This study presents a hybrid modeling framework integrating a deep learning-based black-box model of a CO₂ heat pump with a physics-based white-box system model developed in Modelica. The approach reduces the complexity of thermodynamic modeling while maintaining system-level accuracy. A deep neural network (DNN) trained on measured data predicts outlet temperatures and compressor power, coupled with the Modelica model through the Functional Mock-up Unit (FMU) interface. The framework was applied to a ground-source CO₂ heat pump system in Oslo, Norway, to evaluate hysteresis-based control strategies with different return temperature ranges (20–50 °C, 20–55 °C, 20–70 °C) and flow rates (1.3–1.5 kg/s). Results showed similar total heating but 25% lower compressor energy use for the 20–50 °C, 1.5 kg/s case compared to 20–70 °C. Temperature-based control improved coefficient of performance (COP) of the heat pump, while narrower temperature ranges and lower flow rates enhanced tank stratification and heat utilization. The findings demonstrate the effectiveness of the hybrid model for dynamic simulation and control optimization of CO₂ heat pump systems.

Traditional air conditioning consumes substantial electricity, exacerbates the urban heat island effect, and creates a maladaptive feedback loop, necessitating a shift toward passive-first net-zero pathways. This study takes a typical six-story residential building in Nanjing’s hot summer and cold winter climate zone as a case study. Using EnergyPlus hourly simulations, three progressive passive strategy packages are designed to quantify the impact of building envelope heat exchange on cooling loads, grid stress, and heat resilience. Package A includes external shading and natural ventilation. Package B adds reflective coating and a green roof. Package C further adds night ventilation precooling and high-performance windows. The results show that Package C achieves a 62.5% reduction in peak cooling load and a 63.0% reduction in seasonal cooling load. Daytime peak inward heat gain decreases from 68 W/m² to 22 W/m², while nighttime outward heat dissipation increases from 12 W/m² to 38 W/m². Under an extreme heat day of 41.2 °C with no active cooling, indoor peak temperature drops from 36.8 °C to 29.4 °C, and heat risk hours decrease by 73.6%. Peak-hour power demand is reduced by 70.4%, with a systemic leverage factor of 1.08. Innovations include achieving over 60% load reduction using only mature passive strategies, introducing the systemic leverage factor to quantify urban heat island mitigation benefits, and establishing a vulnerability-to-resilience transformation framework. The passive-first pathway validates building envelope as the first line of defense for net-zero futures. However, the findings are based on a typical six-story residential building in Nanjing and require validation through field measurements or broader application across different climate zones and building typologies before generalization.

The building sector faces an urgent challenge in balancing carbon neutrality goals with natural resource conservation. This study constructs a three-dimensional dynamic coupling model integrating Life Cycle Assessment, carbon footprint, and emergy analysis to evaluate the sustainability of a hydrogen–solar–geothermal hybrid energy system for an ecological office building in China’s hot summer and cold winter climate zone over a twenty-year horizon. The model incorporates dynamic factors including grid decarbonization, equipment efficiency degradation, and replacement cycles to overcome the systematic bias inherent in static LCA. Results reveal a significant trade-off: the hybrid system achieves a 29.8% reduction in global warming potential with a seven-year carbon payback period, yet non-renewable resource consumption doubles and resource scarcity damage increases by 173%. The carbon payback trajectory exhibits non-monotonic fluctuation, with electrolyzer replacement in year ten generating 360 tonnes of additional emissions that nearly reset the cumulative net value to zero. Multi-objective optimization identifies photovoltaic capacity as the system baseline (170–210 kW) and electrolyzer capacity as the primary regulating variable (35–62 kW), with the TOPSIS-recommended compromise solution of 200 kW photovoltaic, 50 kW electrolyzer, 30 kW fuel cell, and 32 m³ hydrogen storage achieving annual carbon emissions of 280 tonnes and a 33.3% reduction. Carbon pricing exhibits a nonlinear leverage effect with an incentive threshold of 200 RMB per tonne, substantially above China’s current 60–80 RMB per tonne level. This study concludes that while hydrogen–solar–geothermal hybrid systems offer substantial climate benefits, their comprehensive sustainability depends on proactive management of material scarcity costs, precise planning of equipment replacement cycles, and coordinated multi-level policy instruments. The findings provide methodological foundations for transitioning building carbon neutrality assessment from static LCA to dynamic coupling frameworks and from single carbon metrics to integrated carbon-resource-cost evaluations. All quantitative results presented herein are derived from this specific case study under the stated assumptions and parameter values; generalization to other building types or climate zones requires recalibration.