Comparison of generalized additive model and boosted regression tree in predicting fish community diversity in the Yangtze River Estuary, China.

doi:10.13287/j.1001-9332.201902.037

Abstract

Abstract: Yangtze River Estuary is the biggest estuarine ecosystem in the western Pacific Ocean. Evaluating fish community in this ecosystem can provide scientific basis for its restoration and mana-gement. Generalized additive model (GAM) and boosted regression tree (BRT) were built to examine the relationship between fish community diversity and environmental and spatio-temporal variables based on data collected during 2012-2014. Combined with linear regression analysis, a cross validation was used to evaluate the fitness and predictive performance of both models. We plotted the spatial distribution of fish community diversity and richness in each station of the Yangtze River Estuary in 2014. The results showed that salinity, pH and chlorophyll-a had the most contribution on diversity, while pH, dissolved oxygen and chlorophyll-a were the most contributive variables on richness. BRT models showed better fitness and lower prediction error than GAM models. In contrast to GAM models, BRT models could distinguish the fish community index in each station area with respect to the spatial prediction. The diversity index in external water was obviously greater than that in internal water. Meanwhile, the station at higher latitude had a higher diversity index in both external and internal water.

Key words: generalized additive model, fish community diversity, Yangtze River Estuary, boosted regression tree model

WU Jian-hui, DAI Li-bin, DAI Xiao-jie, TIAN Si-quan, LIU Jian, CHEN Jin-hui, WANG Xue-fang, WANG Jia-qi. Comparison of generalized additive model and boosted regression tree in predicting fish community diversity in the Yangtze River Estuary, China.[J]. Chinese Journal of Applied Ecology, 2019, 30(2): 644-652.

References

[1] Shan X-J (单秀娟), Chen Y-L (陈云龙), Jin X-S (金显仕), et al. Reshaping the distribution of fish abundance by climate change: A case study in the Yangtze River Estuary. Progress in Fishery Sciences (渔业科学进展), 2016, 37(6): 1-10 (in Chinese)
[2] Shen X-Q (沈新强), Shi Y-R (史赟荣), Chao M (晁敏), et al. Fish community structure of the Yangtze River Estuary in summer and autumn. Journal of Fisheries of China (水产学报), 2011, 35(5): 700-710 (in Chinese)
[3] Shi Y-R (史赟荣), Chao M (晁敏), Shen X-Q (沈新强). Characteristics and monthly variations of set net fish community structure in the Changjiang River estuary. Acta Oceanologica Sinica (海洋学报), 2014, 36(2): 81-92 (in Chinese)
[4] Whitfield AK. Distribution patterns of fishes in a freshwater deprived Eastern Cape estuary, with particular emphasis on the geographical headwater region. Water SA, 2004, 29: 61-67
[5] Shi Y-R (史赟荣), Chao M (晁敏), Quan W-M (全为民), et al. Fish community diversity analyses in the Yangtze River estuary, China. Journal of Fishery Sciences of China (中国水产科学), 2012, 19(6): 1051-1059 (in Chinese)
[6] Shen X-Q (沈新强), Shi Y-R (史赟荣), Chao M (晁敏), et al. Analysis of taxonomic diversity of fish community in Yangtze River estuary. Progress in Fishery Sciences (渔业科学进展), 2013, 34(4): 1-7 (in Chinese)
[7] Zhao J (赵静), Zhang S-Y (章守宇), Wang Z-H (汪振华), et al. Fish community diversity distribution and its affecting factors based on GAM model. Chinese Journal of Ecology (生态学杂志), 2013, 32(12): 3226-3235 (in Chinese)
[8] Leathwick JR, Elith J, Francis MP, et al. Variation in demersal fish species richness in the oceans surrounding New Zealand: An analysis using boosted regression trees. Marine Ecology Progress, 2006, 321: 267-281
[9] Gao F (高峰), Chen X-J (陈新军), Guan W-J (官文江), et al. Fishing ground forecasting of chub mackerel in the Yellow Sea and East China Sea using boosted regression trees. Acta Oceanologica Sinica (海洋学报), 2015, 37(10): 39-48 (in Chinese)
[10] Martínez-Rincn RO, Ortega-García S, Vaca-Rodríguez JG. Comparative performance of generalized additive models and boosted regression trees for statistical modeling of incidental catch of wahoo (Acanthocybium solandri) in the Mexican tuna purse-seine fishery. Ecological Modelling, 2012, 233: 20-25
[11] Chang JH, Chen Y, Holland D, et al. Estimating spatial distribution of American lobster Homarus americanus using habitat variables. Marine Ecology Progress, 2010, 420: 145-156
[12] Margalef R. Information theory in ecology. General Systems, 1958, 3: 36-71
[13] Wilhm JL. Use of biomass units in Shannon’s formula. Ecology, 1968, 49: 153-156
[14] Wood SN, Augustin NH. GAMs with integrated model selection using penalized regression splines and applications to environmental modelling. Ecological Modelling, 2002, 157: 157-177
[15] Burnham KP, Anderson DR. Model Selection and Multimodel Inference: A Practical Information-theoretic Approach. 2nd Ed. New York: Springer-Verlag, 2002
[16] Elith J, Leathwick JR, Hastie T. A working guide to boosted regression trees. Journal of Animal Ecology, 2008, 77: 802-813
[17] Zhang Y-Z (张雅芝), Huang L-M (黄良敏). A study on fish species diversity and community structure in eastern waters of Xiamen. Journal of Tropical Oceano-graphy (热带海洋学报), 2009, 28(2): 66-76 (in Chinese)
[18] Selleslagh J, Amara R. Environmental factors structuring fish composition and assemblages in a small macrotidal estuary (Eastern English Channel). Estuarine, Coastal & Shelf Science, 2008, 79: 507-517
[19] Akin S, Buhan E, Winemiller KO, et al. Fish assemblage structure of Koycegiz Lagoon-Estuary, Turkey: Spatial and temporal distribution patterns in relation to environmental variation. Estuarine, Coastal & Shelf Science, 2005, 64: 671-684
[20] Shi Y-R (史赟荣), Chao M (晁敏), Quan W-M (全为民), et al. Spatial variation in fish community of Yangtze River estuary in spring.Journal of Fishery Sciences of China (中国水产科学), 2011, 18(5): 1141-1151 (in Chinese)
[21] Maes J, Stevens M, Ollevier F. The composition and community structure of the ichthyofauna of the upper Scheldt estuary: Synthesis of a 10-year data collection (1991-2001). Journal of Applied Ichthyology, 2005, 21: 86-93
[22] Maes J, Damme SV, Meire P, et al. Statistical modeling of seasonal and environmental influences on the population dynamics of an estuarine fish community. Marine Biology, 2004, 145: 1033-1042
[23] Damme SV, Struyf E, Maris T, et al. Spatial and temporal patterns of water quality along the estuarine salinity gradient of the Scheldt estuary (Belgium and The Nether-lands): Results of an integrated monitoring approach. Hydrobiologia, 2005, 540: 29-45
[24] Maes J, Stevens M, Breine J. Modelling the migration opportunities of diadromous fish species along a gradient of dissolved oxygen concentration in a European tidal watershed. Estuarine, Coastal & Shelf Science, 2007, 75: 151-162
[25] Gao F (高峰). Fishing Ground Forecasting of Chub Mackerel in the East China Sea and Yellow Sea Using Boosted Regression Trees. PhD Thesis. Shanghai: Shanghai Ocean University, 2016 (in Chinese)
[26] Knudby A, Brenning A, Ledrew E. New approaches to modelling fish-habitat relationships. Ecological Modelling, 2010, 221: 503-511
[27] Chen X-J (陈新军), Gao F (高峰), Guan W-J (官文江), et al. Review of fishery forecasting technology and its models. Journal of Fisheries of China (水产学报), 2013, 37(8): 1270-1280 (in Chinese)
[28] Wang Y-H (王幼槐), Ni Y (倪勇). On the fishe-ries resources and their exploitation of the Changjiang (Yangtze) River Estuary in Shanghai region. Journal of Fisheries of China (水产学报), 1984, 8(2): 147-159 (in Chinese)
[29] Shen X-Q (沈新强), Chao M (晁敏), Quan W-M (全为民), et al. The current situation and restoration research of the Yangtze River estuarine ecosystem. Journal of Fishery Sciences of China (中国水产科学), 2006, 13(4): 624-630 (in Chinese)