Artificial neural networks as an indicator search engine: The visualization of natural and man-caused taxa variability

Milošević, Djuradj; Čerba, Dubravka; Szekeres, József; Csányi, Béla; Tubić, Bojana; Simić, Vladica; Paunović, Momír

doi:10.1016/j.ecolind.2015.10.029

Cited by 14 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Macroinvertebrate assemblages have been widely used as indicators of ecosystem changes because macroinvertebrate communities encompass a diverse group with a wide range of life-history requirements (O'Brien et al, 2016). Macroinvertebrates vary spatially and temporally and integrate ecosystem changes as a result of their suite of feeding strategies and lifestyles and their different sensitivities to changes in physical habitat and water quality (Milošević et al, 2016;Ogbeibu and Oribhabor, 2002). According to a recent review on indicator species over the last 14 years, nearly 50% of the taxa used as indicators were animals, and 70% of these were invertebrates (Siddig et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Determining the macroinvertebrate community indicators and relevant environmental predictors of the Hun-Tai River Basin (Northeast China): A study based on community patterning

Zhang

Muñoz‐Mas

Martínez‐Capel

et al. 2018

Science of The Total Environment

View full text Add to dashboard Cite

It is essential to understand the patterning of biota and environmental influencing factors for proper rehabilitation and management at the river basin scale. The Hun-Tai River Basin was extensively sampled four times for macroinvertebrate community and environmental variables during one year. Self-Organizing Maps (SOMs) were used to reveal the aggregation patterns of the 355 samples. Three community types (i.e., clusters) were found (at the family level) based on the community composition, which showed a clearly gradient by combining them with the representative environmental variables: minimally impacted source area, intermediately anthropogenic impacted sites, and highly anthropogenic impacted downstream area, respectively. This gradient was corroborated by the decreasing trends in density and diversity of macroinvertebrates. Distance from source, total phosphorus and water temperature were identified as the most important variables that distinguished the delineated communities. In addition, the sampling season, substrate type, pH and the percentage of grassland were also identified as relevant variables. These results demonstrated that macroinvertebrates communities are structured in a hierarchical manner where geographic and water quality prevail over temporal (season) and habitat (substrate type) features at the basin scale. In addition, it implied that the local-scale environment variables affected macroinvertebrates under the longitudinal gradient of the geographical and anthropogenic pressure. More than one family was identified as the indicator for each type of community. Abundance contributed significantly for distinguishing the indicators, while Baetidae with higher density indicated minimally and intermediately impacted area and lower density indicated highly impacted area. Therefore, we suggested the use of abundance data in community patterning and classification, especially in the identification of the indicator taxa.

show abstract

Section: Introductionmentioning

confidence: 99%

Determining the macroinvertebrate community indicators and relevant environmental predictors of the Hun-Tai River Basin (Northeast China): A study based on community patterning

Zhang

Muñoz‐Mas

Martínez‐Capel

et al. 2018

Science of The Total Environment

View full text Add to dashboard Cite

show abstract

“…Those approaches, however, include some disturbance in their reference database, thus reducing the sensitivity of indices to detect impairment in test sites. More recently, methods based on artificial intelligence (e.g., species distribution models) were employed to predict "null assemblages" from large historical databases and then compared with contemporary distributions to determine the ecological status of streams (Davies et al 2012, Labay et al 2015, Milošević et al 2016. These tools rely on large, comparable and sufficiently representative databases, something that unfortunately are not available for many biological groups and regions around the globe.…”

Section: Further Developments On Environmental Filters Approachmentioning

confidence: 99%

“…The need to implement bioassessment programs in regions where reference sites are absent or scarce have fostered the development and testing of alternative methods (Chessman & Royal 2004, Carter & Fend 2005, Stranko et al 2005, Chessman 2006, Blocksom & Johnson 2009, Hawkins et al 2010, Birk et al 2012, Schoolmaster et al 2013, Labay et al 2015, Milošević et al 2016, Elias et al 2016. Some researchers point that an approach that does not require the use of reference sites should be explored (Olden et al 2006, Feio et al 2009, Feio & Poquet 2011, Elias et al 2015.…”

Section: Introductionmentioning

confidence: 99%

A predictive index based on environmental filters for the bioassessment of river basins without reference areas in Atlantic Forest biome, Brazil

2019

View full text Add to dashboard Cite

Biological assessments that use the reference condition approach are based on the concept of comparing a site's observed biology to sites where disturbance is minimal or absent. However, in many regions of the world, such areas are scarce or nonexistent. In this study, an alternative approach proposed by Chessman and Royal for bioassessment without reference areas based on environmental filters was tested in Brazil. This approach assumes that key environmental features act in the selection of potential colonists, from a regional pool of taxa, based on the ecological traits (tolerances) possessed by each taxon. We developed the approach by: 1) determining the regional pool, based on a large Atlantic Forest biome database; 2) selecting environmental filters (elevation, original vegetation and soil type); and 3) including information on the tolerance and preferences of aquatic insects to these filters. With this information we were able to determine the expected taxon under natural conditions and compare with observed taxon, developing a predictive index (Observed/Expected). Although the model was intended to predict the fauna in regions without reference sites, we included reference areas to test the model responsiveness, precision and sensitivity. Our results indicated that the index was able to discriminate impairment classes (F=56.9; p<0,001), it has high precision due to low standard deviation across reference sites values (SD=0.098) and high sensitivity due the correlation with environmental variables that are sensitive to human alteration (r=0.74, p<0.01). Also, it was strongly correlated with multimetric indices developed for multiple watersheds in the state, showing agreement between the methods in relation to ecological quality classification. Even though the predictive index had performed well in our study, we make some considerations that may help to improve its sensitivity of similar methods that are being tested using the environmental filters approach.

show abstract

“…Aquatic invertebrate assemblages have been widely used as indicators of ecosystem conditions. These communities encompass a diverse group with a wide range of life-history requirements and can provide information about the current conditions of a freshwater wetland, as well as the effects of past, cumulative stressors (Milošević et al, 2016, O'Brien et al, 2016Odountan et al, 2019). The advantages of using aquatic invertebrates for MMIs include 1) aquatic life stages that respond to a broad range of environmental conditions; 2) being relatively immobile and 3) living in close contact with bottom sediments and the water column (Bonada et al, 2006;Mereta et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

A Macroinvertebrate Multimetric Index for the Bioassessment of Wetlands Adjacent to Agriculture Fields in the Sanjiang Plain, China

Lyu

et al. 2019

Chin. Geogr. Sci.

View full text Add to dashboard Cite

Adjacent intensive agriculture disturbs the natural condition of wetlands. However, to assess the effect of this agriculture on wetlands, few studies have used indices based on aquatic invertebrates. Multi-metric indices (MMIs) have been successfully used to assess freshwater ecosystems worldwide and are an important management tool, but little is known about their applicability in the Sanjiang Plain, Northeast China. In this study, we developed a MMIs for aquatic invertebrates to assess freshwater wetlands in this region. The aquatic invertebrate assemblages were sampled in 27 wetlands in the Sanjiang Plain that included those in natural reserves and those affected by adjacent, intensive agriculture. Twenty-four candidate metrics were initially reviewed and screened before four core metrics were selected: total number of taxa, number of Hemiptera taxa, proportion of Gastropoda, and proportion of predators. Mann-Whitney U tests, Box and Whisker plots, correlation analyses, and redundant metric tests were used to assess the ability of metrics to distinguish among reference and impaired wetlands. Four ordinal rating categories for wetland were defined: poor, fair, good, and excellent. Of the impaired freshwater wetlands, 76.2% were in poor or fair categories. The MMIs was robust in discriminating reference wetlands from impaired wetlands and therefore have potential as a biomonitoring tool to assess the condition and to guide the restoration efforts of freshwater wetlands in Northeast China.

show abstract

Artificial neural networks as an indicator search engine: The visualization of natural and man-caused taxa variability

Cited by 14 publications

References 47 publications

Determining the macroinvertebrate community indicators and relevant environmental predictors of the Hun-Tai River Basin (Northeast China): A study based on community patterning

Determining the macroinvertebrate community indicators and relevant environmental predictors of the Hun-Tai River Basin (Northeast China): A study based on community patterning

A predictive index based on environmental filters for the bioassessment of river basins without reference areas in Atlantic Forest biome, Brazil

A Macroinvertebrate Multimetric Index for the Bioassessment of Wetlands Adjacent to Agriculture Fields in the Sanjiang Plain, China

Contact Info

Product

Resources

About