ECOPERSIA

ECOPERSIA

The Use of Geostatistical Techniques to Predict the Distributional Areas of the Common Kilka (Clupeonella cultriventris) in the Southern Caspian Sea

Document Type : Original Research

Authors
Gozal Kokabee 1
mohammad farhangi 2
Hadi Raeisi 3
Hojatollah Jafariyan 4
1 Department of Fisheries, Faculty of Agricultural Science and Natural Resources, Gonbad Kavous University
2 Gonbad Kavous University
3 Assistant Professor, Department of Fisheries, Faculty of Agricultural Science and Natural Resources, Gonbad Kavous University
4 Associate Professor, Department of Fisheries, Faculty of Agricultural Science and Natural Resources, Gonbad Kavous University
10.48311/ecopersia.2026.104019.0
Abstract
Aims: The present study aimed to evaluate the spatial distribution of common Kilka (Clupeonella cultriventris) in the southern Caspian Sea using geostatistical interpolation, adaptive neuro-fuzzy inference system (ANFIS), and machine-learning approaches. The study addresses the limited use of integrated spatial and predictive modeling techniques to understand Kilka distribution patterns across varying environmental conditions.
Material & Methods: Daily catch and fishing-effort data were collected from commercial fishing grounds in Mazandaran Province between 1996 and 2021 during the active fishing season (April–October). Monthly CPUE values were calculated for six fishing stations. Environmental variables included fishing depth, chlorophyll-a concentration, sea surface temperature, and wind speed. Spatial interpolation methods (IDW, Kriging, and Natural Neighbor), ANFIS models with different membership functions, and a Multi-Layer Perceptron (MLP) model with a five-month lag structure were evaluated using prediction error metrics and correlation coefficients.
Findings: Among the evaluated interpolation methods, IDW with power 3 provided the most reliable representation of CPUE-based relative abundance patterns. Common Kilka abundance increased with fishing depth up to approximately 80 m and declined beyond this range. Among the ANFIS configurations, the Gaussian membership function yielded the highest predictive performance (r = 0.86). The MLP model with a five-month lag structure achieved the highest predictive performance within the evaluated dataset (R = 0.98). Fishing depth, chlorophyll-a concentration, sea surface temperature, and wind speed were identified as important predictors of Kilka distribution patterns.
Conclusion: The integration of geostatistical interpolation, ANFIS, and machine-learning approaches provided an effective framework for predicting the spatial distribution of common Kilka in the southern Caspian Sea. IDW produced the most reliable spatial interpolation results, whereas the MLP model demonstrated the highest predictive performance. The findings indicate that environmental variability plays an important role in shaping Kilka distribution patterns, and nonlinear predictive models may provide useful tools for fisheries management and ecological monitoring. Nevertheless, further validation with independent temporal datasets is recommended to assess the model’s generalizability and reduce potential temporal validation bias.
Keywords
Caspian Sea
Clupeonella cultriventris
CPUE, Geostatistics
Spatial Distribution
Subjects
1. Addis P., Secci M., Angioni A., Cau, A. Spatial distribution patterns and population structure of the sea urchin Paracentrotus lividus (Echinodermata: Echinoidea), in the coastal fishery of western Sardinia: a geostatistical analysis. Sci. Mar. 2012; 76(4): 733-740. 
2. Mohseni F., Saba F., Mirmazloumi S.M., Amani M., Mokhtarzade M., Jamali S., Mahdavi S. Ocean water quality monitoring using remote sensing techniques: A review. Mar. Environ. Res. 2022; 180: 105701. 
3. Trochta J.T., Branch T.A., Shelton A.O., Hay D.E. The highs and lows of herring: A meta‐analysis of patterns and factors in herring collapse and recovery. Fish 2020; 21(3): 639-662. 
4. Sun F., Sun W., Chen J., Gong P. Comparison and improvement of methods for identifying water bodies in remotely sensed imagery. Int. J. Remote Sens. 2012; 33(21): 6854-6875. 
5. Melo-Merino S.M., Reyes-Bonilla H., Lira-Noriega A. Ecological niche models and species distribution models in marine environments: A literature review and spatial analysis of evidence. Ecol. Model. 2020; 415: 108837. 
6. Gladju J., Kamalam B.S., Kanagaraj A. Applications of data mining and machine learning framework in aquaculture and fisheries: Smart Agric. Technol. 2022; 2: 100061. 
7. De Campos Souza P.V. Fuzzy neural networks and neuro-fuzzy networks: A review of the main techniques and applications used in the literature. Appl. Soft Comput. 2020; 92:106275. 
8. Ghoushchi S.J., Manjili S., Mardani A., Saraji M.K. An extended new approach for forecasting short-term wind power using modified fuzzy wavelet neural network: A case study in wind power plant. EN. 2021; 223: 120052. 
9. Leroy S.A., Lahijani H.A., Crétaux J. F., Aladin N.V., Plotnikov I.S. Past and current changes in the largest lake of the world: The Caspian Sea. Large Asian Lakes in a Changing World: Natural State and Human Impact. 2020; 65-107. 
10. Fazli H., Kaymaram F., Daryanabard G.R. Effects of fishing and environmental parameters on the commercial bony fish assemblage in the southern Caspian Sea. Oceanol. Hydrobiol. Stud. 2022; 51(1): 90-99. 
11. Naseka N.M., Bogutskaya N.G. Fishes of the Caspian Sea: zoogeography and updated check-list. Zoosyst. Ross. 2009; 18(2): 295-317. 
12. Janbaz A.A., Fazli H., Pourgholam R., Kaymaram F., Bandpei A., Abdolmaleki S., Khedmati K. Fishery and biological aspects of anchovy Kilka (Clupeonella engrauliformis) in the southern Caspian Sea. Iran. J. Fish. Sci. 2012; 11(4): 796-806. 
13. Fazli H., Janbaz A.A., Rabbaniha M., Khedmati K., Chaudhari H.S. Study of environmental and three Kilka species regime shifts in the Caspian Sea. Iran. J. Fish. Sci. 2021; 20(5): 1247-1261. 
14. Aazami J., Esmaili-Sari A., Abdoli A., Sohrabi H., Van den Brink P. J. Monitoring and assessment of water health quality in the Tajin River, Iran using physicochemical, fish, and macroinvertebrate indices. J. Environ. Health Sci. Eng. 2015; 13(1): 1-12. 
15. Hashemi S., Ghorbani R., Kymaram F., Hossini S.A., Eskandari G., Hedayati A. Relationship of physicochemical factors with fish biomass and production in Shadegan Wetland, Iran. B JBD. 2016; 17(2): 32-39. 
16. Franceschini S., Gandola E., Martinoli M., Tancioni L., Scardi M. Cascaded neural networks improving fish species prediction accuracy: the role of the biotic information. Sci. Rep. 2018; 8(1): 4581. 
17. Siddiqui S. A., Salman A., Malik M. I., Shafait F., Mian A., Shortis M. R., Harvey E. S. Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labeled data. ICES 2018; 75(1): 374-389. 
18. Allken V., Handegard N.O., Rosen S., Schreyeck T., Mahiout T., Malde K. Fish species identification using a convolutional neural network trained on synthetic data. ICES 2019; 76(1): 342-349. 
19. Sangün L., Güney O.İ., Özalp P., Başusta, N. Estimation of body weight of Sparus aurata with artificial neural network (MLP) and M5P. (nonlinear regression)–LR algorithms. Iran. J. Fish. Sci. 2020; 19(2): 541-550. URL: 
20. Muthukumaran V. Water quality index process using artificial neural networks. IJITRA. 2022; 1(1): 33-37. 
21. Zhang Y., Yamamoto M., Suzuki G., Shioya H. Collaborative forecasting and analysis of fish catch in Hokkaido from multiple scales by using neural network and ARIMA. Model. IEEE Access. 2022; 10(1): 7823-7833. 
22. Wackernagel M., Moran D., White S., Murray M. Ecological Footprint accounts for advancing sustainability: measuring human demands on nature. SDIs in Ecolo Econo. 2006; 246p.
23. Habashi H., Hosseini S.M., Shaaban Sh., Jahangard M. Evaluation and accuracy of interpolation methods in estimating total soil nitrogen using GIS. Spatial Information Systems Conference. 2015; 3: 1-7. 
24. Abzalov M., Abzalov M. Introduction to geostatistics. J. Appl.Min. Geol. 2016; 2: 233-237. 
25. Ahmed H., Siddique M.T., Iqbal M., Hussain F. Comparative study of interpolation methods for mapping soil pH in the apple orchards of Murree, Pakistan J.SE., 2017; 36(1): 70-76. 
26. Jiang C., Zhang H., Ren Y., Han Z., Chen K. C., Hanzo L. Machine learning paradigms for next-generation wireless networks. IEEE Wirel. Commun. 2016; 24(2): 98-105. 
27. Wang J., Duncan D., Shi Z., Zhang B. WEB-based gene set analysis toolkit (Web Gestalt): update 2013. Nucleic Acid. Res. 2013; 41(W1): W77-W83. 
28. Fazli H. Some Environmental Factors Effects on Species Composition, Catch and CPUE of Kilka in the Caspian Sea. ECOPERSIA 2011; 1(2); 157-164.
29. Martin P. Y. Gender as social institution. Soc. Force. 2004; 82(4): 1249-1273. 
30. Van Meirvenne M. Characterization of soil spatial variation using geostatistics. Ph.D. Thesis. Academic Press, University of Gent, Belgium. 1991;168P. 
31. Inniss L., Simcock A., Ajawin A. Y., Alcala A. C., Bernal P., Calumpong H. P., Węsławski J. M. The first global integrated marine assessment. United Nations. Accessed on 5 February. 2016. Bernal, P. &  A. Simcock. 2016. Marine Scientific Research. Chapter 30, p 1-18. In: L. Inniss and A. Simcock (Joint Coordinators). The First Global Integrated Marine Assessment. World Ocean Assessment I. United Nations, New York.
32. Henson S.A., Beaulieu C., Ilyina T., John J.G., Long M., Séférian R., Sarmiento J.L. Rapid emergence of climate change in environmental drivers of marine ecosystems. Nat. Commun. 2017; 8(1): 14682. 
33. Mirhasannia1 S.D., Akhoundian H., Taghavi H. Spatial and Temporal Distribution and Biomass Trend of Planktonic Green Microalgae (Chlorophyta) in Southeast of the Caspian Sea. ECOPERSIA 2019; 7(1):1-11. 
34. Jägerbrand A.K., Bouroussis C.A. Ecological impact of artificial light at night: effective strategies and measures to deal with protected species and habitats. Sustainability. 2021; 13(11): 5991. 
35. Gholizadeh M.H., Melesse A.M., Reddi L. A comprehensive review on water quality parameters estimation using remote sensing techniques. J. Sens. 2016; 16(8): 1298. 
36. Kalaji H.M., Jajoo A., Oukarroum A., Brestic M., Zivcak M., Samborska I.A., Ladle R.J. Chlorophyll a fluorescence as a tool to monitor physiological status of plants under abiotic stress conditions. Acta Physiol. Plant. 2016; 38(4): 1-11. 
37. Thanigaivel S., Vickram S., Dey N., Jeyanthi P., Subbaiya R., Kim W., Karmegam N. Ecological disturbances and abundance of anthropogenic pollutants in the aquatic ecosystem: Critical review of impact assessment on the aquatic animals. Chemosphere. 2022; 137475. 
38. Muruganandam M., Rajamanickam S., Sivarethinamohan S., Reddy M.K., Velusamy P., Gomathi R., Munisamy S.K. Impact of climate change and anthropogenic activities on aquatic ecosystem–A review. Environ. Res. 2023; 117233. 
39. Poloczanska E.S., Burrows M.T., Brown C.J., García Molinos J., Halpern B.S., Hoegh-Guldberg O., Sydeman W.J. Responses of marine organisms to climate change across oceans. Front. Mar. Sci. 2016; 62(3): 212-220. 
40. Makhlough A., Nasrollahzadeh Saravi H., Roohi A., Keyhansani A.R., Vahedi F. The study on dinocysts in the southern coastal waters of the Caspian Sea. Iran. J. Fish. Sci. 2022; 21(1): 48-62. 
41. Mahmoudi N., Babanezhad M., Seyfabadi J., Ahmadi M.R. Spatiotemporal relationships between life stages of the invasive ctenophore, Mnemiopsis leidyi, and environmental parameters in the southern Caspian Sea. J. Gt. Lakes Res. 2020; 46(5): 1262-1276. 
42. Liu S., Liu Y., Alabia I. D., Tian Y., Ye Z., Yu H., Cheng J. Impact of climate change on wintering ground of Japanese anchovy (Engraulis japonicus) using marine geospatial statistics. Front. Mar. Sci. 2020; 7(1): 41-47. 
43. Spencer P.D., Hollowed A. B., Sigler M.F., Hermann A.J., Nelson M.W. Trait‐based climate vulnerability assessments in data‐rich systems: An application to eastern Bering Sea fish and invertebrate stocks. Glob. Change Biol. 2019; 25(11): 3954-3971.