Strengthening regulations on carbon emissions from ships is important for ensuring that China can achieve its dual carbon aims of reaching peak carbon emissions before 2030 and achieving carbon neutrality before 2060. Currently, the primary means of monitoring ship exhaust emissions are the sniffing method and non-imaging optical remote sensing; however, these methods suffer from a low prediction efficiency and high cost. We developed a method for predicting the CO₂ content of ship exhaust that uses a convolutional neural network and mid-infrared spectral images. First, a bench experiment was performed to synchronously obtain mid-wave infrared spectral images of the ship exhaust plume and true values for the CO₂ concentration from the online monitoring of eight spectral channels. Then, the ResNet50 residual neural network, which is suitable for image prediction tasks, was selected to predict the CO₂ content. The preprocessed mid-infrared spectral image of each channel and the corresponding true value for the CO₂ content were input to the neural network, and convolution was applied to extract the radiation characteristics. The neural network then mapped the relationship between the true CO₂ content and the radiation characteristics for each channel, which it used to predict the CO₂ content in the ship exhaust. The results demonstrated that the predicted and true CO₂ contents had a root mean square error of <0.2, mean absolute error of <0.15, and mean absolute percentage error of <3.5 for all eight channels. The developed model demonstrated a high prediction accuracy with one channel in particular demonstrating the best performance. This study demonstrates that the method used for predicting the CO₂ content of ship exhaust based on convolutional neural networks and mid-infrared spectral images is feasible and has reference significance for the remote monitoring of ship exhaust emissions.

Liver simulation serves as a crucial foundation for precise preoperative planning and intraoperative navigation, with its accuracy and real-time performance directly impacting the safety and efficiency of surgical procedures. However, existing physical simulation techniques face a trade-off between high precision with slow computational speeds and rapid performance with diminished accuracy. This imbalance restricts their utility in dynamic surgical environments that demand both accuracy and real-time interaction. To overcome this limitation, we present a novel real-time liver simulation algorithm leveraging Extended Position-Based Dynamics (XPBD). Our approach integrates four well-formulated physical constraints–Distance, Volume, Shape Matching, and the Neo-Hookean model–within a proprietary, high-efficiency physics engine, achieving high-precision, real-time simulation of hepatic geometric deformations and mechanical properties. Experimental evaluations reveal that our method not only meets the stringent real-time requirements of surgical procedures but also significantly enhances the visual realism and stability of simulations. This advancement demonstrates substantial potential for extensive applications in preoperative planning, intraoperative navigation, and medical training.