Different Responses of Loliginidae and Sepiolidae to Climate Change in Zhejiang Coastal Waters Driven by Life‐History Traits: A Machine Learning Approach

Cephalopods are commercially valuable invertebrates with short lifespans and rapid responsiveness to climate change, making them sensitive indicators of ecosystem dynamics. In recent decades, they have become the primary target species in the East China Sea (ECS) fishery following declines in demersal fish catches. Investigating the relationship between cephalopod populations and environmental factors enables researchers to characterize the ecological conditions conducive to their proliferation. The study employed six machine learning models to predict cephalopod distributions in the coastal waters of Zhejiang. Sea water temperature (SST) and chlorophyll‐a concentration (Chl‐a) were identified as key seasonal distribution drivers. Family‐level patterns largely reflected the dominant species, yet inter‐family differences revealed distinct environmental niches: Loliginidae favored warmer, nutrient‐rich waters, whereas Sepiolidae exhibited different seasonal patterns in their preferences for SST and Chl‐a. Notwithstanding these general consistencies, both cephalopods exhibited distinct spatiotemporal distribution patterns under different climate change scenarios. Under RCP2.6, Loliginidae were concentrated in the coastal waters of southern Zhejiang in spring and displayed a broader distribution in autumn. In contrast, under RCP8.5, their distribution range expanded notably with a northward migration in autumn. Sepiolidae showed a more constrained spatial distribution pattern, with shifts in their concentration areas across different climate scenarios and seasonal periods. Our findings systematically establish links between cephalopod spatiotemporal distribution patterns and dynamic environmental conditions, and highlight taxon‐specific responses to climate change, thereby providing a scientific reference for the formulation of future fisheries management strategies under variable climate scenarios.