arXiv · Machine Learning· Muhammad Saeed, Fatema Al Hajri, Mohamed H. Alhosani, Dmitry Mikhaylov, Yasser F. Al Wahedi·· 9 小时前AI 评分46
阿拉伯湾港口卫星衍生水深测量：无泄漏验证下经验、机器学习与深度学习模型对285,000个多波束测深点的基准测试，并展望UAE水域
Satellite-derived bathymetry of Arabian Gulf ports under leakage-free validation: a multi-site benchmark of empirical, machine-learning and deep-learning models against 285,000 multibeam soundings, with an outlook for UAE waters
AI 导读
研究用阿布扎比海岸六个港区的285,619个多波束测深点，评估Sentinel-2卫星衍生水深测量的跨地点表现。验证方式比模型更影响结果：LightGBM在随机切分、空间分块和未见地点的RMSE分别为0.57 m、1.30 m和1.66 m；迁移测试中Stumpf ratio为1.45 m，未被LightGBM、U-Net或Lyzenga超越。
来源：arXiv · Machine Learning · arxiv.org