Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches
Semi-Automated Semantic Segmentation of Arctic Shorelines Using Very High-Resolution Airborne Imagery, Spectral Indices and Weakly Supervised Machine Learning Approaches
复制标题
DOI：
10.3390/rs13224572
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
B. Aryal;S. Escarzaga;S. V. Zesati;M. Velez-Reyes;O. Fuentes;C. Tweedie
中科院分区：
文献类型：
--
作者：
B. Aryal;S. Escarzaga;S. V. Zesati;M. Velez-Reyes;O. Fuentes;C. Tweedie
精确的海岸岸线测绘对于监测侵蚀速率、地表水文以及生态系统结构和功能的变化至关重要。监测北极国家野生动物保护区（ANWR）的水体非常重要，特别是考虑到该地区石油和天然气勘探的潜力。在这项工作中，我们提出了一种基于深度神经网络的U-Net架构的改进变体，用于使用稀疏标记的训练数据对4波段正校正NOAA航空图像进行自动制图，并将其与传统的基于机器学习（ML）的方法（即随机森林、xgboost和光谱水指数——归一化差分水指数（NDWI）和归一化差分地表水指数（NDSWI））的性能进行比较，以支持北极海岸线的海岸线制图。我们得出的结论是，可以修改U-Net模型以接受稀疏标签作为输入，结果与其他ML方法相当（使用U-Net的交集-over- union （IoU）为94.86%，而使用性能最好的方法的IoU为95.05%）。
Precise coastal shoreline mapping is essential for monitoring changes in erosion rates, surface hydrology, and ecosystem structure and function. Monitoring water bodies in the Arctic National Wildlife Refuge (ANWR) is of high importance, especially considering the potential for oil and natural gas exploration in the region. In this work, we propose a modified variant of the Deep Neural Network based U-Net Architecture for the automated mapping of 4 Band Orthorectified NOAA Airborne Imagery using sparsely labeled training data and compare it to the performance of traditional Machine Learning (ML) based approaches—namely, random forest, xgboost—and spectral water indices—Normalized Difference Water Index (NDWI), and Normalized Difference Surface Water Index (NDSWI)—to support shoreline mapping of Arctic coastlines. We conclude that it is possible to modify the U-Net model to accept sparse labels as input and the results are comparable to other ML methods (an Intersection-over-Union (IoU) of 94.86% using U-Net vs. an IoU of 95.05% using the best performing method).