What does this research mean for the field?

Different AI models exhibit distinct strengths in predicting estuarine bathymetry depending on geomorphological variability, with XGBoost performing best in stable areas, ConvLSTM excelling in capturing local spatial changes, and Transformer providing the most stable long-term predictions. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This study aims to compare the performance of AI models in predicting geomorphological changes based on historical data from the Nakdong River Estuary.

May 17, 2026Journal of the Korean Society of Surveying Geodesy Photogrammetry and Cartography

Suitability Analysis of AI Models for Bathymetry Prediction Considering Geomorphological Variability in the Nakdong River Estuary

View Full Paper

Ask AI

Bookmark

Authors

SKSung Bo Kim SLSang Hee LeeBiosolution (South Korea)

Discussion

Member takes

Implication

Randomized trial compares predictive performance of AI models in bathymetry analysis, indicating model suitability for estuarine management.

Key Points

This study aims to compare the performance of AI models in predicting geomorphological changes based on historical data from the Nakdong River Estuary.
Used bathymetric data from 2013 to 2022 to analyze AI model performance.
Compared XGBoost, ConvLSTM, and Transformer models under varying geomorphological conditions.
Evaluated model suitability for estuarine management based on accuracy measures.
In region B, all models achieved high reliability (KGE 0.936-0.940).
In region A, XGBoost showed superior quantitative performance (KGE=0.883), while ConvLSTM excelled in spatial representations of local changes.
The Transformer model demonstrated the most stable predictions for long-term geomorphological shifts.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/6a095c147880e6d24efe2095 https://doi.org/10.7848/ksgpc.2026.44.2.261

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial compares predictive performance of AI models in bathymetry analysis, indicating model suitability for estuarine management.

Suitability Analysis of AI Models for Bathymetry Prediction Considering Geomorphological Variability in the Nakdong River Estuary

Discussion

Member takes

Implication

Key Points

Cite This Study

Suitability Analysis of AI Models for Bathymetry Prediction Considering Geomorphological Variability in the Nakdong River Estuary

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider