Efficient indoor environmental management is vital for reducing energy use while safeguarding indoor air quality and occupants’ comfort. However, due to difficulty of obtaining comprehensive datasets across multiple domains, many current studies still focus on a single performance metric, with dataset limitations preventing the development of robust and accurate multi-objective predictive models and operate as opaque data-driven systems with limited explanatory capability. This work developed CFD datasets derived from an experimentally validated model to systematically generate data covering parameters of indoor air quality, energy use, and thermal sensation with varied ventilation conditions. This dataset is further used for machine learning (ML) analysis. A cutting-edge Tabular Prior-data Fitted Network (TabPFN) is adopted for multi-target prediction and benchmarked against XGBoost, CatBoost, and Backpropagation Neural Networks (BPNN). SHapley Additive exPlanations (SHAP) method was used to elucidate its predictions, identifying how the most influential parameters govern the variations in indoor environmental behavior. The findings indicate that TabPFN outperforms the other three models in both predictive accuracy and computational efficiency, with MAE reduced by 62.08-95.4 % and RMSE by 49.15-85.50 %, while inference is accelerated by 67.5-85.9 %. SHAP analysis quantified nonlinear and directional contributions of features, linking model outputs to physical mechanisms such as draft risk, thermal sensation, and cooling load demand. The proposed TabPFN-SHAP framework is expected to offer valuable insights to guide the optimisation of building environmental control strategies.

Inhaled drug delivery is a promising strategy for the rapid treatment of respiratory diseases due to its direct targeting of the pulmonary system. Nevertheless, challenges remain in optimizing deposition efficiency, particularly in reaching deeper lung generations and achieving directional control of particle transport. To achieve effective deep-lung aerosol delivery, the present proof-of-concept study proposes computational optimization of particle release strategies. Both non-invasive and invasive approaches are explored, with particular emphasis on release concentration and spatial positioning. Numerical simulations are conducted using a previously validated subject-specific mouth-to-lung model reconstructed from high-resolution Computed Tomography (CT) scans, ensuring anatomical realism and geometrical reproducibility. The results show that concentrated non-invasive release at the mouth plane improves particle penetration through the constricted laryngeal region. Meanwhile, invasive strategies involving focused delivery (such as catheter-based injection) lead to enhanced deposition in the deeper lung regions. Notably, directional control of deposition was preliminarily achieved, with particles preferentially targeting either the left or right lung lobe based on the injection position, offering new potential for site-specific therapy. It is concluded that the presented computational framework can provide detailed insights for optimizing particle transport and deposition in specific lung regions. These detailed insights could provide valuable information for developing novel clinical treatments for respiratory diseases.

Deep coal mining operates in increasingly extreme environments, where substantial dust generated during the mining process poses serious risks to both production safety and miners' health. To understand the dust transport pattern and miners' particulate exposure risk within a full-scale heading face under various ventilation configurations, airflow patterns and dust dispersion characteristics were systematically investigated using the Euler-Lagrangian approach. A user-defined function was developed to enable the dynamic injection of particles, simulating realistic dust generation processes. The average residence times of particles with varying sizes were calculated, and the number of particles entering the respiratory zone was quantified to assess the driver's exposure risk. Results revealed that the driver remained in the recirculation zone in all layouts. The centrally positioned ventilation cylinder facilitated the suspension of smaller particles. With a total suspension time of 300 s and an air supply velocity of 11 m/s, particles sized below 20 µm exhibited the longest average residence time—11.24% and 26.24% longer than in layout R (cylinder on the opposite side of the driver) and layout L (cylinder on the driver's side), respectively. Smaller respiratory dust (i.e., d p < 7.07 µm) and particles originating from the upper part of the dust injection surface were most likely to enter the driver's respiratory zone. Increasing the fresh air supply alone proved insufficient to reduce particulate exposure. Among the configurations, layout L was optimal, reducing particulate exposure by 65.12% compared to layout R. This study provides theoretical insights for optimizing ventilation strategies within the heading face.

Targeted drug delivery to the deep lung improves therapeutic outcomes, but respiratory system variability complicates drug spray design. Numerical simulations offer insights for individualized treatments but are computationally intensive, highlighting the need for surrogate models for real-time deposition prediction. This study comprehensively explores the multi-task predictive capability of regression models, including Linear regression (LR), Bayesian regression (BR), Back Propagation Neural Network (BPNN), Support Vector Machine (SVM), Random Forest (RF), XGBoost, and CatBoost, for predicting total and regional deposition rates of inhaled particles in airway. A training dataset is obtained from well-validated CFD simulations with realistic human airway model using Euler-Lagrangian method. The results indicate that LR, BR, and SVM yield unsatisfactory predictive accuracy, with average R² values in range of 0.21 to 0.73. Comparatively, BPNN and decisiontree-based models show great potential in predicting total deposition rate in the upper and central airway. However, for regional deposition rate prediction, BPNN did not consistently yield high accuracy, particularly for oral deposition (R² = 0.538). Comparatively, XGBoost emerges as optimal model, achieving an R² approximately close to 1 on both the training and testing datasets, with predictive errors within the range of ±0.5. The overall results demonstrate that decision-tree-based models, particularly XGBoost, have superior performance in accurately predicting both total and regional deposition rates of inhaled particles within airway. Despite limitations like geometry complexity and data quantity, the workflow developed in this study is expected to pave the way for future research integrating ML models into drug delivery device design and evaluation.