Adaptive Correction of Physics-based Drift Model: Improving Drowning Person Drift Prediction Using Buoy Observations

Q: What does this research mean for the field?

A 3-stage adaptive correction framework combining machine learning, incremental learning, and dynamic coefficient correction significantly improves the prediction accuracy of a drowning person's drift path using only buoy observations. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Taehun Kim; Ji-Chang Kim; Do‐Youn Kim; Seung‐Hyun Moon; Yong-Hyuk Kim

doi:10.5391/jkiis.2026.36.4.313

August 31, 2026Journal of Korean institute of intelligent systems

Adaptive Correction of Physics-based Drift Model: Improving Drowning Person Drift Prediction Using Buoy Observations

View at Publisher

Ask AI

Bookmark

Share

Key Points

To develop and evaluate a three-stage adaptive framework that uses ocean buoy observations to accurately predict drowning person drift trajectories despite differences in physical drift characteristics.
Constructed a three-stage framework combining a pre-trained LightGBM model to adjust physics-based Leeway model errors, real-time incremental learning from buoy tracks, and a coefficient correction module for object discrepancies.
Conducted and evaluated two maritime field experiments in the East Sea and Yellow Sea.
Normalized Cumulative Lagrangian Separation improved from 0.245 to 0.894 using the adaptive correction framework.
Final separation distance between predicted and actual trajectories decreased from 4.563 km to 0.320 km.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Experimental study demonstrates enhanced drift trajectory prediction for drowning victims using buoy-adapted physics models, highlighting improved maritime search and rescue precision.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/6a9935b1636c6408cfa7e214 https://doi.org/10.5391/jkiis.2026.36.4.313

View at Publisher

Ask AI

Bookmark

Share

Adaptive Correction of Physics-based Drift Model: Improving Drowning Person Drift Prediction Using Buoy Observations

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Adaptive Correction of Physics-based Drift Model: Improving Drowning Person Drift Prediction Using Buoy Observations

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading