EPRI researcher at the crossroads of renewable forecast scenarios and GraphRAG-based power-grid QA
2
papers here
1
reviewed by Evolve
2
first-author
1
corresponding
—
works · OpenAlex
3
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) 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 yet scored: this snapshot lacks sufficient output metrics. The axis would measure cumulative publication volume and trajectory; the record shows 14 works over the last three years, but a computed output score is not available.
Impact—
Not yet scored: citation-based evidence is too thin (h-index 3, i10-index 0). This axis would measure citation influence and uptake of the work across fields; no impact score is available yet.
Focus100/100
Scores 100: the indexed field distribution contains a single field, power systems / renewable energy forecasting (proportion 1.0). Both Evolve-reviewed 2026 papers fall inside power-systems AI, one on renewable forecast scenarios for economic dispatch and one on GraphRAG question answering over CIM/CGMES grid models, indicating a deliberately narrow, applications-anchored agenda.
Collaboration14/100
Scores 14, reflecting a very small collaboration footprint: the record lists exactly 1 distinct coauthor, Yamini Sehgal, who recurs as the frequent collaborator. Both reviewed papers are first-authored within this two-person pattern (one additionally as corresponding author), suggesting self-driven, small-team work rather than large consortium projects.
Activity79/100
Scores 79, driven by an accelerating cadence: countsByYear shows 3 works in 2024, 1 in 2025, and 10 in 2026, with 14 works in the last three years. The 2026 surge coincides with both first-author arXiv preprints entering the Evolve catalog.
Reproducibility55/100
Averages 55 across one assessed paper (reproPapers: 1), and both reviewed papers carry medium repro-readiness. Evolve specifically credits the dispatch ablation study as rigorous, controlled and transparent, while noting the GraphRAG paper's evidence is templated and confined to a single topology family — consistent with its moderate placement.
Research summary
Jayakumar Manoharan is a researcher at the Electric Power Research Institute (US) working where renewable energy forecasting meets applied AI for power systems. The Evolve catalog holds two 2026 first-author arXiv papers. The first, also corresponding-authored, is a controlled ablation study quantifying the operational value of spatial dependence in renewable forecast scenarios for single-period economic dispatch: in a newsvendor-style stochastic dispatch, spatial coherence changes cost by less than 0.64%, and Evolve judges the ablation rigorous and transparent though narrow in scope. The second proposes seed-anchored, budget-bounded graph rendering for question answering over industry-standard CIM/CGMES grid models, fixing context-budget truncation and matching LLM-extracted graphs at zero rendering tokens, with Evolve noting templated evidence limited to one topology family. Bibliometrically, the OpenAlex record lists 14 works over the last three years — 3 in 2024, 1 in 2025, and 10 in 2026 — with h-index 3, i10-index 0, exactly 1 distinct coauthor (Yamini Sehgal), and a focus score of 100 from a single indexed field. Activity scores 79 and reproducibility averages 55 over one assessed paper. Output and impact remain unscored for insufficient data, and the record's scattered topic tags warrant caution about name clustering.
Collaboration pattern
Collaboration is tightly scoped: exactly 1 distinct coauthor appears in the record, and Yamini Sehgal is the recurring frequent collaborator. Both catalog papers are first-authored under this compact two-person setup, with the dispatch paper additionally led as corresponding author. The low collaboration score (14) matches this pattern — focused small-team output rather than broad multi-institution networks; the single-institution affiliation (EPRI) is consistent with that picture.
Research keywords
Highlights
Controlled ablation puts spatial dependence's dispatch value under 0.64%
Seed-anchored graph rendering answers CGMES questions at zero token cost
Timeline
- 2024Earliest year in the bibliometric snapshot: 3 publications recorded in countsByYear.
- 2025A quiet year, with only 1 publication recorded.
- 2026Peak output year: 10 publications; both Evolve-reviewed papers appear as first-author arXiv preprints, one led as corresponding author.
Papers in the Evolve catalog
- first authorcorresponding
The Operational Value of Spatial Dependence in Renewable Forecast Scenarios for Single-Period Economic Dispatch: A Controlled Ablation Study
- first author
Seed-Anchored Budget-Bounded Graph Rendering for Question Answering on Industry-Standard Power-Grid Information and Exchange Models
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 figures come from the OpenAlex record only (identity: openalex).
- The output and impact axes are unscored because the underlying metrics are insufficient; h-index 3 and i10-index 0 indicate a very early citation record.
- The reproducibility score averages only 1 assessed paper (reproMean 55, reproPapers 1); both reviewed papers are medium repro-readiness arXiv preprints.
- OpenAlex topic tags on this record span unrelated clusters (semantic web, topic modeling, digital marketing, service AI, smart grids), so name-clustering cannot be ruled out; the profile is name-resolved from public bibliographic data.