First-author work on uncertainty-aware sea-ice mapping and GeoAI Arctic routing at University of Colorado Denver
3
papers here
3
reviewed by Evolve
3
first-author
0
corresponding
—
works · OpenAlex
2
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—
Not yet scored: this axis would aggregate publication volume and authorship role. The raw record shows 14 works in the last three years (h-index 2, i10-index 0), but a composite output score has not been computed.
Impact—
Not yet scored: this axis would track citations, citations-per-year, and uptake beyond the immediate subfield. Current signals are thin — h-index 2 and i10-index 0 — so no impact estimate is made here.
Focus0/100
The radar reports a focus score of 0/100, reflecting a topic spread rather than a single-thread profile: OpenAlex topics list Arctic and Antarctic ice dynamics (8), remote-sensing image classification (7), advanced neural network applications (6), fire effects on ecosystems (3), and satellite communication systems (3). Her three reviewed 2026 first-author papers nonetheless converge tightly on sea-ice machine learning and Arctic GeoAI, suggesting focus may strengthen as the record matures.
Collaboration28/100
Collaboration scores 28/100, the lowest present axis: OpenAlex records only 3 distinct co-authors, with Younghyun Koo, Farnoush Banaei-Kashani, and Andrew P. Barrett recurring across works. All three reviewed 2026 papers are first-authored without a corresponding-author flag, consistent with a small, stable team rather than a large distributed network; a small-team pattern can limit co-authorship breadth metrics while still reflecting intensive, repeated collaboration.
Activity79/100
Activity scores 79/100 on the strength of recent output: OpenAlex counts 14 works in the last three years, rising from 1 in 2024 to 8 in 2025 and 5 in 2026 to date. The three 2026 arXiv preprints, each first-authored, indicate a fast-moving cadence in sea-ice machine learning and GeoAI, though 2026 figures may still be incomplete.
Reproducibility70/100
Reproducibility scores 70/100, computed by Evolve across 3 reviewed papers (mean 70). Readiness varies: the autonomous GeoAI agent for Arctic eco-navigation is rated high, while the multi-label proportion learning and multi-ice-chart uncertainty papers are each rated medium, with Evolve noting thin SAR-only gains and untested significance in one case.
Research summary
Samira Alkaee Taleghan is an early-career researcher at the University of Colorado Denver (United States), profiled here from OpenAlex bibliographic records and Evolve's reviews of three 2026 arXiv preprints, on all of which she is first author. Her work sits at the intersection of machine learning and polar remote sensing: she reframes sea-ice type prediction as polygon-level multi-label proportion learning, quantifies stage-of-development label uncertainty across four national ice charts using Sentinel-1 SAR, and builds an autonomous GeoAI multi-agent system for multi-objective Arctic eco-navigation with certified ε-Pareto search. OpenAlex attributes 14 works in the last three years — 1 in 2024, 8 in 2025, and 5 in 2026 — with an h-index of 2 and i10-index of 0, consistent with a record whose citations have not yet had time to accumulate. Topic profiling concentrates on Arctic and Antarctic ice dynamics (8), remote-sensing image classification (7), and advanced neural network applications (6), with smaller clusters in fire effects on ecosystems (3) and satellite communication systems (3). Evolve rates reproducibility readiness across the three reviewed papers at a mean of 70/100, highest for the Arctic navigation agent; frequent co-authors are Younghyun Koo, Farnoush Banaei-Kashani, and Andrew P. Barrett.
Collaboration pattern
Collaboration is concentrated in a small, stable team: OpenAlex lists only 3 distinct co-authors, with Younghyun Koo, Farnoush Banaei-Kashani, and Andrew P. Barrett as recurring collaborators. All three reviewed 2026 papers are first-authored without a corresponding-author flag, consistent with close work within one group at University of Colorado Denver rather than a broad external network. The collaboration radar score of 28/100 reflects this narrow breadth; deepening ties beyond the current circle would likely lift it.
Research keywords
Highlights
Multi-label proportion learning for sea-ice type prediction
Uncertainty-aware sea-ice type mapping with multiple ice charts
An autonomous GeoAI agent for Arctic eco-navigation
Timeline
- 2024First work appears in the OpenAlex record, with 1 publication indexed in 2024.
- 2025Output accelerates to 8 indexed works, the highest annual count in the record so far.
- 20265 works indexed so far; three first-author arXiv preprints appear — multi-label proportion learning for sea-ice typing, uncertainty-aware sea-ice mapping with multiple ice charts, and an autonomous GeoAI agent for Arctic eco-navigation.
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.
- Bibliometric counts (h-index, i10-index, per-year works, topics, co-authors) come from OpenAlex and cover only its indexed record.
- Output and impact radar axes are unscored due to insufficient data, so citation-based standing cannot yet be assessed.
- All three reviewed papers are 2026 arXiv preprints; peer-review status and final published versions are not reflected.
- The profile is name-resolved from public bibliographic data (OpenAlex identity, ORCID 0009-0009-2928-8144); no biographical information beyond these sources was used.