DNA barcoding; Fish post-larvae; Modeling; Random Forests; Remote sensing; Surface water masses; Ecology, Evolution, Behavior and Systematics; Aquatic Science; Ecology
Abstract :
[en] Post-larval prediction is important, as post-larval supply allows us to understand juvenile fish populations. No previous studies have predicted post-larval fish species richness and abundance combining molecular tools, machine learning, and past-days remotely sensed oceanic conditions (RSOCs) obtained in the days just prior to sampling at different scales. Previous studies aimed at modeling species richness and abundance of marine fishes have mainly used environmental variables recorded locally during sampling and have merely focused on juvenile and adult fishes due to the difficulty of obtaining accurate species richness estimates for post-larvae. The present work predicted post-larval species richness (identified using DNA barcoding) and abundance at 2 coastal sites in SW Madagascar using random forest (RF) models. RFs were fitted using combinations of local variables and RSOCs at a small-scale (8 d prior to fish sampling in a 50 × 120 km2 area), meso-scale (16 d prior; 100 × 200 km2), and large-scale (24 d prior; 200 × 300 km2). RF models combining local and small-scale RSOC variables predicted species richness and abundance best, with accuracy around 70 and 60%, respectively. We observed a small variation of RF model performance in predicting species richness and abundance among all sites, highlighting the consistency of the predictive RF model. Moreover, partial dependence plots showed that high species richness and abundance were predicted for sea surface temperatures <27.0°C and chlorophyll a concentrations <0.22 mg m-3. With respect to temporal changes, these thresholds were solely observed from November to December. Our results suggest that, in SW Madagascar, species richness and abundance of post-larval fish may only be predicted prior to the ecological impacts of tropical storms on larval settlement success.
Disciplines :
Environmental sciences & ecology
Author, co-author :
Jaonalison, Henitsoa ; Université de Liège - ULiège > Freshwater and OCeanic science Unit of reSearch (FOCUS) ; Institut Halieutique et des Sciences Marines, Université de Toliara, Toliara, Madagascar
Durand, Jean-Dominique; MARBEC, Univ. Montpellier, CNRS, Ifremer, IRD, Montpellier, France
Mahafina, Jamal; Institut Halieutique et des Sciences Marines, Université de Toliara, Toliara, Madagascar
Demarcq, Hervé; MARBEC, IRD, Univ Montpellier, CNRS, Ifremer, Sète, France
Teichert, Nils; Laboratoire de Biologie des Organismes et Ecosystèmes Aquatiques (BOREA), Museúm National d'Histoire Naturelle, CNRS, IRD, SU, UCN, UA-Station Marine de Dinard-CRESCO, Dinard, France
Ponton, Dominique; ENTROPIE, IRD-Université de la Reúnion-CNRS, Université de la Nouvelle-Calédonie-Ifremer, C/o Institut Halieutique et des Sciences Marines, Université de Toliara, Toliara, Madagascar
Language :
English
Title :
Predicting species richness and abundance of tropical post-larval fish using machine learning
Acknowledgements. We thank J. J. Marcellin, D. Fiandria, R. Tsipy, Tovondrainy, and Noelson for help with field collections and the staff of the GenSeq technical facilities of the LabEx ‘Centre Méditerranéen de l’Environnement et de la Biodiversité’ of the Université de Montpellier for sequencing collected samples. We also thank Camille DeSisto and Dr. Christopher Golden for help in reviewing the language accuracy. This work was financially supported by the Critical Ecosystem Partnership Fund (CEPF/IH.SM-MG 66 341), project POE 2.10 POCT FED − FEDER ‘Biodiversité de l’Océan Indien’, the French National Research Institute for Sustainable Development (JEAI-ACOM project), and Insti-tut Halieutique et des Sciences Marines (materials support). This a contribution from ‘Laboratoire Mixte International MIKAROKA’, Institut Halieutique et des Sciences Marines - Centre National de Recherche Océanographique − IRD - University of La Réunion − CNRS - Ifremer.
Albajes-Eizagirre A, Romero L, Soria-Frisch A, Vanhellemont Q (2011) Jellyfish prediction of occurrence from remote sensing data and a non-linear pattern recognition approach. Proc SPIE 8174: 18
Anderson TW, Bartels CT, Hixon MA, Bartels E, Carr MH, Shenker JM (2002) Current velocity and catch efficiency in sampling settlement-stage larvae of coral-reef fishes. Fish Bull 100: 404-413
Avendanõ-Ibarra R, Godínez-Domínguez E, Aceves-Medina G, González-Rodríguez E, Trasvinã A (2013) Fish larvae response to biophysical changes in the Gulf of California, Mexico (wintersummer). J Mar Biol 2013: 1-17
Bailey KM, Nakata H, Van der Veer HW (2005) The planktonic stages of flatfishes: Physical and biological interactions in transport processes. In: Gibson RN (ed) Flatfishes. Blackwell Science, Oxford, p 94-119
Berenshtein I, Paris CB, Gildor H, Fredj E, Amitai Y, Lapidot O, Kiflawi M (2018) Auto-correlated directional swimming can enhance settlement success and connectivity in fish larvae. J Theor Biol 439: 76-85
Breiman L, Cutler A, Liaw A, Wiener M (2018) Breiman and Cutler's random forests for classification and re gres-sion, version 4.6-14. www. stat. berkeley. edu/~breiman/RandomForests/(accessed 8 May 2018)
Bruggemann JH, Rodier M, Guillaume MMM, Andréfouët S and others (2012) Wicked social ecological problems forcing unprecedented change on the latitudinal margins of coral reefs: The case of southwest Madagascar. Ecol Soc 17: 47
Burgess SC, Kingsford MJ, Black KP (2007) Influence of tidal eddies and wind on the distribution of presettlement fishes around One Tree Island, Great Barrier Reef. Mar Ecol Prog Ser 341: 233-242
Chen LC, Lan KW, Chang Y, Chen WY (2018) Summer assemblages and biodiversity of larval fish associated with hydrography in the northern South China Sea. Mar Coast Fish 10: 467-480
Chevalier C, Devenon JL, Rougier G, Blanchot J (2014) Hydrodynamics of the Toliara reef lagoon (Madagascar): Example of a lagoon influenced by waves and tides. J Coast Res 31: 1403-1417
Cho HJ (2007) Effects of prevailing winds on turbidity of a shallow estuary. Int J Environ Res Public Health 4: 185-192
Collet A, Durand JD, Desmarais E, Cerqueira F, Cantinelli T, Valade P, Ponton D (2018) DNA barcoding post-larvae can improve the knowledge about fish biodiversity: An example from La Reunion, SW Indian Ocean. Mitochondrial DNA A DNA Mapp Seq Anal 29: 905-918
Cowen RK, Sale PF (2002) Larval dispersal and retention and consequences for population connectivity. In: Sale PF (ed) Coral reef fishes: Dynamics and diversity in a complex ecosystem. Academic Press, San Diego, CA, p 149-170
Cowen RK, Gawarkiewicz G, Pineda J, Thorrold SR, Werner FE (2007) Population connectivity in marine systems: An overview. Oceanography (Wash DC) 20: 14-21
Cutler DR, Edwards TC Jr, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88: 2783-2792
Darst BF, Malecki KC, Engelman CD (2018) Using recursive feature elimination in random forests to account for correlated variables in high dimensional data. BMC Genet 19: 65-70
ESR (Earth & Space Research) (2009) OSCAR third degree resolution ocean surface currents. NASA Physical Oceanography Distributed Active Archive Center, Pasadena, CA
Falfán-Vázquez E, Ordóñez-López U, Órnelas-Roa M (2008) Spatial variation of snapper and grouper larvae in Yucatan Shelf. Hidrobiologica 18: 69-76
Fisher R (2005) Swimming speeds of larval coral reef fishes: Impacts on self-recruitment and dispersal. Mar Ecol Prog Ser 285: 223-232
Francą S, Cabral HN (2015) Predicting fish species richness in estuaries: Which modeling technique to use Environ Model Softw 66: 17-26
Francą S, Vasconcelos RP, Fonseca VF, Tanner SE, Reis-Santos P, Costa MJ, Cabral HN (2012) Predicting fish community properties within estuaries: Influence of habitat type and other environmental features. Estuar Coast Shelf Sci 107: 22-31
Francis MP, Morrison MA, Leathwick J, Walsh C, Middleton C (2005) Predictive models of small fish presence and abundance in northern New Zealand harbours. Estuar Coast Shelf Sci 64: 419-435
Francis MP, Morrison MA, Leathwick J, Walsh C (2011) Predicting patterns of richness, occurrence and abundance of small fish in New Zealand estuaries. Mar Freshw Res 62: 1327-1341
Frantine-Silva W, Sofia SH, Orsi ML, Almeida FS (2015) DNA barcoding of freshwater ichthyoplankton in the Neotropics as a tool for ecological monitoring. Mol Ecol Resour 15:1226-1237
Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann Stat 29: 1189-1232
Genuer R, Poggi JM, Tuleau-Malot C (2010) Variable selection using random forests. Pattern Recognit Lett 31: 2225-2236
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3: 1157-1182
Han J, Kamber M (2006) Data mining: Concepts and techniques, 2nd edn. Morgan Kaufmann, San Francisco, CA
Harris SA, Cyrus DP, Beckley LE (2001) Horizontal trends in larval fish diversity and abundance along an oceanestuarine gradient on the Northern KwaZulu-Natal Coast, South Africa. Estuar Coast Shelf Sci 53: 221-235
Hickford MJH, Schiel DR (1999) Evaluation of the performance of light traps for sampling fish larvae in inshore temperate waters. Mar Ecol Prog Ser 186: 293-302
Hoareau TB, Boissin E, Berrebi P (2012) Evolutionary history of a widespread Indo-Pacific goby: The role of Pleistocene sea-level changes on demographic contraction/expansion dynamics. Mol Phylogenet Evol 62: 566-572
Hsieh CH, Reiss C, Watson W, Allen MJ and others (2005) A comparison of long-term trends and variability in populations of larvae of exploited and unexploited fishes in the Southern California region: A community approach. Prog Oceanogr 67: 160-185
Hsieh HY, Lo WT, Liu DC, Su WC (2010) Influence of hydrographic features on larval fish distribution during the south-westerly monsoon in the waters of Taiwan, western North Pacific Ocean. J Fish Biol 76: 2521-2539
Huebert KB, Cowen RK, Sponaugle S (2011) Vertical migrations of reef fish larvae in the Straits of Florida and effects on larval transport. Limnol Oceanogr 56: 1653-1666
Irisson JO, Guigand C, Paris CB (2009) Detection and quantification of marine larvae orientation in the pelagic environment. Limnol Oceanogr Methods 7: 664-672
Jackson JB, Kirby MX, Berger WH, Bjorndal KA and others (2001) Historical overfishing and the recent collapse of coastal ecosystems. Science 293: 629-637
James MK, Armsworth PR, Mason LB, Bode L (2002) The structure of reef fish metapopulations: Modelling larval dispersal and retention patterns. Proc R Soc B 269: 2079-2086
Jaonalison H, Mahafina J, Ponton D (2016) Fish post-larvae assemblages at two contrasted coral reef habitats in southwest Madagascar. Reg Stud Mar Sci 6: 62-74
Jenkins GP, King D (2006) Variation in larval growth can predict the recruitment of a temperate, seagrass-associated fish. Oecologia 147: 641-649
Jenkins GP, Black KP, Keough MJ (1999) The role of passive transport and the influence of vertical migration on the presettlement distribution of a temperate, demersal fish: Numerical model predictions compared with field sampling. Mar Ecol Prog Ser 184: 259-271
JPL (Jet Propulsion Laboratory) (2015) GHRSST Level 4 MUR global foundation sea surface temperature analysis. NASA Physical Oceanography Distributed Active Archive Center, Pasadena, CA
Kingsford M, Finn M (1997) The influence of phase of the moon and physical processes on the input of presettlement fishes to coral reefs. J Fish Biol 51: 176-205
Klemas V (2012) Remote sensing of environmental indicators of potential fish aggregation: An overview. Baltica 25: 99-112
Knudby A, Brenning A, LeDrew E (2010) New approaches to modeling fishhabitat relationships. Ecol Modell 221: 503-511
Ko HL, Wang YT, Chiu TS, Lee MA and others (2013) Evaluating the accuracy of morphological identification of larval fishes by applying DNA barcoding. PLOS ONE 8:e53451
Koehl MAR, Strother JA, Reidenbach MA, Koseff JR, Hadfield MG (2007) Individual-based model of larval transport to coral reefs in turbulent, wave-driven flow: Behavioral responses to dissolved settlement inducer. Mar Ecol Prog Ser 335: 1-18
Koslow JA, Wright M (2016) Ichthyoplankton sampling design to monitor marine fish populations and communities. Mar Policy 68: 55-64
Koslow JA, Goericke R, Watson W (2013) Fish assemblages in the Southern California Current: Relationships with climate, 1951-2008. Fish Oceanogr 22: 207-219
Kuhn M (2019) Classification and regression training, version 6.0-84. https://github.com/topepo/caret/(accessed 8
May 2018) Kumar S, Stecher G, Tamura K (2016) MEGA7: Molecular evolutionary genetics analysis version 7.0 for bigger datasets. Mol Biol Evol 33: 1870-1874
Leathwick JR, Elith J, Francis MP, Hastie T, Taylor P (2006) Variation in demersal fish species richness in the oceans surrounding New Zealand: An analysis using boosted regression trees. Mar Ecol Prog Ser 321: 267-281
Leis J (2007) Behaviour as input for modeling dispersal of fish larvae: Behaviour, biogeography, hydrodynamics, ontogeny, physiology and phylogeny meet hydrography. Mar Ecol Prog Ser 347: 185-193
Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2: 18-22
Lin I, Liu WT, Wu CC, Wong GTF and others (2003) New evidence for enhanced ocean primary production triggered by tropical cyclone. Geophys Res Lett 30: 1718
Lindquist DC, Shaw RF (2005) Effects of current speed and turbidity on stationary light-trap catches of larval and juvenile fishes. Fish Bull 103: 438-444
Marchetti MP, Esteban E, Limm M, Kurth R (2004) Evaluating aspects of larval light trap bias and specificity in the northern Sacramento river system: Do size and color matter Am Fish Soc Symp 39: 269-279
Mavruk S, Bengil F, Yüksek A, Özyurt CE, Kiyaa VB, Avar D (2018) Intra-annual patterns of coastal larval fish as-semblages along environmental gradients in the northeastern Mediterranean. Fish Oceanogr 27: 232-245
McLaren IA, Avendanõ P (1995) Prey field and diet of larval cod on Western Bank, Scotian Shelf. Can J Fish Aquat Sci 52: 448-463
Meissner T, Wentz FJ (2016) Remote sensing systems SMAP level 3 sea surface salinity standard mapped image 8-day running mean V2.0 validated dataset. NASA Physical Oceanography Distributed Active Archive Center, Pasadena, CA
Milicich M, Meekan MG, Doherty PJ (1992) Larval supply: A good predictor of recruitment of three species of reef fish (Pomacentridae). Mar Ecol Prog Ser 86: 153-166
Morsink K (2018) Hurricanes, typhoons, and cyclones. http://ocean.si.edu/planet-ocean/waves-stormstsunamis/hurricanes-typhoons-and-cyclones (accessed 28
May 2019) Moser HG, Watson W (1990) Distribution and abundance of early life history stages of the California halibut, Paralichthys californicus and comparisons with the fantail sole, Xystreurys liolepis. Fish Bull 174: 31-84
Murphy MA, Evans JS, Storfer A (2010) Quantifying Bufo boreas connectivity in Yellowstone National Park with landscape genetics. Ecology 91: 252-261
NASA Ocean Biology Processing Group (2017) MODISAqua level 3 mapped chlorophyll data version R2018.0. NASA Ocean Biology Distributed Active Archive Center, Greenbelt, MD
Nicolas D, Lobry J, Lepage M, Sautour B and others (2010) Fish under influence: A macroecological analysis of relations between fish species richness and environmental gradients among European tidal estuaries. Estuar Coast Shelf Sci 86: 137-147
Paris CB, Cowen RK (2004) Direct evidence of a biophysical retention mechanism for coral reef fish larvae. Limnol Oceanogr 49: 1964-1979
Potts JM, Elith J (2006) Comparing species abundance models. Ecol Modell 199: 153-163
R Core Team (2018) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna
Ramanantsoa JD, Penven P, Krug M, Gula J, Rouault M (2018) Uncovering a new current: The southwest Madagascar coastal current. Geophys Res Lett 45: 1930-1938
Ratnasingham S, Hebert PDN (2013) A DNA-based registry for all animal species: The Barcode Index Number (BIN) system. PLOS ONE 8: E66213
Reid K, Crochelet E, Bloomer P, Hoareau TB (2016) Investigating the origin of vagrant dusky groupers, Epinephelus marginatus (Lowe, 1834), in coastal waters of Reúnion Island. Mol Phylogenet Evol 103: 98-103
Reunanen J (2003) Overfitting in making comparisons be-tween variable selection methods. J Mach Learn Res 3: 1371-1382
Reynalte-Tataje DA, Zaniboni-Filho E, Bialetzki A, Agostinho AA (2012) Temporal variability of fish larvae assemblages: Influence of natural and anthropogenic disturbances. Neotrop Ichthyol 10: 837-846
Robertson DR, Green DG, Victor BC (1988) Temporal coupling of production and recruitment of larvae of a Caribbean reef fish. Ecology 69: 370-381
Schlaefer JA, Wolanski E, Lambrechts J, Kingsford MJ (2018) Wind conditions on the Great Barrier Reef influenced the recruitment of snapper (Lutjanus carponotatus). Front Mar Sci 5: 193
Shanks AL (2009) Pelagic larval duration and dispersal distance revisited. Biol Bull (Woods Hole) 216: 373-385
Sponaugle S, Cowen RK (1996) Nearshore patterns of coral reef fish larval supply to Barbados, West Indies. Mar Ecol Prog Ser 133: 13-28
Stearns DE, Holt GJ, Forward RB Jr, Pickering PL (1994) Ontogeny of phototactic behavior in red drum larvae (Sciaenidae: Sciaenops ocellatus). Mar Ecol Prog Ser 104: 1-11
Stige LC, Hunsicker ME, Bailey KM, Yaragina NA, Hunt GL Jr (2013) Predicting fish recruitment from juvenile abundance and environmental indices. Mar Ecol Prog Ser 480: 245-261
Takahashi M, Watanabe Y (2004) Growth rate-dependent recruitment of Japanese anchovy Engraulis japonicus in the KuroshioOyashio transitional waters. Mar Ecol Prog Ser 266: 227-238
Tricklebank KA, Jacoby CA, Montgomery JC (1992) Composition, distribution and abundance of neustonic ichthyoplankton off northeastern New Zealand. Estuar Coast Shelf Sci 34: 263-275
Tzeng WN, Wang YT (1993) Hydrography and distribution dynamics of larval and juvenile fishes in the coastal waters of the Tanshui River estuary, Taiwan, with re ference to estuarine larval transport. Mar Biol 116: 205-217
Vasconcelos RP, Henriques S, Francą S, Pasquaud S, Cardoso I, Laborde M, Cabral HN (2015) Global patterns and predictors of fish species richness in estuaries. J Anim Ecol 84: 1331-1341
Wentz FJ, Ricciardulli L, Gentemann C, Meissner T, Hilburn KA, Scott J (2013) Remote sensing systems Coriolis Windsat [Daily]. Environmental Suite on 0.25 deg grid, version 7.0.1. Remote Sensing Systems, Santa Rosa, CA
Wernberg T, Smale DA, Tuya F, Thomsen MS and others (2013) An extreme climatic event alters marine ecosystem structure in a global biodiversity hotspot. Nat Clim Chang 3: 78-82
Wilson D (2001) Patterns of replenishment of coral-reef fishes in the nearshore waters of the San Blas Archipelago, Caribbean Panama. Mar Biol 139: 735-753
