Consumption of aquatic products in China continues to grow and encourages the expansion of aquaculture farms. The examination of factors influencing expenditures on all aquatic products, freshwater fish, squid/octopus, and shellfish uses survey data collected from residents of Shanghai, China. The use of the Tobit modeling approach identified socio-demographic variables such as income, aquatic product safety perceptions, and preferences for quality as significant determinants of expenditures on aquatic product categories. Expenditures tend to increase with age, but the effect of education varies with regard to specific categories, suggesting distinct choices of educated consumers. Wives tend to spend substantially less on aquatic products than husbands. Knowledge of past sickness due to ingestion of aquatic products causes expenditures to drop in all categories, while quality certification, certified organic origin, and certified aquaculture products increase expenditure in selected categories. Monitoring consumer socio-demographic profiles and establishing transparent quality certification systems will benefit aquaculture farms and aquatic product marketers.

Predicting seafood consumption behavior is essential for fishing companies to adjust their production plans and marketing strategies. To achieve accurate predictions, this paper introduces a model for forecasting seafood consumption behavior based on an interpretable machine learning algorithm. Additionally, the Shapley Additive exPlanation (SHAP) model and the Accumulated Local Effects (ALE) plot were integrated to provide a detailed analysis of the factors influencing Shanghai residents’ intentions to purchase salmon. In this study, we constructed nine regression prediction models, including ANN, Decision Tree, GBDT, Random Forest, AdaBoost, XGBoost, LightGBM, CatBoost, and NGBoost, to predict the consumers’ intentions to purchase salmon and to compare their predictive performance. In addition, Bayesian optimization algorithm is used to optimize the hyperparameters of the optimal regression prediction model to improve the model prediction accuracy. Finally, the SHAP model was used to analyze the key factors and interactions affecting the consumers’ willingness to purchase salmon, and the Accumulated Local Effects plot was used to show the specific prediction patterns of different influences on salmon consumption. The results of the study show that salmon farming safety and ease of cooking have significant nonlinear effects on salmon consumption; the BO-CatBoost nonlinear regression prediction model demonstrates superior performance compared to the benchmark model, with the test set exhibiting RMSE, MSE, MAE, R² and TIC values of 0.155, 0.024, 0.097, 0.902, and 0.313, respectively. This study can provide technical support for suppliers in the salmon value chain and help their decision-making to adjust their corporate production plan and marketing activities

In order to address the carbon emissions generated by the plantation industry in China, this study used panel data from 30 provinces between 2012 and 2022 to predict and analyse the carbon emissions from the plantation industry through the LightGBM algorithm and SHAP. In addition, the hyper-parameters of the LightGBM regression model were optimised through a Bayesian optimisation algorithm and a five-fold cross-validation was applied to check the robustness of the machine learning regression model results. Finally, the SHAP model was used to analyse in depth the key factors affecting carbon emissions in the plantation industry and to explore ways to promote carbon emission reduction in China's plantation industry. The results show that agriculture-related financial expenditure, the number of agricultural high-tech enterprises and the number of rural professional cooperatives have negative effects and non-linear characteristics on carbon emissions from China's plantation industry. The LightGBM regression prediction model optimised by Bayesian algorithm outperforms the benchmark machine learning algorithm, and the R² mean value of the five-fold cross-validation is 0.982. The results of this study can provide scientific basis and technical support for promoting the sustainable development of Chinese agriculture.