Jiang Mingming
—
Machine learning researcher working on photovoltaic power forecasting with 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 publication-count or output-tempo data is available in the current snapshot, so this axis is unscored. Once indexed, it would measure the volume and yearly cadence of scholarly output across venues.
Impact—
Citation counts, h-index, and downstream uptake are absent from the snapshot, so impact is unscored. The axis would measure the citations and scholarly influence generated by the two indexed papers.
Focus0/100
The radar scores focus at 0/100. The raw field distribution splits the two catalog papers evenly — 0.5 and 0.5 — between two near-identical labels for applied machine learning in renewable energy / photovoltaic forecasting. On visible evidence the portfolio sits in one tightly defined applied niche, so with only two papers the 0 score should be read as a small-sample artifact rather than evidence of scattered interests.
Collaboration32/100
Collaboration scores 32/100, based on 4 distinct coauthors in the snapshot — Xu Yuqing, Zhou Liguo, Sun Ze, and Yu Lei — who recur across the two catalog papers. Jiang Mingming sits in the last author position on both papers but is not the corresponding author on either, a pattern consistent with a senior contributor within a small, stable team rather than a broad external network.
Activity—
Recency and per-year publishing tempo are not yet computed for this researcher, so activity is unscored. The axis would track how continuously the researcher has published across recent years.
Reproducibility55/100
Reproducibility scores 55/100, the mean readiness rating across 2 scored papers (reproMean 55, reproPapers 2), each rated medium. Evolve's verdicts support that level: the expert-fusion paper reports its own 0.2pp significance bar and honestly reports missing it, while the ensemble-complexity paper runs component ablations, matched boosting baselines, and correction-aware comparisons on GEFCom2014 and OPSD, though oracle-weather assumptions temper generalisation.
Research summary
Jiang Mingming is an early-stage researcher in applied machine learning for renewable energy forecasting. The visible record consists of two 2026 arXiv papers on photovoltaic power forecasting, both held in the Evolve catalog with Jiang in the last author position and neither marked corresponding. The research program centers on forecast combination: whether ensembles of experts can beat strong gradient-boosting baselines under honest evaluation. In Horizon-specific Expert Fusion for Photovoltaic Power Forecasting, a hierarchical ensemble of 8 experts edged LightGBM by 4.11% on one station yet missed the paper's own 0.2 percentage-point significance bar — a result Evolve judged rigorous and honest, with small, site-specific gains. In Ensemble Complexity in Photovoltaic Forecasting, a transparent component-level audit showed fusion beating matched boosting only on OPSD after correction, weather gating adding nothing, and oracle-weather assumptions limiting broader claims. The consistent signature is methodological care — matched baselines, component ablations, explicit thresholds — with both papers rated medium reproducibility readiness, averaging 55 across the two scored papers. Collaboration is compact: 4 distinct coauthors (Xu Yuqing, Zhou Liguo, Sun Ze, Yu Lei) recur across both papers. Radar scores are reproducibility 55, collaboration 32, and focus 0; output, impact, and activity axes lack data.
Collaboration pattern
Collaboration is compact and stable: only 4 distinct coauthors (Xu Yuqing, Zhou Liguo, Sun Ze, Yu Lei) appear across the two catalog papers, and they recur together, suggesting one small working group. Jiang Mingming holds the last author position on both papers without being the corresponding author on either, consistent with a senior supervisory or advisory role inside that group. The radar's collaboration score of 32 reflects this small network; no institutional ties are visible in the data.
Research keywords
Highlights
Honest negative edge: 8-expert fusion vs LightGBM
Transparent audit of ensemble complexity
A reproducibility-first methodological style
Across both papers the signature is matched baselines, component ablations, and explicit significance thresholds; both are rated medium repro-readiness, giving a mean readiness score of 55 across the two scored papers.
Timeline
- 2026Published 'Horizon-specific Expert Fusion for Photovoltaic Power Forecasting' on arXiv, holding the last author position (non-corresponding).
- 2026Published 'Ensemble Complexity in Photovoltaic Forecasting' on arXiv, holding the last author position (non-corresponding).
- 2026Both papers entered the Evolve review catalog with medium reproducibility-readiness ratings; the four recurring coauthors were identified from this same period.
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 only; no ORCID, institution, or country record was available, so identity matching carries common-name risk.
- The bibliometric snapshot covers only the two 2026 arXiv papers in the Evolve catalog; no citation counts, h-index, or venue history are included.
- Output, impact, and activity radar axes are unscored because their underlying data is missing from the snapshot.
- The timeline covers only 2026; no earlier publication years exist in the provided data.