Abstract

Renewable energy continues to rise, with supercritical water gasification (SCWG) emerging as a potential biofuel production technique. Conventional approaches for estimating CH4 and H2 generation in complex systems frequently fail due to the complicated and dynamic nature of these processes. Machine learning (ML) has emerged as a disruptive technology in various industries, including energy, where it is used to optimize operations and improve prediction accuracy. Conventional techniques lack the versatility and scalability of ML models, resulting in less accurate and efficient prediction capabilities. This gap emphasizes the importance of incorporating machine learning into the energy domain, notably for optimization and prediction in SCWG processes. Furthermore, for any machine learning model, determining the appropriate hyperparameter setting has a direct and significant influence on its performance. In this study, we investigate the influence of three distinct types of hyperparameter optimization techniques on CH4 and H2 production prediction based on supercritical water gasification. Grid Search Optimization, Random Search Optimization, and Bayesian Optimization were analyzed utilizing six machine learning models: Ridge Lasso, Elastic Net, Decision Tree, Random Forest, and XGBoost, as well as two ensemble models: linear-based and tree-based models. The dataset from supercritical water gasification of Yimin lignite was used based on three evaluation metrics: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2). The results were evaluated based on 5-fold cross-validation and results show that the Random Forest stood out with an R2 of 0.995, RMSE of 0.109, and MAE of 0.085 for the CH4 production prediction while recording an R2 of 1.00, RMSE of 0.112 and MAE of 0.088 for H2 production prediction. The analysis carried out in this study shows that the choice of optimization technique does not significantly impact the performance of the deployed models, which indicates that the hyperparameter space is relatively well-behaved for this CH4 and H2 Production Prediction based on Supercritical Water Gasification, and thus even simpler optimization strategies like Random Search can perform nearly as well as more sophisticated ones like Bayesian Optimization. The result implies that if computation time or resources are a factor, Random Search would be a more efficient approach without a significant trade-off in model performance

Abstract

Countries worldwide are adopting carbon neutrality targets to address global warming challenges. High-density cities, viewed as a promising path toward a sustainable future, exhibit a unique emission pattern dominated by the building sector. Therefore, this study devised a lightweight and adaptable modeling framework to project long-term carbon emissions from building operations, outlining a decarbonization roadmap for the building sector in high-density cities, with Hong Kong as a case. Using multi-source data, the features of each district are considered, such as land planning, technology, and socioeconomic factors. The model was built and validated by data over ten years, with a mean percentage error of 5%. Results reveal that radical policies are necessary for carbon neutrality, necessitating simultaneous energy demand and supply decarbonization. Limited space for renewables in such cities makes demand-side technologies vital. Electrifying home appliances display significant carbon reduction potential. Among building types, public facilities, multi-functional commercial buildings, and private housing offer substantial reduction potential. The proposed carbon mitigation roadmap underscores the complex nature of achieving carbon neutrality in high-density cities, calling for comprehensive strategies from various sectors.

Abstract

Hydrate-based CO2 sequestration has emerged as one of the possible methods for the long-term storage of CO2 as hydrates within the geological media, notably under marine sediments. In this direction, a thermodynamic model for the phase equilibria of CO2 hydrates in pure water and THF solutions (≤ 5.56 mol%), based on the fugacity approach is employed to predict the three-phase (LHV) equilibrium pressures and the fractional occupancy of CO2 and THF molecules in small and large cages. The hydrate, vapor, and liquid phases are modeled using the van der Waals-Platteeuw solid solution theory, Peng-Robinson-Stryjek-Vera equation of state, and the modified UNIFAC method, respectively. The model-predicted equilibrium pressures are in excellent agreement with experimental data with an AAD of 1.55%. The presence of THF has greatly reduced the CO2 hydrate equilibrium pressures. The cage occupancy results revealed the reduction in small cage occupancy of CO2 at (≥) 1.296 mol% THF and a continuous substantial decrease in large cage occupancy of CO2 with increased THF concentration. However, the overall hydrate stability is ensured by the large cage occupancy of the large molecule THF in larger fractions. This study is an important precursor for future hydrate-based CO2 sequestration.

Abstract

Air-source heat pump, as an efficient and clean heating methods, have significant potential in the electrification of energy terminals within public buildings. This study delves into the suitability of air-source heat pumps for use in public buildings located in severe cold, cold, and hot-summer and cold-winter regions. Considering the performance adjustments required under defrosting and low-temperature conditions, the heating system is constructed using the TRNSYS software. The hourly operational characteristics and dynamic control strategies of heat pump clusters are simulated and analyzed across various climate regions and public building types. The results reveal a positive correlation between the COP of heat pump systems and outdoor temperature, with COP values of 1.64 (Harbin), 2.57 (Beijing), and 2.81 (Shanghai), alongside average operation numbers of 16.6 (Harbin), 7.5 (Beijing), and 2.6 (Shanghai). Notably, the COP remains unaffected by the type of public building. This study aims to offer valuable insights for the application and regulation of air-source heat pumps in public buildings.