Sun Ze
—
Sun Ze — applied ML researcher in photovoltaic power forecasting, focused on forecast combination and ensembles
2
papers here
2
reviewed by Evolve
1
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—
Insufficient data: output is not scored because publication counts could not be computed from the current snapshot. This axis would measure total and per-year publication volume across venues.
Impact—
No citation data is available, so impact is not scored. This axis would measure citations, citing works, and downstream influence of the two 2026 arXiv papers once citation indexes cover them.
Focus0/100
The radar assigns focus a score of 0, computed from a field distribution that splits evenly — 0.5 and 0.5 — between two near-identical labels, 'applied machine learning for renewable energy forecasting' and 'applied machine learning / renewable energy forecasting'. In substance, both reviewed 2026 papers sit in a single niche, photovoltaic power forecasting via ensemble methods, so the visible record is topically narrow; the score rests on only two cataloged papers.
Collaboration32/100
Collaboration scores 32 out of 100, based on 4 distinct coauthors — Xu Yuqing, Zhou Liguo, Yu Lei, and Jiang Mingming — a small, stable circle consistent with a compact research team. Sun Ze is first author on 'Ensemble Complexity in Photovoltaic Forecasting' but a middle author, and not corresponding author, on 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting', suggesting alternating leading and supporting roles within the same group.
Activity—
Activity cannot be scored yet: the snapshot lacks the temporal publication record needed to compute recent output cadence. This axis would measure publishing frequency and continuity in recent years.
Reproducibility55/100
Reproducibility scores 55, the mean over the two papers with reproducibility assessments (reproPapers: 2), each rated 'medium'. The record supports this: both papers evaluate on public benchmarks — GEFCom2014 and OPSD in the ensemble audit, per-station LightGBM comparisons in the expert-fusion study — and include component ablations and explicit improvement bars the authors themselves miss, a transparent, honest evaluation style that aids replication.
Research summary
Sun Ze is an early-stage researcher in applied machine learning for renewable energy forecasting, whose reviewed work centers on photovoltaic (PV) power forecasting and, specifically, on forecast combination and ensemble methods. The Evolve catalog holds two 2026 arXiv papers. The first, 'Ensemble Complexity in Photovoltaic Forecasting', with Sun Ze as first author, is a transparent audit of ensemble complexity: after correction, forecast fusion beats a matched boosting baseline only on the OPSD dataset, a weather-gating component adds nothing, and an oracle-weather experiment bounds how far the conclusions generalize. The second, 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting', lists Sun Ze in a middle author position; a hierarchical ensemble of 8 experts beats LightGBM by 4.11% on one station while missing the paper's own 0.2 percentage-point improvement bar — gains the Evolve verdict calls rigorous and honest, but small and site-specific. Radar signals point the same way: a narrowly concentrated field profile (both papers in applied machine learning for renewable energy forecasting), a small collaboration network of 4 distinct coauthors, and a medium reproducibility mean of 55 across two papers. No institution, country, ORCID, citation, or venue data were available; 'Sun Ze' is a common name, so this profile is name-resolved from public bibliographic data and should be read as an early-stage, evidence-limited record.
Collaboration pattern
Sun Ze works within a small, stable circle: 4 distinct coauthors, with Xu Yuqing, Zhou Liguo, Yu Lei, and Jiang Mingming recurring. The collaboration score of 32 reflects this limited network size. Authorship roles alternate — first author on 'Ensemble Complexity in Photovoltaic Forecasting', middle position and not corresponding on 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting' — a pattern typical of a compact team sharing leading and supporting duties rather than a broad multi-group network.
Research keywords
Highlights
Transparent audit of ensemble complexity in PV forecasting
Horizon-specific expert fusion edges LightGBM at one station
Medium reproducibility on public benchmarks
Both reviewed papers rate 'medium' for reproducibility readiness (mean 55 over 2 papers), anchored in public benchmarks — GEFCom2014 and OPSD — plus component ablations and stated improvement thresholds.
Timeline
- 2026Publishes first-author arXiv paper 'Ensemble Complexity in Photovoltaic Forecasting', a transparent audit of ensemble complexity in PV forecasting.
- 2026Co-authors 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting' in a middle author position; the 8-expert ensemble beats LightGBM by 4.11% on one station.
- 2026Both 2026 papers receive 'medium' reproducibility ratings, averaging 55 across the two assessed papers.
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.
- 'Sun Ze' is a common name; this profile is name-resolved from public bibliographic data, and no ORCID, institution, or country was available to confirm identity.
- Bibliometric evidence is thin: it rests on a small snapshot plus the two arXiv papers Evolve has reviewed, so scores may shift as coverage grows.
- Output, impact, and activity are unscored — no publication counts, citation numbers, h-index, or venue metadata were available; all quoted figures come from the Evolve snapshot verbatim.
- Both papers are 2026 arXiv preprints; their peer-reviewed publication status is unknown.