Microhabitat use by two small benthic stream fish in a 2nd order stream

Direct observation of two benthic fish species — the stone loach (Barbatula barbatula) and the gudgeon (Gobio gobio) — in the field revealed a spatial segregation between the species in a study area with shallow riffle and moderately deeper pool sections. Stone loach generally inhabited shallow, more current-exposed locations and gudgeon preferred deeper, mostly sandy areas. The small individuals of both species were confined to shallow muddy locations and the larger individuals were found in deeper and more current exposed areas. The main factor affecting microhabitat choice was the flow regime:

it was a limiting factor for the stone loach, where the discharge rates controlled the presence of fish in the study area.

distribution patterns of both species were influenced by discharge and by fluctuations in discharge.

The following mechanisms regulating the distribution of stone loach and gudgeon are hypothesized:

1. Gudgeon: They prefer high water depth, low current velocities and sandy substrate, which strongly limits their spatial niche. Mainly relatively small individuals (size class 2; 6—9 cm) changed microhabitat in relation to environmental parameters. Size class 3 (approx. 9—12 cm) may be interpreted as a rather unpredictable transitory period between juvenile and adult stage. Large gudgeon entered the observation area mainly when discharge rates were high and variable. Increasing discharge rates increased the spatial niche of the large gudgeon.
2. Stone loach: At low flow rates, the observation area seemed to be an optimal place for the stone loach. Changes in environmental conditions are reflected in the distribution patterns. The transition between juvenile and adult microhabitat use takes place in size class 2. Under high and/or variable flow regime the species was not found in the observation area.

     

The distribution of an invasive fish species is highly affected by the presence of native fish species: evidence based on species distribution modelling

Topmouth gudgeon (Pseudorasbora parva) is one of the most invasive aquatic fish species in Europe and causes adverse effects to ecosystem structure and functioning. Knowledge and understanding of the species’ interactions with the environment and with native fish are important to stop and prevent the further spread of the species. Creating species distribution models is a useful technique to determine which factors influence the occurrence and abundance of a species. We applied three different modelling techniques: general additive models, random forests and fuzzy habitat suitability modelling (FHSM) to assess the habitat suitability of topmouth gudgeon. The former two techniques indicated that the abundance of native fish (i.e. biotic variables) was more important than environmental variables when determining the abundance of topmouth gudgeon in Flanders (Belgium). Bitterling (Rhodeus amarus), stone loach (Barbatula barbatula), three-spined stickleback (Gasterosteus aculeatus) and predator abundance were selected as the most important biotic variables and implemented in the FHSM to investigate species interactions. Depending on the preferred food source and spawning behaviour, either coexistence or interspecific competition can occur with bitterling, stone loach and three-spined stickleback. In contrast, the presence of predators clearly had a top down effect on topmouth gudgeon abundance. These findings could be applied as a biological control measure and implemented in conservation strategies in order to reduce the abundance of earlier established populations of topmouth gudgeon.     

Microhabitat use and interspecific associations of introduced topmouth gudgeon Pseudorasbora parva and native fishes in a small stream

To address a lack of information on topmouth gudgeon Pseudorasbora parva introduced to watercourses, the microhabitat use of this non-native cyprinid and co-existing native species was assessed in a small stream located in southern England. Overall, microhabitat use was size-structured and significant associations were observed between topmouth gudgeon and native species, including brown trout Salmo trutta , chub Leuciscus cephalus , European bullhead Cottus gobio and stone loach Barbatula barbatula . Significant associations with environmental variables, however, were more frequent in native species than in topmouth gudgeon. Topmouth gudgeon demonstrated few habitat preferences, which were weak and limited to small specimens, emphasizing the species broad, plastic breadth of microhabitat use. This is expected to facilitate the species' successful invasion of novel aquatic systems.     

Empirical modelling of lake water-temperature relationships: a comparison of approaches

1.  As a result of the role that temperature plays in many aquatic processes, good predictive models of annual maximum near-surface lake water temperature across large spatial scales are needed, particularly given concerns regarding climate change. Comparisons of suitable modelling approaches are required to determine their relative merit and suitability for providing good predictions of current conditions. We developed models predicting annual maximum near-surface lake water temperatures for lakes across Canada using four statistical approaches: multiple regression, regression tree, artificial neural networks and Bayesian multiple regression.
2.  Annual maximum near-surface (from 0 to 2 m) lake water-temperature data were obtained for more than 13 000 lakes and were matched to geographic, climatic, lake morphology, physical habitat and water chemistry data. We modelled 2348 lakes and three subsets thereof encompassing different spatial scales and predictor variables to identify the relative importance of these variables at predicting lake temperature.
3.  Although artificial neural networks were marginally better for three of the four data sets, multiple regression was considered to provide the best solution based on the combination of model performance and computational complexity. Climatic variables and date of sampling were the most important variables for predicting water temperature in our models.
4.  Lake morphology did not play a substantial role in predicting lake temperature across any of the spatial scales. Maximum near-surface temperatures for Canadian lakes appeared to be dominated by large-scale climatic and geographic patterns, rather than lake-specific variables, such as lake morphology and water chemistry.     

An improved method for two-dimensional fluorescence monitoring of complex bioreactors

An improved method for deconvoluting complex spectral maps from bidimensional fluorescence monitoring is presented, relying on a combination of principal component analysis (PCA) and feedforward artificial neural networks (ANN). With the aim of reducing ANN complexity, spectral maps are first subjected to PCA, and the scores of the retained principal components are subsequently used as ANN input vector. The method is presented using the case study of an extractive membrane biofilm reactor, where fluorescence maps of a membrane-attached biofilm were analysed, which were collected under different reactor operating conditions. During ANN training, the spectral information is associated with process performance indicators. Originally, 231 excitation/emission pairs per fluorescence map were used as ANN input vector. Using PCA, each fluorescence map could be represented by a maximum of six principal components, thereby catching 99.5% of its variance. As a result, the dimension of the ANN input vector and hence the complexity of the artificial neural network was significantly reduced, and ANN training speed was increased. Correlations between principal components and ANN predicted process performance parameters were good with correlation coefficients in the order of 0.7 or higher.     

Use of artificial neural networks to accurately identify Cryptosporidium oocyst and Giardia cyst images

Cryptosporidium parvum and Giardia lamblia are protozoa capable of causing gastrointestinal diseases. Currently, these organisms are identified using immunofluorescent antibody (IFA)-based microscopy, and identification requires trained individuals for final confirmation. Since artificial neural networks (ANN) can provide an automated means of identification, thereby reducing human errors related to misidentification, ANN were developed to identify Cryptosporidium oocyst and Giardia cyst images. Digitized images of C. parvum oocysts and G. lamblia cysts stained with various commercial IFA reagents were used as positive controls. The images were captured using a color digital camera at 400 x (total magnification), processed, and converted into a binary numerical array. A variety of "negative" images were also captured and processed. The ANN were developed using these images and a rigorous training and testing protocol. The Cryptosporidium oocyst ANN were trained with 1,586 images, while Giardia cyst ANN were trained with 2,431 images. After training, the best-performing ANN were selected based on an initial testing performance against 100 images (50 positive and 50 negative images). The networks were validated against previously "unseen" images of 500 Cryptosporidium oocysts (250 positive, 250 negative) and 282 Giardia cysts (232 positive, 50 negative). The selected ANNs correctly identified 91.8 and 99.6% of the Cryptosporidium oocyst and Giardia cyst images, respectively. These results indicate that ANN technology can be an alternate to having trained personnel for detecting these pathogens and can be a boon to underdeveloped regions of the world where there is a chronic shortage of adequately skilled individuals to detect these pathogens.     

Optimization of culture parameters for extracellular protease production from a newly isolated Pseudomonas sp. using response surface and artificial neural network models

Radial basis function (RBF) artificial neural network (ANN) and response surface methodology (RSM) were used to build a predictive model of the combined effects of independent variables (pH, temperature, inoculum volume) for extracellular protease production from a newly isolated Pseudomonas sp. The optimum operating conditions obtained from the quadratic form of the RSM and ANN models were pH 7.6, temperature 38 °C, and inoculum volume of 1.5 with 58.5 U/ml of predicted protease activity within 24 h of incubation. The normalized percentage mean squared error obtained from ANN and RSM models were 0.05 and 0.1%, respectively. The results demonstrated an higher prediction accuracy of ANN compared to RSM. This superiority of ANN over other multi factorial approaches could make this estimation technique a very helpful tool for fermentation monitoring and control.     

Artificial neural network as an alternative to multiple regression analysis in optimizing formulation parameters of cytarabine liposomes

The objective of the study was to optimize the formulation parameters of cytarabine liposomes by using artificial neural networks (ANN) and multiple regression analysis using 3(3) factorial design (FD). As model formulations, 27 formulations were prepared. The formulation variables, drug (cytarabine)/lipid (phosphatidyl choline [PC] and cholesterol [Chol]) molar ratio (X1), PC/Chol in percentage ratio of total lipids (X2), and the volume of hydration medium (X3) were selected as the independent variables; and the percentage drug entrapment (PDE) was selected as the dependent variable. A set of causal factors was used as tutorial data for ANN and fed into a computer. The optimization was performed by minimizing the generalized distance between the predicted values of each response and the optimized one that was obtained individually. In case of 3(3) factorial design, a second-order full-model polynomial equation and a reduced model were established by subjecting the transformed values of independent variables to multiple regression analysis, and contour plots were drawn using the equation. The optimization methods developed by both ANN and FD were validated by preparing another 5 liposomal formulations. The predetermined PDE and the experimental data were compared with predicted data by paired t test, no statistically significant difference was observed. ANN showed less error compared with multiple regression analysis. These findings demonstrate that ANN provides more accurate prediction and is quite useful in the optimization of pharmaceutical formulations when compared with the multiple regression analysis method.     

Role of habitat degradation in determining fish distribution and abundance along the lowland Warta River, Poland

The distribution and abundance of fish collected in 1996–1998 are compared in three river sections X, Y and Z in the 808‐km‐long Warta River, Poland. The upper section, X, was least human‐modified, the middle section, Y, was the most polluted by industry and regulated, and the downstream section, Z, was moderately disturbed. The differences between X and Y in concentrations of dissolved oxygen, volatile phenols and nitrite nitrogen, and in the index of availability of hiding places, were highly significant because these parameters were several times worse in the Y section; in the Z section they assumed intermediate values. Although the abundance of certain fish species was changing along the downstream river gradient (i.e. differed the most between X and Z), both the Kohonen artificial neural network (SOM) and assemblage indices showed the biggest differences between X and Y, thus confirming the crucial role of the degradation of aquatic environment in shaping fish assemblages. The latter result ensued from the reaction of the rheophilic burbot, stone loach, gudgeon, chub and dace, which were most abundant in X, almost absent in Y and reoccurring in Z (although less numerous when compared with X). The opposite was recorded for mud loach, tench, ide and silver bream, which were most abundant in the degraded section Y, probably because of weak competition with the almost‐absent rheophils. The abundance of two generalists, roach and pike, was similar in all three sections, i.e. changed neither along the downstream nor in the degradation gradient.     

Habitat overlap between predatory benthic fish and their invertebrate prey in streams: the relative influence of spatial and temporal factors on predation risk

1. The spatial heterogeneity of ecosystems as well as temporal activity patterns of organisms can have far‐reaching effects on predator–prey relationships. We hypothesised that spatiotemporal constraints in mesohabitat use by benthic fish predators would reduce habitat overlap with benthic invertebrates and lead to mesohabitat‐specific predation risks. 2. We analysed the spatiotemporal activity patterns of two small‐bodied benthivorous fishes, gudgeon (Gobio gobio) and stone loach (Barbatula barbatula), and of benthic invertebrates in a small temperate stream during three 24‐h field experiments. By applying a novel method of field video observation, we monitored the spatiotemporal foraging behaviour of the fish in their natural environment. A parallel analysis of invertebrate mesohabitat use by means of small area Hess sampling allowed a direct estimation of habitat overlap at a pool–riffle scale. 3. Gudgeon showed a dominant spatial activity pattern preferring pools at all times of day, whereas stone loach used both mesohabitats but with a distinct temporal (nocturnal) activity pattern. The patterns of residence were not identical with those of active foraging. Invertebrate community composition differed significantly between mesohabitats but not between times of day. More than half of the total dissimilarity between pools and riffles was accounted for by six invertebrate taxa. Five of these were subject to higher fish predation in pools than in riffles. The total prey consumption of the two fish species together in pools was about three times as high as in riffles. Trophic niche breadth of stone loach and thus its predation range was broader than that of gudgeon. 4. These results indicate that the potential predation risk for stream invertebrates depends on the combination of spatial and temporal patterns of both predator and prey. Given the distinct differences in predation risk found between pools and riffles, we conclude that spatial heterogeneity at the mesohabitat scale can influence mechanisms and consequences of selective predation. We also suggest that the analysis of spatiotemporal predator–prey relationships should not be based on the premise that the main residence habitat and active foraging habitat of a predator are identical.     

Analysis of macrobenthic communities in Flanders,Belgium, using a stepwise input variable selection procedure with artificial neural networks

The effect of environmental conditions on river macrobenthic communities was studied using a dataset consisting of 343 sediment samples from unnavigable watercourses in Flanders, Belgium. Artificial neural network models were used to analyse the relation among river characteristics and macrobenthic communities. The dataset included presence or absence of macroinvertebrate taxa and 12 physicochemical and hydromorphological variables for each sampling site. The abiotic variables served as input for the artificial neural networks to predict the macrobenthic community. The effects of the input variables on model performance were assessed in order to identify the most diagnostic river characteristics for macrobenthic community composition. This was done by consecutively eliminating the least important variables and, when beneficial for model performance, adding previously removed ones again. This stepwise input variable selection procedure was tested not only on a model predicting the entire macrobenthic community, but also on three models, each predicting an individual taxon. Additionally, during each step of the stepwise leave-one-out procedure, a sensitivity analysis was performed to determine the response of the predicted macroinvertebrate taxa to the input variables applied. This research illustrated that a combination of input variable selection with sensitivity analyses can contribute to the development of reliable and ecologically relevant ANN models. The river characteristics predicting presence or absence of the benthic macroinvertebrates best were the Julian day, conductivity, and dissolved oxygen content. These conditions reflect the importance of discharges of untreated wastewater that occurred during the period of investigation in nearly all Flemish rivers.     

Artificial neural network as an alternative to multiple regression analysis in optimizing formulation parmaeters of cytarabine liposomes

The objective of the study was to optimize the formulation parameters of cytarabine liposomes by using artificial neural networks (ANN) and multiple regression analysis using 3³ factorial design (FD). As model formulations, 27 formulations were prepared. The formulation variables, drug (cytarabine)/lipid (phosphatidyl choline [PC] and cholesterol [Chol]) molar ratio (X ₁, PC/Chol in percentage ratio of total lipids (X ₂), and the volume of hydration medium, (X ₃) were selected as the independent variables; and the percentage drug entrapment (PDE) was selected as the dependent variable. A set of causal factors was used as tutorial data for ANN and fed into a computer. The optimization was performed by minimizing the generalized distance between the predicted values of each response and the optimized one that was obtained individually. In case of 3³ factorial design, a second-order full-model polynomial equation and a reduced model were established by subjecting the transformed values of independent variables to multiple regression analysis, and contour plots were drawn using the equation. The optimization methods developed by both ANN and FD were validated by preparing another 5 liposomal formulations. The predetermined PDE and the experimental data were compared with predicted data by pairedt test, no statistically significant difference was observed. ANN showed less error compared with multiple regression analysis. These findings demonstrate that ANN provides more accurate prediction and is quite useful in the optimization of pharmaceutical formulations when compared with the multiple regression analysis method.     

Applications of neural networks to recovery of biological products

Artificial neural networks (ANN) are being applied to recovery of products from fermentation broths. Recovery methods for which mathematical models are complex or non-existent are particularly suitable for control and analysis by ANNs. Use and potential of artificial neural networks for product recovery applications are reviewed.     

Microhabitat use by 0+ and older fishes in a small English chalk stream

The microhabitat use of two size/age classes of fish (0 +, ≥1+) in the River Lee, based on measurements of 14 environmental variables, was studied using point abundance sampling by electrofishing over the summer and autumn of 1995. Microhabitat use by all cyprinid species (barbel Barbus barbus, minnow Phoxinus phoxinus , chub Leuciscus cephalus and gudgeon Gobio gobio ) differed between 0+ and older (≥1+) with lentic, shallow, littoral environments being important for 0+ fishes, whereas deeper, faster areas in mid-channel were important for ≥ 1 + fishes. There was more overlap in microhabitat use by 0+ juvenile cyprinids in the River Lee than in larger systems such as the River Danube (Slovakia/Hungary) and River Great Ouse (U.K.).     

Use of Artificial Neural Networks To Accurately Identify Cryptosporidium Oocyst and Giardia Cyst Images

Cryptosporidium parvum and Giardia lamblia are protozoa capable of causing gastrointestinal diseases. Currently, these organisms are identified using immunofluorescent antibody (IFA)-based microscopy, and identification requires trained individuals for final confirmation. Since artificial neural networks (ANN) can provide an automated means of identification, thereby reducing human errors related to misidentification, ANN were developed to identify Cryptosporidium oocyst and Giardia cyst images. Digitized images of C. parvum oocysts and G. lamblia cysts stained with various commercial IFA reagents were used as positive controls. The images were captured using a color digital camera at 400× (total magnification), processed, and converted into a binary numerical array. A variety of “negative” images were also captured and processed. The ANN were developed using these images and a rigorous training and testing protocol. The Cryptosporidium oocyst ANN were trained with 1,586 images, while Giardia cyst ANN were trained with 2,431 images. After training, the best-performing ANN were selected based on an initial testing performance against 100 images (50 positive and 50 negative images). The networks were validated against previously “unseen” images of 500 Cryptosporidium oocysts (250 positive, 250 negative) and 282 Giardia cysts (232 positive, 50 negative). The selected ANNs correctly identified 91.8 and 99.6% of the Cryptosporidium oocyst and Giardia cyst images, respectively. These results indicate that ANN technology can be an alternate to having trained personnel for detecting these pathogens and can be a boon to underdeveloped regions of the world where there is a chronic shortage of adequately skilled individuals to detect these pathogens.     

Amphibian species richness and distribution in relation to pond water chemistry in south-western Ontario, Canada

1. We assessed the patterns of amphibian species richness and distribution in relation to water chemistry over a large geographical area in 1992–94.
2. Thirteen amphibian species were observed at 180 ponds, with mean species richness 3.5 ± 0.13 species per pond (range zero to nine). Water samples were collected from 143 ponds, analysed for fifteen chemical variables, and further analysed by multivariate statistical techniques.
3. Water in the study area was hard, alkaline and well-buffered against pH change, and most ponds were eutrophic. Amphibian species richness was negatively correlated with five chemical variables (chloride, conductivity, magnesium, total hardness, turbidity).
4. Principle components analysis reduced the data set to four chemical components that explained 65.4% of the variance in the original variables. Principle component scores were retained for use in further multivariate tests. Multiple regression accounted for only 19.0% of the variance in amphibian species richness. Discriminant function analysis (DFA) was used to determine if water chemistry variables discriminated among species, but it was only able to classify 17.5% of cases correctly. DFA was also used to determine if water chemistry distinguished between used and unused sites for individual species. DFA was moderately successful, classifying 61–77% of cases correctly.
5. General water chemistry appears to play only a minor part in affecting amphibian species richness in south-western, Ontario. However, chemical variables may be helpful to distinguish between used and unused sites for some species.     

Spatial and ontogenetic variability in the microhabitat use of stream-dwelling spined loach (Cobitis taenia) and stone loach (Barbatula barbatula)

Ontogenetic and spatial variability in microhabitat use of spined loach Cobitis taenia (Linnaeus), considered as one species for the purposes of this study, and stone loach Barbatula barbatula (Linnaeus) were examined in the River Great Ouse basin, England, using multivariate and habitat suitability methods, including a technique for handling spatial variation in collections of preference curves. Distinct ordinations of spined age classes and stone loach developmental stages, respectively, in canonical correspondence analysis of species × variables × samples relationships suggest that the two species occupy completely different microhabitats; however, young‐of‐the‐year spined loach occurred more often than expected with all developmental stages of stone loach except young larvae. Water velocity and filamentous algae were the most influential microhabitat variables, the latter decreasing in importance with increasing age of both fish species. Preferred water velocities generally decreased with age in spined loach and increased in stone loach, with substratum size generally increasing with fish age in both species. Spatial variation in microhabitat preferences was great in both species but less so in the spined loach, suggesting that limited plasticity in habitat use could account, at least in part, for the latter species’ limited distribution and abundance in the catchment. Preference curves for a species, if generated and verified for all life intervals and all seasons, could be used as a management tool for a given stream or sector of river basin. But preference curves should be generated for each location to ensure that river management decisions with regard habitat and species conservation consider local‐level species requirements. Thus, a multi‐(eco)species and multi‐scale approach is required in habitat suitability assessments.