Yu Lei
—
Applied ML researcher in photovoltaic power forecasting, focused on ensemble and forecast-combination methods
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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—
No data: this snapshot provides no publication counts or output volume, so the output axis is unscored. It would measure total and annual research production, preprint and venue volume, and authorship positions across the career record.
Impact—
No data: citation counts and downstream uptake are absent from the input, so impact is unscored. This axis would measure citations to the reviewed papers and their uptake in the photovoltaic forecasting and forecast-combination literature.
Focus0/100
The radar focus score is 0, the lowest of the scored axes. The underlying field distribution splits 0.5/0.5 between two labels — 'applied machine learning for renewable energy forecasting' and 'applied machine learning / renewable energy forecasting' — which describe the same applied niche and differ mainly in punctuation. Both reviewed papers sit squarely in photovoltaic power forecasting with forecast combination, so the topic itself appears narrowly concentrated even as the computed score reads zero.
Collaboration32/100
The collaboration dimension scores 32 on the 0-100 radar. The raw record lists 4 distinct coauthors — Xu Yuqing, Zhou Liguo, Sun Ze, and Jiang Mingming — indicating a small, stable working group rather than a broad network. On both reviewed 2026 arXiv papers Yu Lei appears in a middle authorship position and is not the corresponding author, consistent with contributing within a team-led ensemble-modelling project rather than leading one.
Activity—
No data: only the 2026 paper year is available, with no multi-year publication history, so activity is unscored. It would measure publication cadence over time and sustained engagement with renewable energy forecasting.
Reproducibility55/100
Reproducibility scores 55, computed as a mean over 2 papers, both rated 'medium' reproducibility readiness. The Evolve verdicts support this middling reading: the ensemble-complexity audit is described as transparent about which components help (fusion on OPSD after correction) and which do not (weather gating), while the expert-fusion paper states and honestly misses its own 0.2pp improvement bar. Explicit reporting of negative results is a reproducibility plus, though the medium readiness rating keeps the score in the middle band.
Research summary
Yu Lei is an early-stage applied machine-learning researcher whose reviewed work concentrates on photovoltaic (PV) power forecasting within renewable energy forecasting. Both catalogued papers appeared on arXiv in 2026, with Yu Lei in a middle authorship position and not corresponding author on either. Horizon-specific Expert Fusion for Photovoltaic Power Forecasting builds a hierarchical ensemble of eight experts that edges LightGBM by 4.11% on one station yet misses the study's own 0.2pp improvement bar — a result Evolve reads as rigorous and honest, though small and site-specific. Ensemble Complexity in Photovoltaic Forecasting is a transparent component audit: forecast fusion beats a matched boosting baseline only on OPSD after correction, a weather gate adds nothing, and oracle-weather experiments limit broader claims. The radar scores collaboration 32 (4 distinct coauthors), reproducibility 55 (mean over 2 papers, both rated medium readiness), and focus 0, despite a field distribution split evenly between two near-identical labels for the same applied niche. Output, impact, and activity lack underlying data and remain unscored. The result is a focused but thin early-career profile: methodologically careful ensemble research in one applied domain, with scale and citation evidence not yet visible in the data.
Collaboration pattern
Yu Lei works within a compact four-person circle — Xu Yuqing, Zhou Liguo, Sun Ze, and Jiang Mingming — matching the 4 distinct coauthors behind the collaboration score of 32. Authorship on both 2026 arXiv papers is middle-position and non-corresponding, suggesting a contributing specialist role inside a small, stable ensemble-forecasting team rather than an independent or corresponding-lead pattern. No cross-institution or international collaborations are visible in the snapshot.
Research keywords
Highlights
Transparent audit of ensemble complexity in PV forecasting
Eight-expert fusion edges LightGBM, but only marginally
Timeline
- 2026arXiv preprint 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting': an eight-expert hierarchical ensemble edges LightGBM by 4.11% on one station but misses its own 0.2pp improvement bar.
- 2026arXiv preprint 'Ensemble Complexity in Photovoltaic Forecasting': a transparent component audit in which fusion wins only on OPSD after correction and weather gating adds no gain.
- 2026Both reviewed works appear in the same year within applied machine learning for renewable energy forecasting, forming a concentrated early record in PV forecast combination.
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 dimensions are computed from a small snapshot: only 2 reviewed papers and 4 distinct coauthors underpin the scored axes, so scores are volatile.
- Output, impact, and activity axes lack underlying data (no publication counts or citation metrics) and are intentionally left unscored.
- No institutional affiliation, country, or ORCID is available; the profile is name-resolved from public bibliographic data, and 'Yu Lei' is a common name, so identity matching carries uncertainty.
- Both reviewed papers are 2026 arXiv preprints with middle, non-corresponding authorship; peer-reviewed venue status and funding context are not captured.