# From Local Training to Large-Scale Mapping: A Comparative Assessment of Machine Learning and Deep Learning for Transferable Satellite-Derived Bathymetry

arXiv: https://arxiv.org/abs/2606.02764 · HTML: https://mlsanity.com/paper/2606.02764/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 55 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Dead Pixel Test Using Effective Receptive Field](https://mlsanity.com/paper/2108.13576/) (2021)
- [Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance](https://mlsanity.com/paper/2211.14487/) (2022)
- [Deep Learning-based Bathymetry Retrieval without In-situ Depths using Remote Sensing Imagery and SfM-MVS DSMs with Data Gaps](https://mlsanity.com/paper/2504.11416/) (2025)
- [From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2](https://mlsanity.com/paper/2601.12636/) (2026)

## Abstract (arXiv)

Satellite-derived bathymetry (SDB) from multispectral imagery is cost-effective but scales poorly across regions, especially in optically complex coastal environments. We evaluate machine learning and deep learning for transferable SDB over the 0-20 m depth range using Sentinel-2 imagery. A Random Forest baseline and four CNNs (ResNet-50, ResNet-101, EfficientNet-B4, ConvNeXt-Large) are trained on Pratas Island and selected Great Barrier Reef regions, then evaluated on spatially independent intra- and cross-regional test areas. Preserving spatial continuity during training, by keeping contiguous reef blocks rather than random patches, is the single most impactful design choice; we further introduce a Smooth Weight Function (SWF)-weighted RMSE loss that emphasizes near-surface depths. With these choices, intra-regional RMSE ranges from 1.15 to 1.92 m over 0-20 m and is as low as 0.26 m for depths <= 3 m. Random Forest degrades sharply under cross-regional transfer (RMSE 1.53 m -> 2.99-3.78 m), while the deep models stay more robust (2.46-2.98 m). On the public MagicBathyNet aerial-RGB benchmark (0-16 m) the proposed networks reach 0.19-0.22 m RMSE, outperforming a U-Net baseline and a task-specific transformer architecture with substantially fewer parameters. We further exploit multi-temporal repeat imagery: training on it broadens diversity, and median-aggregating predictions across passes at inference reduces noise from changing sun angles, atmospheric conditions, water properties, and tides. We release optimized architectures and pretrained weights to enable scalable transfer to new sites.