Text mining and sensor fusion veteran at University of Oulu, now applied AI for climate and disaster analytics
3
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
32
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 axis measures total publication volume and its yearly distribution. The snapshot lists annual work counts from 1999 to 2026, but a consolidated output score has not been computed, so no estimate is offered here.
Impact—
Not yet scored. This axis would measure citation-based influence such as citations per work and field-normalized impact. The snapshot lists h-index 32 and i10-index 89 as raw indicators, but the composite impact score has not been computed from citation data.
Focus100/100
Scored 100. Topic distribution shows a strongly concentrated profile: Topic Modeling (45 works), Sentiment Analysis and Opinion Mining (32) and Natural Language Processing Techniques (28) dominate, with adjacent clusters in Target Tracking and Data Fusion (31) and Fuzzy Logic and Control Systems (22), indicating a sustained text-mining core.
Collaboration64/100
Scored 64. The last three years link 80 works to 24 distinct co-authors, a moderately sized network. Recurrent partners include Kavindu Perera, Mohammad Abaeiani, Ekaterina Gilman, Lauri Loven and Tassos Kanellos, with recent arXiv papers placing him in middle or last rather than first author position.
Activity100/100
Scored 100. Publication activity is high and accelerating: yearly counts rise from 13-17 works in 2019-2021 to 37 in 2022, then 27 in 2023, 29 in 2024, 25 in 2025 and 26 in 2026, with 80 works across the last three years.
Reproducibility20/100
Scored 20 from one reviewed paper. The climate tipping-point detector releases neither code nor data, and its Set B accuracy trails the majority baseline; the disaster severity study is rated medium but is tested on a filtered 129-sample subset. Reproducibility is a current weakness.
Research summary
Mourad Oussalah is a researcher at the University of Oulu (Finland), name-resolved here from OpenAlex bibliographic data linked to ORCID 0000-0002-4422-8723. His topic profile combines long-standing text mining with a sensing and control background: Topic Modeling (45 works), Sentiment Analysis and Opinion Mining (32), Target Tracking and Data Fusion in Sensor Networks (31), Natural Language Processing Techniques (28) and Fuzzy Logic and Control Systems (22). The snapshot lists an h-index of 32 and an i10-index of 89, with publication counts spanning 1999 to 2026, a 2022 peak of 37 works, 80 works in the last three years and 24 distinct co-authors. Recent catalog papers push this base into applied AI: a modular passage-level framework for detecting and structuring social tipping point evidence in climate documents; a multimodal disaster severity assessment pipeline using supervised fine-tuning and Direct Preference Optimization on human-validated rationales; and FiLM-GPNet, a geometry-aware pseudo-supervised network for phase restoration in large temporal InSAR stacks. Evolve's reviews flag real limitations — unreleased code and data for the tipping-point detector and a filtered 129-sample test subset for the disaster study — leaving the reproducibility mean at 20 across one reviewed paper.
Collaboration pattern
With 24 distinct co-authors across 80 works in the last three years, Oussalah operates in moderately sized, project-driven teams. Frequent partners include Kavindu Perera, Mohammad Abaeiani, Ekaterina Gilman, Lauri Loven and Tassos Kanellos. On the 2026 catalog papers he is never first author — middle on the climate tipping point study and last on the disaster assessment and InSAR papers — and is corresponding author on neither, a pattern consistent with a senior supervisory role.
Research keywords
Highlights
Modular AI framework surfaces social tipping point evidence in climate documents
Preference optimization improves multimodal disaster severity assessment
FiLM-GPNet targets phase restoration in large temporal InSAR stacks
A geometry-aware pseudo-supervised network aims at zero-shot generalization across large temporal InSAR stacks; this arXiv preprint has not yet received an Evolve review, keywords, or reproducibility rating.
Timeline
- 1999Earliest publication year in the OpenAlex snapshot, with 6 works recorded.
- 2019Annual output reaches 17 works, the highest level before the 2022 surge.
- 2022Peak annual output of 37 works in the snapshot's counts-by-year series.
- 2026Three arXiv preprints appear: climate social tipping point detection, multimodal disaster severity assessment, and the FiLM-GPNet InSAR paper.
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.
- Bibliometric indicators (h-index, i10-index, yearly counts, topics, co-author counts) come from an OpenAlex-based snapshot; consolidated output and impact scores are not yet computed.
- Only two of the three listed papers have full Evolve reviews; the FiLM-GPNet InSAR preprint has no verdict, keywords, or reproducibility assessment.
- The reproducibility score of 20 rests on a single reviewed paper and may shift as more of the catalog is assessed.
- Identity is name-resolved from public bibliographic data linked to ORCID 0000-0002-4422-8723; biographical details beyond the snapshot are not covered.