基于拉格朗日积分与HDP-CatBoost区域融合的MERMAID浮标上浮位置预测方法

doi:10.11978/2026102

热带海洋学报

基于拉格朗日积分与HDP-CatBoost区域融合的MERMAID浮标上浮位置预测方法

张嘉烁^1,2, 王维栋³, 卜宪海¹, 朱心科², 宋一卓², 张天骏^2,4

1. 山东科技大学测绘与空间信息学院, 山东青岛 266590;
2. 自然资源部第二海洋研究所, 浙江杭州 310012;

3. 浙江省海洋科学院, 浙江杭州 310012;

4. 中国地质大学(武汉)海洋学院, 湖北武汉 430074

收稿日期:2026-07-01 修回日期:2026-08-27 接受日期:2026-09-04
通讯作者: 王维栋
基金资助:
中央级公益性科研院所基本科研业务费专项资金项目(SZ2562)

MERMAID float surfacing position prediction based on Lagrangian integration and regional HDP–CatBoost fusion

ZHANG Jiashuo^1,2, WANG Weidong³, BU Xianhai¹, ZHU Xinke², SONG Yizhuo², ZHANG Tianjun^2,4

1. College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China;
2. Second Institute of Oceanography, Hangzhou 310012, China;

3. Marine Academy of Zhejiang Province, Hangzhou 310012, China;

4. College of Marine Science and Technology, China University of Geosciences (Wuhan), Wuhan 430074, China

Received:2026-07-01 Revised:2026-08-27 Accepted:2026-09-04
Supported by:
Special Fund for Basic Scientific Research of Central Public Research Institutes (SZ2562)

摘要/Abstract

摘要： 沉浮式海洋地震仪（mobile earthquake recording in marine areas by independent divers，MERMAID）在水下监听与漂移期间无法获得全球定位系统（global positioning system，GPS）信息，当前剖面周期的上浮点只能在浮标到达海面后确认。针对这一问题，本文利用MERMAID历史剖面记录、事件记录和多深度流场数据，构建历史漂移持续性基线、HYCOM分层拉格朗日积分和CatBoost 全特征位移回归模型。与单一历史外推或单一开环积分不同，本文将前序剖面端点约束、分层海流积分特征和数据驱动位移回归相结合，并通过验证集确定海区自适应融合权重。将1063条建模样本按海区内部时间顺序划分，其中214条剖面记录组成独立测试集。结果表明，区域权重融合方法的平均绝对误差和均方根误差分别为7.800km和11.906km，较历史漂移和CatBoost全特征位移回归模型的平均绝对误差分别降低14.7%和6.3%，20km范围内的预测命中率达到90.19%。该方法可在不改变浮标被动漂移过程的前提下，为上浮前位置预估、岸基通信调度、异常漂移识别和水下观测资料的位置约束提供辅助信息，并可为其他缺少连续水下定位的剖面式或低动力海洋观测平台的位置预报提供参考。

关键词: MERMAID浮标, 上浮点预测, 拉格朗日积分, CatBoost

Abstract: Mobile Earthquake Recording in Marine Areas by Independent Divers (MERMAID) floats cannot obtain Global Positioning System (GPS) fixes during underwater listening and drift phases, so the surfacing position of the current profiling cycle can only be confirmed after the float reaches the sea surface. To address this problem, this study uses historical MERMAID profile records, event records, and multi-depth ocean current data to construct a historical-drift persistence baseline, a HYCOM-driven profile-layered Lagrangian integration module, and a CatBoost full-feature displacement regression model. Unlike single historical extrapolation or open-loop physical integration, the proposed method combines endpoint constraints from previous profiles, layered ocean-current integration features, and data-driven displacement regression, with region-adaptive fusion weights determined from the validation set. A total of 1,063 modelling samples were divided chronologically within each sea region, including 214 profile records used as an independent test set. The results show that the region-weighted fusion model achieved a mean absolute error of 7.800km and a root mean square error of 11.906km. Compared with the historical-drift persistence baseline and the CatBoost full-feature displacement regression model, the mean absolute error was reduced by 14.7% and 6.3%, respectively, and the hit rate within 20km reached 90.19%. Without changing the passive drifting process of the float, this method provides auxiliary information for pre-surfacing position estimation, shore-based communication scheduling, abnormal drift detection,and positional constraints on underwater observations. It may also inform position prediction for other profiling or low-power ocean-observation platforms that lack continuous underwater positioning.

Key words: MERMAID float, surfacing-position prediction, Lagrangian integration, CatBoost

张嘉烁, 王维栋, 卜宪海, 朱心科, 宋一卓, 张天骏. 基于拉格朗日积分与HDP-CatBoost区域融合的MERMAID浮标上浮位置预测方法[J]. 热带海洋学报, 0, (): 1-.

ZHANG Jiashuo1, 2, WANG Weidong3, BU Xianhai1, ZHU Xinke2, SONG Yizhuo2, ZHANG Tianjun2, 4.

MERMAID float surfacing position prediction based on Lagrangian integration and regional HDP–CatBoost fusion [J]. Journal of Tropical Oceanography, 0, (): 1-.