得分而言,2000—2005年、2005—2010年得分降幅分别为18.73%和5.24%,2010年得分最低(41.97分),而2010—2015年得分增幅为81.63%,2015年得分为76.23分,生态环境综合得分评价等级由Ⅱ级升为Ⅰ级。其中城乡居民和工矿用地面积占比、生态系统破碎度和分离度、植被生物量是影响研究区生态环境的关键指标,相关部门应加强对研究区边界处人类活动的监管,并注重生态系统完整性和植被生长状态的保护。该监管评价体系具有较强的实践性、科学性和可操作性,可为生态保护红线区的监管评价提供新思路。     

Hydrometeorological variables predict fecal indicator bacteria densities in freshwater: data-driven methods for variable selection

Statistical models of microbial water quality inform risk management for water recreation. Current research focuses on resource-intensive, location-specific data collection and water quality modeling, but this approach may be cost-prohibitive for risk managers responsible for numerous recreation sites. As an alternative, we tested the ability of two data-driven models, tree regression and random forests with conditional inference trees, to select readily available hydrometeorological variables for use in linear mixed effects (LME) models predicting bacterial density. The study included the Chicago Area Waterway System (CAWS) and Lake Michigan beaches and harbors in Chicago, Illinois, at which Escherichia coli and enterococci were measured seasonally in 2007–2009. Tree regression node variables reduced data dimensionality by >50 %. Variable importance ranks from random forests were used in a forward-step selection based on R ² and root mean squared prediction error (RMSPE). We found two to three variables explained bacteria densities well relative to random forests with all variables. LME models with tree- or forest-selected variables performed reasonably well (0.335?<?R ²?<?0.658). LME models for Lake Michigan had good prediction accuracy with respect to the single sample maximum standard (72–77 %), but limited sensitivity (23–62 %). Results suggest that our alternative approach is feasible and performs similarly to more resource-intensive approaches.