The Northwest Indian Ocean is a key fishing ground for China’s pelagic fisheries, with the purpleback flying squid being a significant target. This study uses commercial fishing logs of the Indian Ocean between 2015 and 2021, alongside pelagic seawater temperature and its vertical temperature difference within the 0–200 m depth range, to construct generalized additive models (GAMs) and gradient boosting tree models (GBTs). These two models are evaluated using cross-validation to assess their ability to predict the distribution of purpleback flying squid. The findings show that factors like year, latitude, longitude, and month significantly influence the distribution of purpleback flying squid, while surface water temperature, 200 m water temperature, and the 150–200 m water layer temperature difference also play a role in the GBT model. Similar factors also take effects in the GAM. Comparing the two models, both GAM and GBT align with reality in predicting purpleback flying squid resource distribution, but the precision indices of GBT model outperform those of the GAM. The predicted distribution for 2021 by GBT also has a higher overlap with the actual fishing ground than that by GAM, indicating GBT’s superior forecasting ability for the purpleback flying squid fishing ground in the Northwest Indian Ocean.

The purpleback flying squid (Sthenoteuthis oualaniensis) is an economically significant cephalopod species in the Northwest Indian Ocean. Predicting its fishing grounds can provide a crucial foundation for fishery management and production. In this research, we collected data from China’s light-purse seine fishery in the Northwest Indian Ocean from 2016 to 2020 to train and validate the AlexNet and VGG11 models. We designed a data partitioning method (DPM) to divide the training set into three scenarios, namely DPM-S1, DPM-S2, and DPM-S3. Firstly, DPM-S1 was employed to select the base model (BM). Subsequently, the optimal BM was lightweighted to obtain the optimal model (OM). The OM, known as the AlexNetMini model, has a model size that is one-third of that of the BM-AlexNet model. Our results also showed the following: (1) the F1-scores for AlexNet and AlexNetMini across the datasets DPM-S1, -S2, and -S3 were 0.6957, 0.7505, and 0.7430 for AlexNet and 0.6992, 0.7495, and 0.7486 for AlexNetMini, suggesting that both models exhibited comparable predictive performance; (2) the optimal dropout values for the AlexNetMini model were 0 and 0.2, and the optimal training set proportion was 0.8; (3) AlexNetMini utilized both DPM-S2 and DPM-S3, yielding comparable outcomes. However, given that the training duration for DPM-S3 was relatively shorter, DPM-S3 was selected as the preferred method for data partitioning. The findings of our study indicated that the lightweight model for the purpleback flying squid fishing ground prediction, specifically AlexNetMini, demonstrated superior performance compared to the original AlexNet model, particularly in terms of efficiency. Our study on the lightweight method for deep learning models provided a reference for enhancing the usability of deep learning in fisheries.