Remote sensing researcher building reproducible wildfire benchmarks and geospatial resilience audits in California
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-20) 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-volume metric is available yet. This axis would measure total outputs and their pace over time; the current snapshot contains only the two reviewed 2026 arXiv papers, too few to score.
Impact—
Citation counts, h-index and uptake indicators are not available in this snapshot. This axis would measure how often and how widely the two wildfire studies are cited and reused by other researchers.
Focus0/100
Scores 0 because the reviewed catalog splits evenly (0.5/0.5) across two fields: remote sensing of agricultural wildfire resilience and remote sensing wildfire detection. The split sits within one application domain — California wildfire remote sensing — so the low score reflects even two-way coverage in a tiny two-paper sample rather than scattered interests.
Collaboration32/100
Scores 32, computed from 4 distinct co-authors across the two reviewed papers — a small-team pattern. Recurring collaborators are Parastoo Farajpoor, Mahla Ardebili Pour, Mohammad Bagher Ghiasi and Shreyan Mitra. He is a middle author on the Sentinel-2 benchmark and last-listed author on the Kincade Fire audit, so co-authorship breadth is currently narrow but consistent.
Activity—
No recent-publication cadence data is available. This axis would measure publishing rhythm and continuity over recent years; with only two 2026 papers on record, no activity trend can be computed.
Reproducibility100/100
Scores 100, the mean across 2 papers assessed for reproducibility. The Sentinel-2 benchmark is openly licensed and well documented, and the Kincade Fire study is openly reproducible, publishing boundary, donut, placebo and residual-spatial diagnostics; both carry high repro-readiness, indicating datasets and scripts other teams can rerun with little friction.
Research summary
Mohammadreza Narimani is a remote sensing researcher whose reviewed work to date concentrates on wildfire applications in California, split evenly between deep-learning fire detection and geospatial analysis of agricultural fire resilience. As a middle author he contributed to a well-documented, openly licensed Sentinel-2 active-fire segmentation benchmark covering 2,148 chips across 25 California wildfires; Evolve's review notes that its labels are algorithmic, so the benchmark measures rule reproduction rather than fire-detection ground truth. He is also the last-listed author of a multisource geospatial audit of the 2019 Kincade Fire across 4,581 Sonoma vineyard fields, combining dNBR burn severity and OpenET evapotranspiration; the finding that vines show lower dNBR is real descriptively but dissolves under boundary, donut, placebo and residual-spatial diagnostics, so no firebreak effect is claimed. Both papers carry high reproducibility readiness, producing a perfect reproducibility mean of 100 across 2 papers. Collaboration metrics are modest — 4 distinct co-authors and a collaboration score of 32 — with recurring collaborators including Parastoo Farajpoor, Mahla Ardebili Pour, Mohammad Bagher Ghiasi and Shreyan Mitra. Output, impact and activity metrics are not yet available, and no institution, country or ORCID is on record, so this profile is name-resolved from public bibliographic data and should be read as an early-stage picture.
Collaboration pattern
All reviewed work is small-team: 4 distinct co-authors and a collaboration score of 32. Parastoo Farajpoor, Mahla Ardebili Pour, Mohammad Bagher Ghiasi and Shreyan Mitra recur across the pair of papers. Narimani moves between middle authorship on the Sentinel-2 benchmark and final-listed (non-corresponding) authorship on the Kincade Fire audit, indicating a dual contributor and terminal-author role within a compact wildfire remote-sensing group.
Research keywords
Highlights
Sentinel-2 active-fire segmentation benchmark: 2,148 chips across 25 California wildfires
Kincade Fire vineyard audit: apparent firebreak effect dissolves under spatial diagnostics
Timeline
- 2026Contributed as a middle author to the Sentinel-2 benchmark dataset for deep-learning active-fire segmentation, spanning 2,148 chips across 25 California wildfires.
- 2026Served as last-listed author of the multisource geospatial analysis of vineyard wildfire impacts in the 2019 Kincade Fire, auditing 4,581 Sonoma vineyard fields.
- 2026Both reviewed papers were released on arXiv with high reproducibility readiness, yielding a perfect reproducibility mean of 100 across 2 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.
- Profile is name-resolved from public bibliographic data; no institution, country or ORCID is available to confirm identity.
- The bibliometric snapshot covers only 2 arXiv-reviewed papers (both 2026); output, impact and activity metrics are unavailable.
- All statistics quoted here come from the provided OpenAlex-derived snapshot and Evolve's paper reviews; no external sources were consulted.
- The perfect reproducibility score rests on 2 papers only and may shift as more work is reviewed.