ML researcher at CIRES working on sea-ice remote sensing, uncertainty-aware ice charting, and Arctic GeoAI navigation
3
papers here
3
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
7
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Output is not yet scored: the snapshot lacks the publication-count and venue-quality inputs this axis requires. It would measure total and per-year output volume with venue tier. The OpenAlex record shows 11 outputs in 2026, but no complete tally exists.
Impact—
Impact is not yet scored: citation counts, citation-by-year, and field-normalized influence inputs are unavailable in this snapshot. It would measure citation-based influence such as field-normalized citations. Only h-index 7 and i10-index 7 are present, which alone cannot support a score.
Focus0/100
Focus scores topical concentration on a 0–100 scale, and the computed value here is 0. The raw distribution explains why: fieldDist splits evenly at 0.333 across sea-ice monitoring, GeoAI route planning, and sea-ice/cryosphere machine learning, while five OpenAlex topic clusters range from Coastal and Marine Dynamics (6) to Cryospheric studies and observations (35). The record spans parallel problem areas rather than one narrow niche.
Collaboration28/100
Collaboration scores 28/100, the second-lowest present axis. The recent window records only 3 distinct coauthors, and the recurring partners are Samira Alkaee Taleghan, Farnoush Banaei-Kashani, and Andrew P. Barrett. All three reviewed 2026 papers carry middle-author, non-corresponding positions, consistent with a compact, stable working group pooling a small set of polar remote-sensing and GeoAI collaborators.
Activity96/100
Activity is the strongest axis at 96/100. The raw record shows 26 works in the last three years and a rising per-year curve: 4 outputs in 2023, 9 in 2024, 6 in 2025, and a snapshot-high 11 in 2026. Even with no recorded outputs in 2022, output has accelerated sharply since 2021, when 9 works were logged.
Reproducibility70/100
Reproducibility averages 70/100 across the 3 papers Evolve has reviewed (reproMean 70, reproPapers 3). Readiness ratings back the score: the Arctic eco-navigation agent is rated high, while the multi-label proportion learning and multi-ice-chart uncertainty papers are rated medium, pending significance tests and stronger non-SAR evidence. This is a mid-to-high standing grounded only in the reviewed sample.
Research summary
Younghyun Koo is a researcher at the Cooperative Institute for Research in Environmental Sciences (CIRES), US, whose OpenAlex record sits at the intersection of machine learning for polar remote sensing and GeoAI. The bibliometric snapshot shows an h-index of 7 and i10-index of 7, with 26 works in the last three years and an accelerating curve that reaches 11 outputs in 2026. Topic modeling concentrates on cryospheric studies and observations (35) and Arctic and Antarctic ice dynamics (32), with secondary clusters in oceanographic and atmospheric processes (12), model reduction and neural networks (9), and coastal and marine dynamics (6). Evolve has reviewed three 2026 arXiv papers: a multi-label proportion learning approach to sea-ice type prediction with evidential deep learning; an uncertainty-aware sea-ice type mapping study that quantifies label disagreement across four national ice charts; and an autonomous GeoAI agent for Arctic eco-navigation built on certified ε-Pareto multi-objective search. Verdicts are cautiously positive — promising reframing, honest uncertainty bounds, and sound agent design — but each notes limited evidence. Field distribution splits evenly at 0.333 across sea-ice monitoring ML, GeoAI route planning, and sea-ice/cryosphere ML. Collaboration is compact (28/100; 3 distinct coauthors), with Samira Alkaee Taleghan, Farnoush Banaei-Kashani, and Andrew P. Barrett as recurring partners. Reproducibility averages 70/100 across the reviewed sample.
Collaboration pattern
The collaboration footprint is compact: 3 distinct coauthors in the recent window and a collaboration score of 28/100. Work recurs with the same three partners — Samira Alkaee Taleghan, Farnoush Banaei-Kashani, and Andrew P. Barrett — spanning sea-ice machine learning and GeoAI routing projects. All three Evolve-reviewed 2026 papers carry middle, non-corresponding positions, consistent with contributing inside a small stable team rather than leading large consortia.
Research keywords
Highlights
Reframing sea-ice typing as multi-label proportion learning
Quantifying label uncertainty across four national ice charts
Certified ε-Pareto GeoAI agent for Arctic eco-navigation
Timeline
- 2017Earliest year in the OpenAlex record, with 1 logged output
- 2021Early peak: 9 outputs logged, the highest annual count before 2024
- 2023Output resumes at 4 works after a 2022 gap in the record
- 2024Activity ramps up with 9 logged outputs
- 20256 outputs logged in the record
- 2026Most active year at 11 outputs, including three Evolve-reviewed arXiv papers on sea-ice ML and Arctic GeoAI
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometrics come from an OpenAlex snapshot only; output and impact dimensions are unscored (dimMissing), and the h-index and i10-index of 7 reflect that snapshot alone.
- All three Evolve-reviewed papers are 2026 arXiv preprints with middle, non-corresponding authorship; peer-reviewed versions and final venues are not yet reflected.
- The per-year record has a 2022 gap and begins in 2017, so earlier-year coverage may be incomplete.
- Identity is name-resolved from public bibliographic data; 'Younghyun Koo' may match multiple researchers, and this profile is scoped to the ORCID-linked OpenAlex record.