The relationship between the annual catch of bigeye tuna and climate factors and its prediction DOI Creative Commons
Pingxing Ding, Hui Xu,

Xiaorong Zou

et al.

Frontiers in Marine Science, Journal Year: 2024, Volume and Issue: 11

Published: Dec. 24, 2024

Introduction In order to explore the impact of climate factors on bigeye tuna catch, monthly data nine factors, including El Niño-related indices (Niño1 + 2, Niño3, Niño4, and Niño3.4), Southern Oscillation Index (SOI), North Atlantic (NAO), Pacific Decadal (PDO), (NPI), global sea–air temperature anomaly index (dT), were combined with annual catch. Methods The relationship between low-frequency catch was studied using long short-term memory(LSTM) model, random forest (RF) BP neural network extreme gradient boosting tree (XGBoost) Sparrow search optimization algorithm (SSA-XGBoost) model. Results results show that optimal lag periods corresponding change characterization Niño1 dT, SOI, NPI, NAO, PDO are 15 years,12 years, 12 1 year, 14 4 respectively. SSA-XGBoost model have highest prediction accuracy, followed by XGBoost, BP, LSTM, RF. fitting degree predicted values actual is 0.853, mean absolute error 0.104, root square 0.124. Discussion trend generally consistent, indicating good performance, which can provide a basis for management fisheries.

Language: Английский

Habitat Suitability of Thunnus spp. in the Northern South China Sea Based on the Maxent Species Distribution Model DOI

Alma Alfatat,

Hagai Nsobi Lauden, Shaoliang Lyu

et al.

Regional Studies in Marine Science, Journal Year: 2025, Volume and Issue: unknown, P. 104238 - 104238

Published: May 1, 2025

Language: Английский

Citations

0
The relationship between the annual catch of bigeye tuna and climate factors and its prediction DOI Creative Commons
Pingxing Ding, Hui Xu,

Xiaorong Zou

et al.

Frontiers in Marine Science, Journal Year: 2024, Volume and Issue: 11

Published: Dec. 24, 2024

Introduction In order to explore the impact of climate factors on bigeye tuna catch, monthly data nine factors, including El Niño-related indices (Niño1 + 2, Niño3, Niño4, and Niño3.4), Southern Oscillation Index (SOI), North Atlantic (NAO), Pacific Decadal (PDO), (NPI), global sea–air temperature anomaly index (dT), were combined with annual catch. Methods The relationship between low-frequency catch was studied using long short-term memory(LSTM) model, random forest (RF) BP neural network extreme gradient boosting tree (XGBoost) Sparrow search optimization algorithm (SSA-XGBoost) model. Results results show that optimal lag periods corresponding change characterization Niño1 dT, SOI, NPI, NAO, PDO are 15 years,12 years, 12 1 year, 14 4 respectively. SSA-XGBoost model have highest prediction accuracy, followed by XGBoost, BP, LSTM, RF. fitting degree predicted values actual is 0.853, mean absolute error 0.104, root square 0.124. Discussion trend generally consistent, indicating good performance, which can provide a basis for management fisheries.

Language: Английский

Citations

0