Applied machine learning researcher at OTH Amberg-Weiden: smart-grid protection, load forecasting, bioacoustics
3
papers here
3
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
15
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-13) 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: the data supplies no total publication count, venue mix, or per-paper output detail. This axis would measure cumulative output volume, productivity trajectory, and publication types across the record.
Impact—
Not scored: the record lists h-index 15 and i10-index 18, but no broader citation data (per-paper citations, field-normalized metrics) was provided, so this axis has no computed value. It would measure citation uptake and field-normalized influence of the work.
Focus0/100
Scored 100: topical concentration is high. The five labeled topics — marine animal studies (16), power system fault detection (10), animal vocal communication and behavior (9), speech recognition and synthesis (8), underwater acoustics (8) — reduce to two coherent strands, and the recent field distribution lists a single field, electric power systems (smart grids) / applied machine learning, matching both 2026 reviewed papers.
Collaboration55/100
Scored 48, a mid-range collaboration signal: 10 distinct coauthors over the last three years, with recurring partners including Julian Oelhaf, Siming Bayer, Andreas Maier, and Johann Jäger. Both Evolve-reviewed 2026 papers list Bergler as a middle author rather than corresponding author, consistent with a contributor role inside larger applied-ML teams rather than solo or lead positions.
Activity100/100
Scored 100: the record is highly active. It shows 30 works in the most recent three-year window, and per-year counts climb from 3 works in 2024 and 7 in 2025 to 20 in 2026 — the highest in the 2019–2026 record, versus an earlier baseline of roughly 3–8 works per year.
Reproducibility85/100
Scored 55 (reproMean 55, from 1 scored paper): the signal rests on EvEMTBench, rated high for reproducibility readiness as an open, versioned benchmark of 4 grids and 24 tasks, while the peak-aware load forecasting paper is rated medium, with reviewers noting gradient-boosting baselines handicapped by fixed seasonal training windows.
Research summary
Christian Bergler is a Germany-based applied machine learning researcher at Ostbayerische Technische Hochschule Amberg-Weiden whose OpenAlex record spans two converging themes: intelligent power systems and bioacoustic AI. Topic counts concentrate on marine animal studies (16), power system fault detection (10), animal vocal communication and behavior (9), speech recognition and synthesis (8), and underwater acoustics (8) — a profile built on sequence models applied to both grid telemetry and animal sound. Recent output is intense: 30 works in the last three years, with 2026's count of 20 the highest in the 2019–2026 record against an earlier baseline of 3–8 works per year. Bibliometric standing is modest but real (h-index 15, i10-index 18). Evolve has reviewed two 2026 arXiv papers where Bergler is a middle author: EvEMTBench, an open, versioned benchmark for machine learning in power system protection (4 grids, 24 tasks) judged rigorous but fully synthetic, and a peak-aware short-term load forecasting study across distribution grid aggregation levels where Chronos-2 outperformed gradient-boosting baselines. The reproducibility signal (mean 55, one scored paper) leans on EvEMTBench's high open-data readiness.
Collaboration pattern
The record shows a mid-range collaboration profile (score 48) with 10 distinct coauthors in the last three years. Recurring partners include Julian Oelhaf, Siming Bayer, Souhardya Chattopadhyay, Bitan Bhattacharyya, Georg Kordowich, Antonia Schoening, Jessica Deuschel, Andreas Maier, and Johann Jäger — a mix spanning the power-systems and bioacoustics/speech strands. In both Evolve-reviewed 2026 papers Bergler appears as a middle, non-corresponding author, suggesting a contributor role within team-based applied ML groups.
Research keywords
Highlights
EvEMTBench: open, versioned ML-protection benchmark
Chronos-2 wins peak-aware load forecasting at three grid levels
Timeline
- 2019First year covered by the OpenAlex snapshot: 6 works recorded.
- 20218 works recorded, the highest annual count before 2026.
- 2024Output dips to 3 works, the lowest annual count in the record.
- 20257 works recorded as activity rebounds.
- 202620 works recorded — the record's annual peak; both Evolve-reviewed arXiv papers (EvEMTBench; peak-aware load forecasting) fall in this year.
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.
- Bibliometrics (h-index 15, i10-index 18, per-year counts, topics, coauthors) derive from an OpenAlex snapshot; no other database was consulted.
- The output and impact radar axes are unscored because total publication counts and citation detail were not part of the input data.
- Evolve has reviewed only two papers (both 2026 arXiv, middle author); earlier work appears only as aggregate topic and per-year counts.
- Identity is name-resolved from public bibliographic data (OpenAlex); verification against ORCID 0009-0005-1793-5798 is recommended.