Time series forecasting researcher at East China Normal University — wind power benchmarks and model adaptation
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-13) 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 scored yet: publication-volume data such as total paper counts, venues, and yearly output is absent from this snapshot. This axis would measure productivity and the breadth of the publication record beyond the two reviewed preprints.
Impact—
Not scored yet: citation counts, citation velocity, and downstream influence metrics are unavailable in this snapshot. This axis would measure how far the WPBench benchmark and the MUSE adapters are adopted by other forecasting studies and practitioner pipelines.
Focus0/100
The radar records a focus score of 0, while the raw field distribution splits evenly at 0.5 each between machine learning (time series forecasting) and machine learning — time series forecasting (renewable energy). Both labels sit within time series forecasting: WPBench targets wind power and MUSE targets multivariate forecasting. The data does not explain the 0 score, but the two-label split reads as substantively coherent specialization, so this axis should be interpreted cautiously.
Collaboration53/100
The collaboration score is 53, built on 13 distinct coauthors across the reviewed work. Frequent collaborators include Xinying Cai, Jilin Hu, Junkai Lu, Xiaoyun Yu, Xiangfei Qiu, Linsen Li, Yingshan Li, Li Ma, Kai Zhang, Yao Fu, and Weihao Jiang. Zhu led WPBench as first author but was a middle author on MUSE, and holds corresponding-author status on neither paper, suggesting team-embedded work with one first-author leadership instance so far.
Activity—
Not scored yet: this snapshot contains no publication cadence data — annual output counts or multi-year timestamps — beyond the two 2026 arXiv entries. This axis would measure research tempo and sustained engagement over time once a longer publication history is indexed.
Reproducibility78/100
The reproducibility score is 78, a mean taken over 2 scored papers. The two entries differ: MUSE rates high readiness, while first-authored WPBench rates medium because Evolve found no significance tests and no visible code. Both papers are also flagged for missing statistical significance testing, so the above-average score rests on methodological reporting rather than full artifact verification.
Research summary
Yuhan Zhu is a machine learning researcher at East China Normal University whose work centers on time series forecasting, spanning general multivariate forecasting and renewable-energy applications such as wind power. The Evolve catalog holds two 2026 arXiv papers. The first, WPBench, is a first-authored benchmark that unifies 26 wind datasets and 19 models from 5 model families and adds shape and structure diagnostics; Evolve judges it well-scoped but notes the absence of significance tests and visible code, with medium reproducibility readiness. The second, MUSE, adapts a frozen masked-autoencoder vision backbone to multivariate forecasting through VCR and TPR adapters, reporting state-of-the-art results on 10 datasets with high reproducibility readiness, though Evolve observes that gains are often thin and lack significance testing. Bibliometric radar data records 13 distinct coauthors, a collaboration score of 53, and a reproducibility score of 78 averaged over 2 scored papers. The field distribution splits evenly between machine learning (time series forecasting) and its renewable-energy branch, indicating coherent specialization even though the focus score is recorded as 0. Output, impact, and activity dimensions lack sufficient data and are deliberately left unscored. With only two reviewed preprints in scope, this is an early-stage profile built on a narrow evidence base.
Collaboration pattern
Radar counts 13 distinct coauthors with a collaboration score of 53. Recurring collaborators include Xinying Cai, Jilin Hu, Junkai Lu, Xiaoyun Yu, Xiangfei Qiu, Linsen Li, Yingshan Li, Li Ma, Kai Zhang, Yao Fu, and Weihao Jiang. The pattern is team-embedded: first-author leadership on WPBench, a middle-author role on MUSE, and no corresponding-authorship in the reviewed sample, consistent with one active collaboration cluster.
Research keywords
Highlights
WPBench: unifying 26 wind datasets and 19 models
MUSE: adapting a frozen vision backbone to forecasting
Shape-aware evaluation via DTW diagnostics
Timeline
- 2026First-authored WPBench benchmark for wind power forecasting released on arXiv
- 2026Co-authored MUSE paper released, adapting a frozen vision backbone to multivariate forecasting
- 2026Both papers enter the Evolve catalog with reproducibility ratings of medium and high
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 scores come from the Evolve radar built on OpenAlex-derived data; output, impact, and activity axes lack underlying data and are unscored.
- Evidence covers only 2 reviewed papers, both 2026 arXiv preprints; no peer-reviewed venue record, career history, or award data is in scope.
- Yuhan Zhu is a common name; this profile is name-resolved from public bibliographic data under ORCID 0000-0002-7817-820X.
- Country-level affiliation is not recorded in the input data; institutional attribution relies on the listed East China Normal University affiliation only.