Dynamic supply-side multipliers in China’s marine economy: A neural network-enhanced Ghosh model for sustainable development

Jian Jin and Mingqi Zhang

PLOS ONE, 2025, vol. 20, issue 10, 1-29

Abstract: With the continuous growth of China’s economy, marine economy plays an increasingly important role in the national economy. This study quantifies multiplier effects and supply-side dynamics in China’s marine economy (2017–2023) to inform sustainable development strategies. Combining the Ghosh model, employment analysis, and structural path analysis (SPA), we enhance traditional input-output frameworks with LSTM neural networks to capture nonlinear sectoral interdependencies. Key results reveal marine tourism as the dominant contributor to value added (44.346%), gross output (48.87%). Marine fishery exhibits the highest direct employment coefficient (0.42681), while marine mining drives significant indirect job growth (coefficient: 0.35072) in related industries. Marine transportation ranks first in income multiplier (8.60929) andemployment multiplier (3.0332), highlighting its pivotal role in household income. By innovatively integrating the Ghosh model with LSTM, this research overcomes static and linear limitations of conventional methods, providing policymakers with actionable insights for balanced sectoral development through optimized resource allocation and infrastructure investment.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0334336 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 34336&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0334336

DOI: 10.1371/journal.pone.0334336

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().