Lau Tsz-Kin, Huang Kai-Hsiang
Department of Civil Engineering, National Kaohsiung University of Science and Technology, No. 415, Jiangong Rd., Sanmin Dist., Kaohsiung City 807618, Taiwan.
Department of Civil Engineering, National Kaohsiung University of Science and Technology, No. 415, Jiangong Rd., Sanmin Dist., Kaohsiung City 807618, Taiwan.
Sci Total Environ. 2024 Feb 20;912:169500. doi: 10.1016/j.scitotenv.2023.169500. Epub 2023 Dec 22.
Oil spill accidents are a key contributor to marine pollution worldwide. Therefore, timely and effective oil spill detection is crucial for reducing marine pollution and enhancing environmental protection. Against this backdrop, this study explored two methods for performing nearshore on-site oil spill detection and segmentation, namely the U-net and Mask region-based convolutional neural network (R-CNN) methods. The U-net and Mask R-CNN models were revealed to exhibit acceptable and favorable performance, achieving overall accuracy of 77.01 % and 89.02 %, respectively. Subsequently, a verification system based on the Geographic Information System (GIS) was developed to improve the performance of the deep-learning model. With the integration of the verification system, the Mask R-CNN model achieved higher overall accuracy of 90.78 %. The feasibility of applying deep-learning methods to nearshore on-site oil spill monitoring was demonstrated through this study. In addition, the integration of the GIS not only assisted in the provision of oil spill information but also in the improvement of the deep-learning models. The timely, accurate, and effective method for nearshore on-site oil spill monitoring that this study explored can be applied to considerably improve traditional on-site oil spill monitoring, which has received limited academic attention in the last two decades.
石油泄漏事故是全球海洋污染的一个关键因素。因此，及时有效的石油泄漏检测对于减少海洋污染和加强环境保护至关重要。在此背景下，本研究探索了两种用于近岸现场石油泄漏检测与分割的方法，即U-net和基于掩膜区域的卷积神经网络（R-CNN）方法。结果显示，U-net和Mask R-CNN模型表现出了可接受的良好性能，总体准确率分别达到了77.01%和89.02%。随后，开发了一个基于地理信息系统（GIS）的验证系统，以提高深度学习模型的性能。通过集成该验证系统，Mask R-CNN模型的总体准确率提高到了90.78%。本研究证明了将深度学习方法应用于近岸现场石油泄漏监测的可行性。此外，GIS的集成不仅有助于提供石油泄漏信息，还能改进深度学习模型。本研究探索的近岸现场石油泄漏监测的及时、准确和有效方法，可应用于大幅改进传统的现场石油泄漏监测，而在过去二十年里，传统现场石油泄漏监测受到的学术关注有限。
