Rapid socio-economic development has made energy application and environmental issues increasingly prominent. Hydrogen energy, clean, eco-friendly, and highly synergistic with renewable energy, has become a global research focus. This study, using the EnergyPLAN model that includes the electricity, transportation, and industrial sectors, takes Jinan City as the research object and explores how hydrogen penetration changes affect the decarbonization path of the urban integrated energy system under four scenarios. It evaluates the four hydrogen scenarios with the entropy weight method and technique, placing them in an order of preference according to their similarity to the ideal solution, considering comprehensive indicators like cost, carbon emissions, and sustainability. Results show the China Hydrogen Alliance potential scenario has better CO₂ emission reduction potential and unit emission reduction cost, reducing them by 7.98% and 29.39%, respectively. In a comprehensive evaluation, it ranks first with a score of 0.5961, meaning it is closest to the ideal scenario when cost, environmental, and sustainability indicators are comprehensively considered. The Climate Response Pioneer scenario follows with 0.4039, indicating that higher hydrogen penetration in terminal energy is not necessarily the most ideal solution. Instead, appropriate hydrogen penetration scenarios should be selected based on the actual situation of different energy systems.

The post-combustion carbon capture process with monoethanolamine/piperazine (MEA/PZ) blends encounters notable modeling and optimization challenges. These arise from strong thermodynamic–kinetic nonlinear coupling, as well as limited availability of high-quality experimental data. To address this, we propose a machine learning and multi-objective optimization strategy driven by physicochemical features. By extracting explicit physical features and embedding physicochemical constraints into data-driven models, this study evaluated the predictive performance of three distinct algorithms based on wet-wall column experimental data. These algorithms included natural gradient boosting (NGBoost), sure independence screening and sparsifying operator (SISSO), and gaussian process regression (GPR). Subsequently, an optimization problem aimed at minimizing $P_{{\mathrm{CO}}_2}^{*}$ and maximizing $k_{\mathrm{g}}^{\prime }$ was formulated. The multi-objective beluga whale optimization (MOBWO) algorithm was then employed for global optimization and benchmarked against the traditional non-dominated sorting genetic algorithm II (NSGA-II). Results indicate that the Gaussian process regression (GPR) model performed best when it was enhanced by physicochemical features and optimized via Bayesian hyperparameter tuning. It achieved R² values of 0.989 and 0.953 for $P_{{\mathrm{CO}}_2}^{*}$ and $k_{\mathrm{g}}^{\prime }$, with average absolute relative deviations (AARDs) kept below 15.7% and 12.2% respectively. Feature importance analysis validated the underlying physical laws. Specifically, temperature dictates thermodynamic equilibrium, while CO₂ loading limits mass transfer kinetics. In the optimization phase, MOBWO outperformed NSGA-II by generating a more uniformly distributed Pareto front. Decision-making analysis further identified three typical operating regimes encompassing kinetics-dominant, thermodynamics-dominant, and comprehensive equilibrium conditions. This framework provides a robust paradigm for small-sample modeling and optimization in complex chemical processes.