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.

Archaeological sites are extremely vulnerable to the impacts of weather-related events, which may lead to irreparable damages to cultural heritage. Here an assessment of the debris-flow hazard for the UNESCO site of Roman Villa del Casale (Italy) is carried out, through a combination of historical analyses, field surveys, geomorphological and hydrological investigations and two-dimensional hydraulic numerical modelling, all performed at river catchment scale. Historical analyses reveal that the site has been hit by several landslides in the far and recent past. This is presently confirmed by the high level of exposure to the impact of rain-triggered debris-flow events, due to the position of the Villa at a closure section of the related river basin and to the hydro-geomorphological characteristics of the basin itself. By applying the proposed approach, a scenario analysis is carried out. Results allow one to highlight the dynamics of the impact of debris flows, thanks to space and time-dependent maps about deposition areas, water depth and speed values, and to identify the most vulnerable archaeological elements within the study site. The numerical simulations are also used to test the efficiency of the existing hydraulic defense systems and to support the implementation of an early warning system for the site protection. Here we also synthetize the design of the architecture of the wireless monitoring network, the sensor technology adopted to develop an effective real time environmental monitoring system and management platform, to construct a Wireless Sensor Network (WSN) - early warning and reporting system, which can be applied as a prevention measure.