RT-ProtoNet: radiative-transfer-guided few-shot prototype networks for cross-region bathymetry in optically clear reef environments

Satellite-derived bathymetry faces two coupled obstacles: labels are scarce, and models transfer poorly across regions. We propose RT-ProtoNet, a radiative-transfer-guided few-shot prototype network, which takes patches from three penetrating Sentinel-2 bands and treats ICESat-2 depths, aggregated to the 10 m grid, as sparse supervision; cross-region episodic meta-training then yields a transferable metric representation. Rather than embedding the radiative transfer relation as an analytic formula, we use it as a comparability criterion between support and query pixels, entering the attention as a learnable additive distance penalty. The prediction sums a convex combination over support depths and a base regression head trained on source domains only and frozen at deployment, so no target-domain parameters are estimated. We evaluate on five optically clear shallow reef regions by leave-one-region-out cross-validation against airborne laser bathymetry, against nine baselines, where K is the total number of support pixels (3, 5, 10, 20, 50). For K ≤ 20, RT-ProtoNet attains the lowest cross-region macro-mean RMSE (2.79–2.48 m), with a run-to-run standard deviation 0.67 times the runner-up’s; at K = 50, pre-training with head fine-tuning overtakes it. Ablation shows the residual head’s gain scales with support depth coverage (correlation 0.991) and that the two physical priors are largely substitutable; twelve perturbations to the attenuation input change RMSE by only 0.66%. The method suits depths of roughly 2–20 m and budgets of K ≤ 20, and does not extrapolate to turbid or optically complex waters. Independent evaluation at two external optical-domain sites, a moderately turbid embayment (Tampa Bay) and a clear-to-moderately-turbid transition site (Boquerón Bay), further delineates the method’s applicability across contrasting optical conditions, showing reliable transfer within the clear-water regime but substantial degradation under stronger optical attenuation.

Authors

Institutions

Publication Details

Journal
ISPRS Journal of Photogrammetry and Remote Sensing
Published
2026-10-15
DOI
https://doi.org/10.1016/j.isprsjprs.2026.10.012
Primary Topic
Underwater Acoustics Research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

RT-ProtoNet: radiative-transfer-guided few-shot prototype networks for cross-region bathymetry in optically clear reef environments

Naiquan Zheng, Dandi Wang, Shuai Xing, Ruiyao Kong et al.
ISPRS Journal of Photogrammetry and Remote Sensing
Underwater Acoustics Research
article

RT-ProtoNet: radiative-transfer-guided few-shot prototype networks for cross-region bathymetry in optically clear reef environments

Naiquan Zheng, Dandi Wang, Shuai Xing, Ruiyao Kong, Li Chen, Guoping Zhang, Ming Gao
article en

Abstract

Satellite-derived bathymetry faces two coupled obstacles: labels are scarce, and models transfer poorly across regions. We propose RT-ProtoNet, a radiative-transfer-guided few-shot prototype network, which takes patches from three penetrating Sentinel-2 bands and treats ICESat-2 depths, aggregated to the 10 m grid, as sparse supervision; cross-region episodic meta-training then yields a transferable metric representation. Rather than embedding the radiative transfer relation as an analytic formula, we use it as a comparability criterion between support and query pixels, entering the attention as a learnable additive distance penalty. The prediction sums a convex combination over support depths and a base regression head trained on source domains only and frozen at deployment, so no target-domain parameters are estimated. We evaluate on five optically clear shallow reef regions by leave-one-region-out cross-validation against airborne laser bathymetry, against nine baselines, where K is the total number of support pixels (3, 5, 10, 20, 50). For K ≤ 20, RT-ProtoNet attains the lowest cross-region macro-mean RMSE (2.79–2.48 m), with a run-to-run standard deviation 0.67 times the runner-up’s; at K = 50, pre-training with head fine-tuning overtakes it. Ablation shows the residual head’s gain scales with support depth coverage (correlation 0.991) and that the two physical priors are largely substitutable; twelve perturbations to the attenuation input change RMSE by only 0.66%. The method suits depths of roughly 2–20 m and budgets of K ≤ 20, and does not extrapolate to turbid or optically complex waters. Independent evaluation at two external optical-domain sites, a moderately turbid embayment (Tampa Bay) and a clear-to-moderately-turbid transition site (Boquerón Bay), further delineates the method’s applicability across contrasting optical conditions, showing reliable transfer within the clear-water regime but substantial degradation under stronger optical attenuation.

ISPRS Journal of Photogrammetry and Remote SensingVol. 243
PLA Information Engineering University (CN), Shandong University of Science and Technology (CN)
National Natural Science Foundation of China, Natural Science Foundation of Henan Province
Life below water
Openalex Percentile: Top 17%
Underwater Acoustics Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.