Abstract
The lack of information on the extinction risk of most species is a fundamental challenge in prioritizing conservation strategies and bending the curve of current biodiversity decline. Machine learning methods have shown promising potential to fill this gap, but their applicability remains to be validated at different taxa (especially aquatic species) and spatial scales. We assessed the extinction risk of 1162 freshwater fish species in China that have not yet been included in the latest IUCN Red List using multiple neural network algorithms based on datasets of species occurrences, biological traits, phylogeny, and relevant environmental layers. The best deep learning models dramatically improved the assessment coverage from 29.9% (496 species) to 93.2–93.9% (1545–1557 species) of the whole fauna with an accuracy of 95.4–99.0%. By combining our prediction results with the IUCN Red List, we found that 23.8–26.5% (394–440 species) of Chinese freshwater fishes were identified as possibly threatened species, which is roughly four times the IUCN assessment. Newly assessed species and threatened species were mainly from the orders Cypriniformes (prediction added: 837–846 species; final threatened: 325–350 species), Siluriformes (113–122; 28–37) and Perciformes (74–76; 18–25). The increase in threatened species richness based on predictions was led by the upper reaches of the Pearl and Yangtze. Overall, our findings suggest that deep learning algorithms can provide robust and time-saving assessments of extinction risk for entire freshwater fish fauna on a large national scale, thereby facilitating relevant conservation prioritization.
Graphical abstract
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The raw data and code can be freely downloaded from the Zenodo repository at https://doi.org/10.5281/zenodo.7993137.
References
Albert JS, Destouni G, Duke-Sylvester SM, Magurran AE, Oberdorff T, Reis RE, Winemiller KO, Ripple WJ (2021) Scientists’ warning to humanity on the freshwater biodiversity crisis. Ambio 50:85–94. https://doi.org/10.1007/s13280-020-01318-8
Bachman S, Field R, Reader T, Raimondo D, Donaldson J, Schatz GE, Nic Lughadha E (2019) Progress, challenges and opportunities for Red Listing. Biol Conserv 234:45–55. https://doi.org/10.1016/j.biocon.2019.03.002
Bergerot B, Hugueny B, Belliard J (2015) Relating life–history traits, environmental constraints and local extinctions in river fish. Freshw Biol 60:1279–1291. https://doi.org/10.1111/fwb.12561
Betts J, Young RP, Hilton-Taylor C, Hoffmann M, Rodríguez JP, Stuart SN, Milner-Gulland EJ (2020) A framework for evaluating the impact of the IUCN Red List of threatened species. Conserv Biol 34:632–643. https://doi.org/10.1111/cobi.13454
Boettiger C, Lang DT, Wainwright PC (2012) rfishbase: exploring, manipulating and visualizing FishBase data from R. J Fish Biol 81:2030–2039. https://doi.org/10.1111/j.1095-8649.2012.03464.x
Borgelt J, Dorber M, Høiberg MA, Verones F (2022) More than half of data deficient species predicted to be threatened by extinction. Commun Biol 5:1–9. https://doi.org/10.1038/s42003-022-03638-9
Brosse S, Charpin N, Su G, Toussaint A, Herrera-R GA, Tedesco PA, Villéger S (2021) FISHMORPH: A global database on morphological traits of freshwater fishes. Global Ecol Biogeogr 30:2330–2336. https://doi.org/10.1111/geb.13395
Cao L, Zhang E, Zang C, Cao W (2016) Evaluating the status of China's continental fish and analyzing their causes of endangerment through the red list assessment. Biodiv Sci 24:598–609. https://doi.org/10.17520/biods.2015331
Cazalis V, Di Marco M, Butchart SH et al (2022) Bridging the research-implementation gap in IUCN Red List assessments. Trends Ecol Evol 37:359–370. https://doi.org/10.1016/j.tree.2021.12.002
Costello MJ, May RM, Stork NE (2013) Can we name Earth’s species before they go extinct? Science 339(6118):413–416. https://doi.org/10.1126/science.1230318
Crist E, Mora C, Engelman R (2017) The interaction of human population, food production, and biodiversity protection. Science 356:260–264. https://doi.org/10.1126/science.aal2011
Dauby G, Stévart T, Droissart V, Cosiaux A, Deblauwe V, Simo-Droissart M, Sosef MSM, Lowry PP, Schatz GE, Gereau RE, Couvreur TLP (2017) ConR: an R package to assist large-scale multispecies preliminary conservation assessments using distribution data. Ecol Evol 7:11292–11303. https://doi.org/10.1002/ece3.3704
De Silva SS, Abery NW, Nguyen TT (2007) Endemic freshwater finfish of Asia: distribution and conservation status. Divers Distrib 13:172–184. https://doi.org/10.1111/j.1472-4642.2006.00311.x
Ding C, Jiang X, Xie Z, Brosse S (2017) Seventy-five years of biodiversity decline of fish assemblages in Chinese isolated plateau lakes: widespread introductions and extirpations of narrow endemics lead to regional loss of dissimilarity. Divers Distrib 23:171–184. https://doi.org/10.1111/ddi.12507
Ding C, Sun J, Huang M et al (2023) Flow and thermal regimes altered by a dam caused failure of fish recruitment in the upper Mekong River. Freshwater Biol. https://doi.org/10.1111/fwb.14105
Domisch S, Amatulli G, Jetz W (2015) Near-global freshwater-specific environmental variables for biodiversity analyses in 1 km resolution. Sci Data 2:1–13. https://doi.org/10.1038/sdata.2015.73
ESRI (2016) ArcGis Desktop: Release 10.4. Redlands: Environmental Systems Research Institute
FAO [Food and Agriculture Organization of the United Nations] (2020) The State of World Fisheries and Aquaculture 2020. Sustainability in action. Rome, Italy
Farr TG, Rosen PA, Caro E et al (2007) The shuttle radar topography mission. Rev Geophys 45. https://doi.org/10.1029/2005RG000183
Fick SE, Hijmans RJ (2017) WorldClim 2: new 1-km spatial resolution climate surfaces for global land areas. Int J Climatol 37:4302–4315. https://doi.org/10.1002/joc.5086
Fricke R, Eschmeyer WN, der Laan VR (2022) Eschmeyer's Catalog of Fishes: Genera, Species, References. http://researcharchive.calacademy.org/research/ichthyology/catalog/fishcatmain.asp. Accessed on 04 Oct 2022
Froese R, Pauly D (2022) FishBase. World Wide Web electronic publication. www.fishbase.org, version (06/2022)
Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In: Proceedings of the 33 rd international conference on machine learning, New York, USA, pp 1050–1059
Gong J, Teng Z, Teng Q et al (2020) Hierarchical graph transformer-based deep learning model for large-scale multi-label text classification. IEEE Access 8:30885–30896. https://doi.org/10.1109/ACCESS.2020.2972751
González-del-Pliego P, Freckleton RP, Edwards DP, Koo MS, Scheffers BR, Pyron RA, Jetz W (2019) Phylogenetic and trait-based prediction of extinction risk for data-deficient amphibians. Curr Biol 29:1557–1563. https://doi.org/10.1016/j.cub.2019.04.005
Guo C, Chen Y, Gozlan RE, Li Z, Mehner T, Lek S, Paukert CP (2019) Biogeographic freshwater fish pattern legacy revealed despite rapid socio-economic changes in China. Fish Fish 20:857–869. https://doi.org/10.1111/faf.12380
He D, Sui X, Sun H, Tao J, Ding C, Chen YF, Chen YY (2020) Diversity, pattern and ecological drivers of freshwater fish in China and adjacent areas. Rev Fish Biol Fisher 30:387–404. https://doi.org/10.1007/s11160-020-09600-4
Hermoso V, Abell R, Linke S, Boon P (2016) The role of protected areas for freshwater biodiversity conservation: challenges and opportunities in a rapidly changing world. Aquat Conserv 26:3–11. https://doi.org/10.1002/aqc.2681
Huang GB (2003) Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans Neural Netw 14:274–281. https://doi.org/10.1109/TNN.2003.809401
IUCN (2022) IUCN, International Union for Conservation of Nature. https://www.iucn.org. Accessed on 21 July 2022
Jia Y, Jiang Y, Liu Y, Sui X, Feng X, Zhu R, Li K, Chen Y (2022) Unravelling fish community assembly in shallow lakes: insights from functional and phylogenetic diversity. Rev Fish Biol Fisher 32:623–644. https://doi.org/10.1007/s11160-021-09688-2
Langford WT, Gordon A, Bastin L, Bekessy SA, White MD, Newell G (2011) Raising the bar for systematic conservation planning. Trends Ecol Evol 26:634–640. https://doi.org/10.1016/j.tree.2011.08.001
Lehner B, Verdin K, Jarvis A (2008) New global hydrography derived from spaceborne elevation data. EOS Trans Am Geophys Union 89:93–94. https://doi.org/10.1029/2008EO100001
Levêque C, Oberdorff T, PAUGy D, Stiassny MLJ, Tedesco PA (2007) Global diversity of fish (Pisces) in freshwater. In: Freshwater animal diversity assessment. Springer, Dordrecht, pp 545–567
Liu X, Olden JD, Wu R, Ouyang S, Wu X (2022) Dam construction impacts fish biodiversity in a subtropical river network, China. Diversity 14:476. https://doi.org/10.3390/d14060476
Luiz OJ, Woods RM, Madin EM, Madin JS (2016) Predicting IUCN extinction risk categories for the world’s data deficient groupers (Teleostei: Epinephelidae). Conserv Lett 9:342–350. https://doi.org/10.1111/conl.12230
Lu X, Fu Z (2010) Survey of Chinese river systems. China Water and Power Press, Beijing
Maasri A, Jähnig SC, Adamescu MC et al (2022) A global agenda for advancing freshwater biodiversity research. Ecol Lett 25:255–263. https://doi.org/10.1111/ele.13931
Naimi B, Hamm NA, Groen TA, Skidmore AK, Toxopeus AG (2014) Where is positional uncertainty a problem for species distribution modelling? Ecography 37:191–203. https://doi.org/10.1111/j.1600-0587.2013.00205.x
Nakamura G, Richter A, Soares BE (2021) FishPhyloMaker: an R package to generate phylogenies for ray-finned fishes. Ecol Inform 66:101481. https://doi.org/10.1016/j.ecoinf.2021.101481
Nic Lughadha E, Walker BE, Canteiro C, Chadburn H, Davis AP, Hargreaves S, Rivers MC (2019) The use and misuse of herbarium specimens in evaluating plant extinction risks. Philos T of the R Soc B 374:20170402. https://doi.org/10.1098/rstb.2017.0402
Olden JD, Hogan ZS, Zanden MJV (2007) Small fish, big fish, red fish, blue fish: size-biased extinction risk of the world’s freshwater and marine fishes. Global Ecol Biogeogr 16:694–701. https://doi.org/10.1111/j.1466-8238.2007.00337.x
Olson DM, Dinerstein E, Wikramanayake ED et al (2001) Terrestrial Ecoregions of the World: a new map of life on EarthA new global map of terrestrial ecoregions provides an innovative tool for conserving biodiversity. Bioscience 51:933–938. https://doi.org/10.1641/0006-3568(2001)051[0933:TEOTWA]2.0.CO;2
Pelletier TA, Carstens BC, Tank DC, Sullivan J, Espíndola A (2018) Predicting plant conservation priorities on a global scale. Proc Natl Acad Sci 115:13027–13032. https://doi.org/10.1073/pnas.1804098115
Pollock LJ, O’Connor LMJ, Mokany K, Rosauer DF, Talluto MV, Thuiller W (2020) Protecting biodiversity (in all its complexity): new models and methods. Trends Ecol Evol 35:1119–1128. https://doi.org/10.1016/j.tree.2020.08.015
Radinger J, Wolter C (2014) Patterns and predictors of fish dispersal in rivers. Fish Fish 15:456–473. https://doi.org/10.1111/faf.12028
Rapacciuolo G (2019) Strengthening the contribution of macroecological models to conservation practice. Global Ecol Biogeogr 28:54–60. https://doi.org/10.1111/geb.12848
R Core Team (2022) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/
Reid AJ, Carlson AK, Creed IF et al (2019) Emerging threats and persistent conservation challenges for freshwater biodiversity. Biol Rev 94:849–873. https://doi.org/10.1111/brv.12480
Rondinini C, Marco MD, Visconti P, Butchart SHM, Boitani L (2014) Update or outdate: long-term viability of the IUCN Red List. Conserv Lett 7:126–130. https://doi.org/10.1111/conl.12040
Sadovy de Mitcheson Y, Craig MT, Bertoncini AA et al (2013) Fishing groupers towards extinction: a global assessment of threats and extinction risks in a billion-dollar fishery. Fish Fish 14:119–136. https://doi.org/10.1111/j.1467-2979.2011.00455.x
Schipper AM, Barbarossa V (2022) Global congruence of riverine fish species richness and human presence. Global Ecol Biogeogr 31:1501–1512. https://doi.org/10.1111/geb.13519
Sherley RB, Winker H, Rigby CL et al (2020) Estimating IUCN Red List population reduction: JARA: a decision–support tool applied to pelagic sharks. Conserv Lett 13:e12688. https://doi.org/10.1111/conl.12688
Sidharthan A, Raghavan R, Anoop VK, Philip S, Dahanukar N (2020) Riddle on the riffle: Miocene diversification and biogeography of endemic mountain loaches in the Western Ghats Biodiversity Hotspot. J Biogeogr 47:2741–2754. https://doi.org/10.1111/jbi.13972
Silva SV, Andermann T, Zizka A, Kozlowski G, Silvestro D (2022) Global estimation and mapping of the conservation status of tree species using artificial intelligence. Front Plant Sci 13:839792. https://doi.org/10.3389/fpls.2022.839792
Song C, Fan C, Zhu J et al (2022) A comprehensive geospatial database of nearly 100 000 reservoirs in China. Earth Syst Sci Data 14:4017–4034. https://doi.org/10.5194/essd-14-4017-2022
Stathakis D (2009) How many hidden layers and nodes? Int J Remote Sens 30:2133–2147. https://doi.org/10.1080/01431160802549278
Tao J, Ding C, Chen J, et al (2023) Boosting freshwater fish conservation with high‐resolution distribution mapping across a large territory. Conserv Biol 37:e14036. https://doi.org/10.1111/cobi.14036
Tickner D, Opperman JJ, Abell R et al (2020) Bending the curve of global freshwater biodiversity loss: an emergency recovery plan. Bioscience 70:330–342. https://doi.org/10.1093/biosci/biaa002
Toussaint A, Brosse S, Bueno CG, Pärtel M, Tamme R, Carmona CP (2021) Extinction of threatened vertebrates will lead to idiosyncratic changes in functional diversity across the world. Nat Commun 12:1–12. https://doi.org/10.1038/s41467-021-25293-0
Venter O, Sanderson EW, Magrach A et al (2016) Sixteen years of change in the global terrestrial human footprint and implications for biodiversity conservation. Nat Commun 7:1–11. https://doi.org/10.1038/ncomms12558
Wang Q, Cheng L, Liu J, Li Z, Xie S, De Silva SS (2015) Freshwater aquaculture in PR China: trends and prospects. Rev Aquacult 7:283–302. https://doi.org/10.1111/raq.12086
WWF [World Wildlife Fund] (2020) In: Almond REA, Grooten M, Petersen T (eds) Living planet report 2020: bending the curve of biodiversity loss. WWF, Gland, Switzerland
Xing Y, Zhang C, Fan E, Zhao Y (2016) Freshwater fishes of China: species richness, endemism, threatened species and conservation. Divers Distrib 22:358–370. https://doi.org/10.1111/ddi.12399
Zanaga D, Van De Kerchove R, De Keersmaecker W, Souverijns N, Brockmann C, Quast R, Arino O (2021) ESA WorldCover 10 m 2020 v100. Zenodo: Geneve, Switzerland
Zhang C, Ding C, Ding L, Chen L, Hu J, Tao J, Jiang X (2019) Large-scale cascaded dam constructions drive taxonomic and phylogenetic differentiation of fish fauna in the Lancang River, China. Rev Fish Biol Fisher 29:895–916. https://doi.org/10.1007/s11160-019-09580-0
Zizka A, Andermann T, Silvestro D (2022) IUCNN–Deep learning approaches to approximate species’ extinction risk. Divers Distrib 28:227–241. https://doi.org/10.1111/ddi.13450
Zizka A, Antonelli A, Silvestro D (2021a) Sampbias, a method for quantifying geographic sampling biases in species distribution data. Ecography 44(1):25–32. https://doi.org/10.1111/ecog.05102
Zizka A, Silvestro D, Vitt P, Knight TM (2021b) Automated conservation assessment of the orchid family with deep learning. Conserv Biol 35:897–908. https://doi.org/10.1111/cobi.13616
Zizka A, Silvestro D, Andermann T et al (2019) CoordinateCleaner: standardized cleaning of occurrence records from biological collection databases. Methods Ecol Evol 10:744–751. https://doi.org/10.1111/2041-210X.13152
Acknowledgements
We would like to thank Yan Wang and Jie Wang for providing advice on the early draft. This study was financially supported by the Strategic Priority Research Program of Chinese Academy of Sciences (grant XDB31000000), the National Key Research and Development Program of China (grant 2021YFC3200103). Jinnan Chen was supported by Yunnan University's Research Innovation Fund for Graduate Students (No. 2021Y370). Jingrui Sun was founded by the China Postdoctoral Science Foundation (2021M702777).
Author information
Authors and Affiliations
Contributions
JT and DH conceived and supervised the project. JC, CD, LD, and JT designed the research strategy and methodology. JC, LD, SJ and TD performed the data collection and data analysis. JC and JT wrote the original draft. JS and MH participated in critically revising the manuscript. All authors contributed to the discussion and, subsequently, various versions of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chen, J., Ding, C., He, D. et al. Assessing the conservation status of Chinese freshwater fish using deep learning. Rev Fish Biol Fisheries 33, 1505–1521 (2023). https://doi.org/10.1007/s11160-023-09792-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11160-023-09792-5