Building Damage Mapping of the 2024 Noto Peninsula Earthquake, Japan, Using Semi-Supervised Learning and VHR Optical Imagery

Deep learning (DL) models are generally less able to maintain their performance in out-of-domain (OOD) testing. Model transferability is crucial, especially when a model needs to be applied to a new dataset, such as in disaster emergency response, where the training samples are scarce. To solve the aforementioned issues, we propose a semi-supervised framework to improve model generalization using unlabeled samples from the target domain. The framework consists of two main steps: model initialization, which incorporates past events, and iterative fine-tuning. The latter step relies heavily on the pseudolabels inferred with high confidence from the former step. We tested our framework on the 2024 Noto Peninsula Earthquake. Our framework shows an improvement in model generalization indicated by higher scores in the tuned model compared with the initial model. The effect is even greater when the local context from the past event is included in the initial learning step. In this case, the score has increased by about 21% from 0.62 to 0.75. The proposed framework offers a promising solution for rapid disaster damage mapping.