Prediction of Bandgap in Lithium-Ion Battery Materials Based on Explainable Boosting Machine Learning Techniques.

The bandgap is a critical factor influencing the energy density of batteries and a key physical quantity that determines the semiconducting behavior of materials. To further improve the prediction accuracy of the bandgap in silicon oxide lithium-ion battery materials, a boosting machine learning model was established to predict the material's bandgap. The optimal model, AdaBoost, was selected, and the SHapley Additive exPlanations (SHAP) method was used to quantitatively analyze the importance of different input features in relation to the model's prediction accuracy.

Fast Building Instance Proxy Reconstruction for Large Urban Scenes.

Digitalization of large-scale urban scenes (in particular buildings) has been a long-standing open problem, which attributes to the challenges in data acquisition, such as incomplete scene coverage, lack of semantics, low efficiency, and low reliability in path planning. In this paper, we address these challenges in urban building reconstruction from aerial images, and we propose an effective workflow and a few novel algorithms for efficient 3D building instance proxy reconstruction for large urban scenes. Specifically, we propose a novel learning-based approach to instance segmentation of urban buildings from aerial images followed by a voting-based algorithm to fuse the multi-view instance information to a sparse point cloud (reconstructed using a standard Structure from Motion pipeline).