Signals of stream fish homogenization revealed by AI-based clusters

Su Ting Cheng, Wen Ping Tsai, Tzu Chun Yu, Edwin E Herricks, Fi John Chang

Research output: Contribution to journalArticle

Abstract

Risks of stream fish homogenization are attributable to multiple variables operating at various spatial and temporal scales. However, understanding the mechanisms of homogenization requires not only watershed-scale, but also exhaustive fish community structure shifts representing detailed local functional relationships essential to homogenization potentials. Here, we demonstrate the idea of applying AI-based clusters to reveal nonlinear responses of homogenization risks among heterogeneous hydro-chemo-bio variables in space and time. Results found that species introduction, dam isolation, and the potential of climate-mediated disruptions in hydrologic cycles producing degradation in water quality triggered shifts of community assembly and resulting structures producing detrimental conditions for endemic fishes. The AI-based clustering approach suggests that endemic species conservation should focus on alleviation of low flows, control of species introduction, limiting generalist expansion, and enhancing the hydrological connectivity fragmented by dams. Likewise, it can be applied in other geographical and environmental settings for finding homogenization mitigation strategies.

Original languageEnglish (US)
Article number15960
JournalScientific reports
Volume8
Issue number1
DOIs
StatePublished - Dec 1 2018

Fingerprint

Fishes
Water Cycle
Water Quality
Climate
Cluster Analysis

ASJC Scopus subject areas

  • General

Cite this

Signals of stream fish homogenization revealed by AI-based clusters. / Cheng, Su Ting; Tsai, Wen Ping; Yu, Tzu Chun; Herricks, Edwin E; Chang, Fi John.

In: Scientific reports, Vol. 8, No. 1, 15960, 01.12.2018.

Research output: Contribution to journalArticle

Cheng, Su Ting ; Tsai, Wen Ping ; Yu, Tzu Chun ; Herricks, Edwin E ; Chang, Fi John. / Signals of stream fish homogenization revealed by AI-based clusters. In: Scientific reports. 2018 ; Vol. 8, No. 1.
@article{f882e1e948284c86ac56d73b0c3ca8ca,
title = "Signals of stream fish homogenization revealed by AI-based clusters",
abstract = "Risks of stream fish homogenization are attributable to multiple variables operating at various spatial and temporal scales. However, understanding the mechanisms of homogenization requires not only watershed-scale, but also exhaustive fish community structure shifts representing detailed local functional relationships essential to homogenization potentials. Here, we demonstrate the idea of applying AI-based clusters to reveal nonlinear responses of homogenization risks among heterogeneous hydro-chemo-bio variables in space and time. Results found that species introduction, dam isolation, and the potential of climate-mediated disruptions in hydrologic cycles producing degradation in water quality triggered shifts of community assembly and resulting structures producing detrimental conditions for endemic fishes. The AI-based clustering approach suggests that endemic species conservation should focus on alleviation of low flows, control of species introduction, limiting generalist expansion, and enhancing the hydrological connectivity fragmented by dams. Likewise, it can be applied in other geographical and environmental settings for finding homogenization mitigation strategies.",
author = "Cheng, {Su Ting} and Tsai, {Wen Ping} and Yu, {Tzu Chun} and Herricks, {Edwin E} and Chang, {Fi John}",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41598-018-34313-x",
language = "English (US)",
volume = "8",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Signals of stream fish homogenization revealed by AI-based clusters

AU - Cheng, Su Ting

AU - Tsai, Wen Ping

AU - Yu, Tzu Chun

AU - Herricks, Edwin E

AU - Chang, Fi John

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Risks of stream fish homogenization are attributable to multiple variables operating at various spatial and temporal scales. However, understanding the mechanisms of homogenization requires not only watershed-scale, but also exhaustive fish community structure shifts representing detailed local functional relationships essential to homogenization potentials. Here, we demonstrate the idea of applying AI-based clusters to reveal nonlinear responses of homogenization risks among heterogeneous hydro-chemo-bio variables in space and time. Results found that species introduction, dam isolation, and the potential of climate-mediated disruptions in hydrologic cycles producing degradation in water quality triggered shifts of community assembly and resulting structures producing detrimental conditions for endemic fishes. The AI-based clustering approach suggests that endemic species conservation should focus on alleviation of low flows, control of species introduction, limiting generalist expansion, and enhancing the hydrological connectivity fragmented by dams. Likewise, it can be applied in other geographical and environmental settings for finding homogenization mitigation strategies.

AB - Risks of stream fish homogenization are attributable to multiple variables operating at various spatial and temporal scales. However, understanding the mechanisms of homogenization requires not only watershed-scale, but also exhaustive fish community structure shifts representing detailed local functional relationships essential to homogenization potentials. Here, we demonstrate the idea of applying AI-based clusters to reveal nonlinear responses of homogenization risks among heterogeneous hydro-chemo-bio variables in space and time. Results found that species introduction, dam isolation, and the potential of climate-mediated disruptions in hydrologic cycles producing degradation in water quality triggered shifts of community assembly and resulting structures producing detrimental conditions for endemic fishes. The AI-based clustering approach suggests that endemic species conservation should focus on alleviation of low flows, control of species introduction, limiting generalist expansion, and enhancing the hydrological connectivity fragmented by dams. Likewise, it can be applied in other geographical and environmental settings for finding homogenization mitigation strategies.

UR - http://www.scopus.com/inward/record.url?scp=85055612205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055612205&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-34313-x

DO - 10.1038/s41598-018-34313-x

M3 - Article

VL - 8

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 15960

ER -