Application of the machine learning method to estimate the biomass of pacific cod in the North Kuril zone
https://doi.org/10.26428/1606-9919-2022-202-1002-1014
Abstract
The biomass of pacific cod (Gadus macrocephalus) in the North Kuril fishing zone is estimated using a multifactorial approach, with evaluation of uncertainty. For this purpose, the density of fish over entire zone is restored using the data on density obtained in 2022 compared with the data of previous surveys and fishery data obtained in 2021 and earlier, converted to the same scale, with application of the machine learning method, as the random forest in the multiple imputation by chained equations procedure (MICE). The coefficient of the restored data determination with out-of-bag (test set) data was > 0.8 with the data of scientific survey in 2021 and > 0.5 with the data of Danish seine observations. The cod density variance in MICE data was in 82 % lower than in the data of the scientific survey; therefore the biomass estimation with MICE data has lower uncertainty than that one calculated just from the mean density in survey. The study showed insignificant difference of the cod biomass in 2021 and 2022. Spatial segregation is revealed for fishing gears used for the pacific cod fishery. There is proposed to extend the list of fishing gears and to expand the study area for reducing possible bias in the biomass estimation due to large area of extrapolation.
Supporting agencies: The authors are thankful to all members of scientific cruises and observers whose materials were used to adjust the models. Special thanks to the staff of the Center for Fisheries Monitoring System and Communications and the Space Research Institute of the Russian Academy of Sciences (IKI RAS) for maintaining the OSM database and providing access to them. The materials for the study were collected and processed under the contract for the performance of research work No. 40-22 with JSC «IC BSF» dated April 13, 2022.
About the Authors
V. V. Kulik
Pacific branch of VNIRO (TINRO)
Russian Federation
Russian Federation
Vladimir V. Kulik - Ph.D., head of laboratory
690091, Vladivostok, Shevchenko Alley, 4
M. I. Goryunov
Pacific branch of VNIRO (TINRO)
Russian Federation
Russian Federation
Mikhail I. Goryunov - leading specialist
690091, Vladivostok, Shevchenko Alley, 4
References
1. Aksyutina, Z.M., Quantitative assessment of fish aggregations by the method of contour lines, Tr. Vses. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 1970, vol. 71, pp. 302–308.
2. Aksyutina, Z.M., On the use of electronic computers for the analysis of the distribution and quantification of fish populations // Tr. Vseross. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr, 1970, vol. 71, pp. 309–318.
3. Aksyutina, Z.M., Elementy matematicheskoi otsenki rezul’tatov nablyudenii v biologicheskikh i rybokhozyaistvennykh issledovaniyakh (Elements of Mathematical Evaluation of the Results of Observations in Biological and Fishery Research), Moscow: Pishchevaya Promyshlennost’, 1968.
4. Volvenko, I.V., Problems in quantitative estimation of fish abundance by trawl sampling, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 1998, vol. 124, pp. 473–500.
5. Volvenko, I.V., Technical problems of adequate interpretation the results of trawl surveys and ways to solve them, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 2013, vol. 172, pp. 282–293.
6. Zakharov, E.A. and Emelin, P.O., Relevance of using the equipment for control of fishing gear to reduce inaccuracy in evaluation of marine organisms abundance, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 2016, vol. 186, pp. 198–206. doi:10.26428/1606-9919-2016-186-198-206
7. Zakharov, E.A., Kruchinin, O.N., Mizurkin, M.A., and Safronov, V.A., Geometric parameters of the bottom trawl 27.1/24.4, and its possible errors in assessment of number of marine organisms, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 2013, vol. 174, pp. 284–292.
8. Zakharov, E.A., Kruchinin, O.N., and Shabelsky, D.L., Development and testing of algorithm for calculation of operating parameters of trawling systems, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 2019, vol. 198, pp. 221–229. doi:10.26428/1606-9919-2019-198-221-229
9. Shuntov, V.P., Volvenko, I.V., Kulik, V.V., and Bocharov, L.N., Makrofauna bentali Okhotskogo morya: tablitsy vstrechaemosti, chislennosti i biomassy. 1977–2010 (Benthic Macrofauna of the Okhotsk Sea: Occurrence, Abundance, and Biomass. 1977–2010), Shuntov, V.P. and Bocharov, L.N., eds, Vladivostok: TINRO-Tsentr, 2014.
10. Shuntov, V.P., Volvenko, I.V., Kulik, V.V., and Bocharov, L.N., Makrofauna bentali severozapadnoi chasti Tikhogo okeana: tablitsy vstrechaemosti, chislennosti i biomassy. 1977–2008 (Benthic Macrofauna of the Northwestern Pacific: Occurrence, Abundance, and Biomass. 1977–2008), Shuntov, V.P. and Bocharov, L.N., eds, Vladivostok: TINRO-Tsentr, 2014.
11. Assis, J., Tyberghein, L., Bosch, S., Verbruggen, H., Serrão, E.A., and De Clerck, O., BioORACLE v2.0: Extending marine data layers for bioclimatic modelling, Glob. Ecol. Biogeogr., 2018, vol. 27, no. 3, pp. 277–284. doi:10.1111/geb.12693
12. Breiman, L., Random forests, Mach. Learn., 2001, vol. 45, no. 1, pp. 5–32. doi:10.1023/A:1010933404324
13. Kulik, V.V., Prants, S.V., Uleysky, M.Yu., and Budyansky, M.V., Lagrangian characteristics in the western North Pacific help to explain variability in Pacific saury fishery, Fish. Res., 2022, vol. 252, 106361. doi:10.1016/j.fishres.2022.106361
14. Ricker, W.E., Computation and Interpretation of Biological Statistics of Fish Populations, Ottawa: Dep. Environ. Fish. Mar. Serv., 1975.
15. Sbrocco, E.J. and Barber, P.H., MARSPEC: ocean climate layers for marine spatial ecology, Ecology, 2013, vol. 94, no. 4, p. 979. doi:10.1890/12-1358.1
16. Thompson, P.L., Anderson, S.C., Nephin, J., Robb, C.K., Proudfoot, B., Park, A.E., Haggarty, D.R., and Rubidge, E., Integrating trawl and longline surveys across British Columbia improves groundfish distribution predictions, Can. J. Fish. Aquat. Sci., 2022. doi:10.1139/cjfas-2022-0108
17. Tyberghein, L., Verbruggen, H., Pauly, K., Troupin, C., Mineur, F., and De Clerck, O., Bio-ORACLE: a global environmental dataset for marine species distribution modelling, Glob. Ecol. Biogeogr., 2012, vol. 21, no. 2, pp. 272–281. doi:10.1111/j.1466-8238.2011.00656.x
18. Wright, M.N. and Ziegler, A., ranger : A Fast Implementation of Random Forests for High Dimensional Data in C++ and R, J. Stat. Softw., 2017, vol. 77, no. 1, pp. 1–17. doi:10.18637/jss.v077.i01
19. Svidetel’stvo № 6394 ot 01.08.2000 g. o registratsii v Gosudarstvennom registre bazy dannykh za № 0220006765 «Morskaja biologija» (Certificate No. 6394 dated August 1, 2000 on registration in the State Register of the database No. 0220006765 “Marine biology”).
20. GEBCO Bathymetric Compilation Group 2020. The GEBCO_2020 Grid — a continuous terrain model of the global oceans and land, British Oceanographic Data Centre, National Oceanography Centre, NERC, UK. https://doi.org/10.5285/a29c5465-b138-234d-e053-6c86abc040b9. Cited July 20, 2022.
21. Baston, D., exactextractr: Fast Extraction from Raster Datasets using Polygons, R package version 0.7.2, 2021. https://CRAN.R-project.org/package=exactextractr. Cited January 27, 2022.
22. Olaya, V., Module Real Surface Area, SAGA-GIS Module Library Documentation (v2.1.3), 2004. R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria, 2022, version 4.2.1. https://www.R-project.org/. Cited July 20, 2022.
23. Svidetel’stvo № 2017620882 ot 11.08.2017 g. o gosudarstvennoy registratsii bazy dannykh «Yarusnyy promysel» (Certificate No. 2017620882 dated August 11, 2017 on state registration of the “Longline Fishery” database).
24. Ogle, D.H., Doll J.C., Wheeler P., and Dinno A., FSA: Fisheries Stock Analysis, R package version 0.9.3. https://github.com/fishR-Core-Team/FSA. Cited July 26, 2022.
Supplementary files
|
1. ПРИЛОЖЕНИЕ А Вспомогательные таблицы | |
| Subject | ||
| Type | Исследовательские инструменты | |
Download
(15MB)
|
Indexing metadata ▾ | |
Review
For citations:
Kulik V.V., Goryunov M.I. Application of the machine learning method to estimate the biomass of pacific cod in the North Kuril zone. Izvestiya TINRO. 2022;202(4):1002-1014. (In Russ.) https://doi.org/10.26428/1606-9919-2022-202-1002-1014
Views:
285
Email this article 