The low-carbon economy is becoming a critical global development paradigm. As the world’s largest carbon emitter, China’s transition toward low-carbon practices in its construction sector is pivotal for achieving its carbon peaking and carbon neutrality goals. Research into the decarbonization pathways and driving factors of this energy- and emission-intensive industry is essential. It not only reduces the sector’s dependence on traditional energy sources but also provides vital support for China’s national energy conservation and emissions reduction strategy. As the construction industry transitions toward low-carbon sustainability, traditional unidimensional assessments based solely on socio-economic and ecological factors are inadequate. This study proposed an integrated evaluation framework using the CRITIC–TOPSIS model, incorporating technological, social, economic, industrial, and energy dimensions. Panel data on energy consumption in the Yangtze River Delta (YRD) region were employed to assess the construction sector’s low-carbon development level and an ARIMA model was utilized to forecast its low-carbon potential. The results indicate that from 2011 to 2022, the sector’s total carbon emissions followed a unimodal trajectory (initial increase followed by decline), with indirect emissions exceeding 90%, primarily from cement, steel, and other building materials. The regional construction industry exhibited a unimodal trajectory in low-carbon development, characterized by an initial increase followed by a decline. Average construction carbon emissions reached 41,637.5877 million tons, with a transient surge (69.67% increase) occurring between 2011 and 2014. This was followed by a 41.83% reduction from 2014 to 2022, with emissions projected to stabilize and gradually increase through 2030. Technological and industrial factors constitute the primary drivers of sectoral low carbon. Quantitative analysis identified the capital utilization rate, industrial structure, and construction industry gross domestic product (GDP) as key impediments to low-carbon transition, with average impedance degrees of 8.713%, 12.280%, and 12.697%, respectively. This study has revealed the key driving factors for the low-carbon development of the construction industry, extending theoretical frameworks for construction industry sustainability. These findings offer empirical support for formulating regionally differentiated carbon mitigation policies.

As a major contributor to energy consumption and carbon emissions, the low-carbon transformation of the construction industry is crucial for China to achieve its established carbon-emission reduction targets. Therefore, a systematic analysis of the spatial and temporal evolution trends and key drivers of carbon emissions in the construction industry is an important reference for the formulation of emission reduction policies in the industry and the promotion of green and low-carbon development. This study first estimated carbon emissions from direct and indirect energy consumption in China’s construction industry. Spatial and temporal variations in emissions were then analyzed using spatial autocorrelation and kernel density methods. Furthermore, an improved logarithmic mean Divisia index decomposition model, tailored to the characteristics of the construction industry, was applied to quantify the key driving factors. The results reveal that total carbon emissions follow an inverted U-shaped trend, with indirect carbon emissions—mainly from the production of cement and steel—being the dominant contributors. Emissions display a spatially uneven pattern: high in the east and south, low in the west and north, with the high-emission zone gradually expanding from the east to the central regions. Marked regional differences also exist in the evolution of emission intensity. Output intensity and energy intensity are identified as primary drivers of emissions, with their impact particularly prominent in the eastern region. These findings provide a quantitative basis and theoretical support for developing region-specific emission reduction policies, advancing the green and high-quality development of China’s construction industry.

The rapid expansion of high-speed railway networks has increased the operational energy demand and indoor overheating risk of large-scale, high-volume railway station buildings. Natural ventilation is a climate-responsive passive strategy that can improve indoor environmental quality and reduce reliance on mechanical cooling. However, its contribution to the operational sustainability of large transportation buildings remains insufficiently quantified, particularly in hot-summer and cold-winter regions. This study investigates a seasonally adaptive window-opening strategy for Chengdu Station, with particular attention to major functional spaces such as waiting halls and commercial areas. A DesignBuilder model was used to simulate six ventilation scenarios, ranging from doors-only operation to fully open doors and windows. The effects of different window-opening ratios on hourly indoor temperature, relative humidity, adaptive thermal comfort, and annual building energy use were systematically evaluated. The simulation approach was further assessed against field measurements obtained from a comparable large railway station. The results reveal a pronounced nonlinear and seasonal response to the window-opening ratio. In winter, maintaining a very low opening ratio or keeping only the entrance doors open limits unnecessary heat loss. During the transitional seasons, opening ratios of 40–60% are sufficient to remove residual indoor heat while maintaining acceptable thermal conditions. In summer, the marginal improvement in ventilation performance becomes limited when the side-window opening ratio exceeds approximately 80%; therefore, an opening ratio of 80% was selected as a practical operating threshold rather than an absolute thermal optimum. Based on these seasonal characteristics, a month-by-month window-opening strategy was developed. Compared with the doors-only baseline, the proposed strategy reduced the annual high-temperature-hour ratio from 33.4% to 16.36%, corresponding to a decrease of 17.04 percentage points and a relative reduction of approximately 51.0%. Total annual building energy use decreased from 32,238.8 MWh to 25,923.8 MWh, representing an energy saving of 19.6%. These findings demonstrate that seasonally adaptive natural ventilation can simultaneously reduce overheating risk and operational energy demand while maintaining acceptable indoor thermal conditions. The proposed strategy provides a quantitative basis for the sustainable, energy-efficient, and intelligently managed operation of large-space railway stations in hot-summer and cold-winter regions.

In the context of global climate mitigation and China’s “Dual Carbon” targets, accurately identifying emission drivers and forecasting long-term trajectories at the provincial level has become a critical research priority for designing sustainable transition pathways. This study investigates carbon emissions in Sichuan Province over the period 1997–2022 using an integrated analytical workflow that sequentially couples Pareto-based feature selection and robust partial least squares regression (PLSR) for explanatory driver identification, with recurrent neural network (RNN) modeling for independent trend projection. Pareto filtering is employed to isolate 34 high-impact variables that collectively explain 85% of total emissions. To address numerical instability in the explanatory phase, a log-transformed robust PLSR is implemented. Separately, to extrapolate near-term trajectories, a dynamically switched long short-term memory (LSTM) and gated recurrent unit (GRU) architecture is utilized under stability assumptions, operating within a data-driven framework with empirically calibrated physical constraints. This integrated modeling approach demonstrates strong explanatory performance (training R² = 0.9237, cross-validation Q² = 0.7241) and yields a mean absolute percentage error (MAPE) of 3.11–3.53% on a chronologically separated five-year validation period (2018–2022). This low error—achieved over a holdout interval encompassing the Double Carbon policy announcement and COVID-19 disruptions—provides preliminary evidence of the model’s capacity to capture the dominant inter-annual emission dynamics for short-horizon projection, despite the inherent constraint of limited annual observations (N = 26). Among the identified drivers, the utilization of by-product gases in heavy industry and gasoline consumption in urban transportation exhibit the strongest positive influence, with variable importance in projection (VIP) scores exceeding 1.5. Conversely, coal use in urban residential sectors exerts a modest negative effect on emission growth (elasticity = −0.023). Under empirically bounded stability assumptions, the constrained baseline projection suggests that total emissions may edge down to 259.84 Mt by 2027. However, this apparent trajectory, is strictly conditioned by the imposed year-to-year change limits. It must be interpreted as a restricted scenario outcome rather than an independent predictive discovery of an approaching carbon-peaking plateau. While the explanatory fit of the PLSR component does not mathematically validate the subsequent neural-network forecasts, this research offers a practical methodological reference for the application-specific integration of established statistical and deep-learning tools in regional emission diagnosis.