With the increasing severity of global climate change, low-carbon development has become a key issue in the energy industry. As an effective way to optimize energy utilization and reduce carbon emissions, integrated energy system is receiving increasing attention. However, existing low-carbon control methods still face many challenges in improving system efficiency and reducing carbon emissions, and the ability of multi-energy cooperative scheduling and optimal control is insufficient. Therefore, a hybrid algorithm combining the particle swarm optimization and cuckoo search algorithms is designed to adjust the integrated energy low-carbon control capability. The proposed algorithm required fewer iterations than the genetic cuckoo algorithm, which only went through 43 iterations. The convergence speed was improved by 34.8% compared with a single cuckoo algorithm. Among the four scenarios, scenario 4 and scenario 3 had the highest utilization rates of 99.75%, while scenario 1 had the lowest utilization rate of 61.96%. This indicates that the integrated energy system controlled by the particle swarm optimization cuckoo algorithm, while considering carbon capture and storage as well as power-to-gas conversion, can effectively utilize solar energy resources for power generation and achieve energy-saving and emission reduction effects. In summary, this method can help the integrated energy system adapt to various optimization strategies, which promotes the development of low-carbon control technologies in the energy industry.

Carbon emission prediction of coastal port-industrial zones integrates industrial production, maritime logistics and spatial environmental governance. Existing models fail to simultaneously capture multi-scale temporal fluctuations and spatial correlations of industrial units under meteorological and policy interference. This paper constructs an interpretable dual-branch framework combining Ensemble Empirical Mode Decomposition–XGBoost (EEMD-XGBoost) and a Temporal Graph Neural Network (T-GNN). The EEMD-XGBoost branch extracts multi-scale temporal features from non-stationary emission sequences, while the T-GNN models spatiotemporal dependencies of industrial sub-units; weighted fusion integrates the two branches, and the framework outputs interpretable indicators including feature importance, spatial contribution and temporal attention weights to analyze emission driving factors. Two 2023 datasets are adopted: a coastal-port prefecture-level subset derived from the national regional carbon dataset (28 coastal port-related prefectures), split chronologically into 70% training and 30% test sets; the Yangtze River Delta ship dataset integrating AIS, ship properties and fuel data is partitioned via tonnage-based stratified sampling into 7:2:1 training–validation–test subsets, with an independent test subset for short-term ship-type forecasting. On the independent ship test set for maritime greenhouse gas prediction, the proposed model achieves an R² of 0.96, 0.95 and 0.93 for container, bulk and oil ships respectively, which only applies to ship-scale forecasting rather than regional carbon prediction. Special ablation experiments show that single T-GNN converges within 72 epochs, single EEMD-XGBoost has a high-frequency fitting error of 6.82%, and the complete dual-branch model reaches a spatial feature capture rate of 94.65% with only a 3.47% fitting error, despite a 27.52 ms single-sample inference time, proving the synergy of the two branches. The model outperforms baselines under abnormal and sparse data conditions. This interpretable framework supports traceable refined carbon management and provides quantitative engineering implications for port zoning control, differentiated ship emission reduction and regional low-carbon policy implementation.