Zhou Liguo
—
Zhou Liguo: applied ML for PV power forecasting via 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 output data is available yet: the snapshot provides no publication counts, venue history, or totals behind this name. This axis would measure the volume, venue quality, and year-over-year consistency of the researcher's published work.
Impact—
Impact cannot be scored: no citation counts, h-index, or downstream adoption signals are present in the data. This axis would measure how frequently and how widely the two forecasting studies are cited and built upon by later work.
Focus0/100
The radar focus score is 0, which looks paradoxical: the raw field distribution places both catalog papers in one applied-ML-for-renewable-energy-forecasting area, split 0.5/0.5 across two near-identical label variants. Taken at face value the portfolio is effectively single-topic, so the zero most plausibly reflects fragmented field labeling rather than genuinely scattered research; it should be re-read once cleaner field tags exist.
Collaboration32/100
Collaboration scores 32, computed from 4 distinct co-authors across the cataloged work: Xu Yuqing, Sun Ze, Yu Lei, and Jiang Mingming. In both 2026 papers Zhou sits in a middle author position and is not the corresponding author, a pattern consistent with a contributing specialist inside a small, stable team rather than an independent group lead. No larger or cross-border network is visible in the available data.
Activity—
Activity data is insufficient: no per-year publication stream or author-disambiguated record is available to trace recent cadence beyond the two 2026 preprints. This axis would measure publishing rhythm, continuity, and current research engagement over time.
Reproducibility55/100
Reproducibility scores 55 (reproMean 55 over 2 assessed papers), with both entries rated medium repro readiness. Evolve's reviews credit the work with transparent component ablations and self-imposed significance thresholds — the fusion paper openly reports missing its own 0.2pp bar — but site-specific gains, post-correction OPSD results, and oracle-weather assumptions keep claims from being straightforwardly re-runnable elsewhere.
Research summary
Zhou Liguo is a name-resolved, early-stage researcher profile built from public bibliographic data, centered on applied machine learning for renewable energy forecasting — specifically photovoltaic (PV) power forecasting via ensemble learning and forecast combination. The Evolve catalog holds two 2026 arXiv preprints. 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting' assembles a hierarchical ensemble of 8 experts that edges LightGBM by 4.11% on one station while missing the authors' own 0.2pp significance bar; Evolve judges it rigorous and honest, with small, site-specific gains. 'Ensemble Complexity in Photovoltaic Forecasting' audits when fusion helps: it beats a matched boosting baseline only on OPSD after correction, a weather gate adds nothing, and oracle-weather assumptions limit broader claims. Both papers carry medium reproducibility readiness; the reproducibility dimension scores 55 (mean over 2 assessed papers). Zhou appears in a middle author position in both, without corresponding status, and the collaboration dimension scores 32 across 4 distinct co-authors (Xu Yuqing, Sun Ze, Yu Lei, Jiang Mingming). The focus score reads 0, yet the raw field distribution places both papers in one applied-ML/renewable-energy area (two near-identical labels at 0.5 each), so the zero likely reflects label fragmentation rather than scattered work. Output, impact, and activity lack data and remain unscored.
Collaboration pattern
Zhou Liguo works within a compact author team: exactly 4 distinct co-authors appear across the catalog — Xu Yuqing, Sun Ze, Yu Lei, and Jiang Mingming — yielding a collaboration score of 32. Both 2026 papers place Zhou in a middle author position without corresponding-author status, suggesting a specialist contributor inside a small, stable group rather than an independent or corresponding lead. The data shows no evidence of larger networks or international collaboration.
Research keywords
Highlights
Eight-expert fusion edges LightGBM by 4.11% — but misses its own bar
Audit: ensemble complexity pays only after correction, on one dataset
Timeline
- 2026A 2026 arXiv preprint on horizon-specific expert fusion for PV power forecasting enters the catalog, introducing an 8-expert hierarchical ensemble benchmarked against LightGBM.
- 2026A second 2026 preprint, 'Ensemble Complexity in Photovoltaic Forecasting', audits when ensemble complexity helps: fusion wins only on OPSD after correction, and weather gating adds nothing.
- 2026The catalog closes the year at two medium-reproducibility PV forecasting papers with 4 distinct co-authors; the reproducibility dimension scores 55 and collaboration 32.
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.
- Profile is name-resolved from public bibliographic data; no ORCID, institution, or country is linked, so identity with other researchers named Zhou Liguo is not confirmed.
- Radar scores come from the bibliometric snapshot only; output, impact, and activity axes lack underlying data and are left unscored.
- Reproducibility (mean 55) rests on just 2 assessed 2026 arXiv preprints — a small sample, and neither is peer reviewed.
- The focus score of 0 conflicts with a field distribution concentrated on one topic (two near-identical label variants at 0.5 each) and may reflect label fragmentation.