AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

RiverScope: High-Resolution River Masking Dataset

Rangel Daroya, Taylor Rowley, Jonathan Acero Flores, Elisa Friedmann, Fiona B Bennitt, Heejin An, Travis Thomas Simmons, Marissa Hughes, Camryn L Kluetmeier, Solomon Kica, J. Daniel Vélez, Sarah E. Esenther and 5 more

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on 3 m PlanetScope RiverScope labels instead of 10 m Sentinel labelsSatlas Swin-B FPN vs ImageNet RN50 FPN · River width estimationmedian absolute error (m): 39.0 -> 7.2Improved
train with RiverScope data instead of Sentinel/WorldCoversegmentation models · water segmentation (PlanetScope test)F1Improved
linear 4-to-3 channel adaptor instead of dropping NIR or random 4-channel training (ablation)RGB-pretrained segmentation models · water segmentationF1Improved
use pretrained backbones instead of PlanetScope CNN / NDWIsegmentation models · water segmentationF1Improved
RiverScope model vs prior CNN width estimatorRiverScope RN50 FPN · River width estimationmedian absolute error (m): 30.0 -> 7.2Improved
Sentinel vs Landsat/SWORD widthsSentinel · River width estimationmean absolute error (m): 77.0 -> 152.8Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy