Sep 29, 2025
🚨 New study! 🐆 We report new distribution records for 8 mammal species, including capybara and anteater. 📍Elevation shifts of up to 1,521 m! 🛣️ Roadkill data can guide conservation, but also inform on species ecology.
I am a Conservation biologist and macroecologist with expertise in spatial ecology, trait-based modeling, and multidimensional biodiversity analysis (taxonomic, functional, and phylogenetic). I also apply Explainable Artificial Intelligence (Inductive Logic Programming) to understand how human pressures shape biodiversity patterns across geographic and taxonomic scales.
My current work as a Postdoctoral Fellow in the Department of Computer Science at Oklahoma State University (USA) focuses on adapting artificial intelligence tools—particularly Inductive Logic Programming—to generate explainable rules for ecological processes.
Previously, I was a postdoctoral researcher at the Spanish National Research Council (CSIC), where my work mainly consisted in evaluating the dynamics of steppe birds hotspots over time in the Iberian Peninsula, assessing the role of protected areas in steppe birds conservation, and calculating/mapping the taxonomic, functional, and phylogenetic diversity of steppe birds and their exposure to renewable energy projects. In addition, my work contributed to other scientific publications such as the European assessment of the conservation status of steppe birds, and another paper on the exposure of sandgrouse populations to photovoltaic infrastructure.
Previously, I was a postdoctoral researcher at the Spanish National Research Council (CSIC), where my work mainly consisted in evaluating the dynamics of steppe birds hotspots over time in the Iberian Peninsula, assessing the role of protected areas in steppe birds conservation, and calculating/mapping the taxonomic, functional, and phylogenetic diversity of steppe birds and their exposure to renewable energy projects. In addition, my work contributed to other scientific publications such as the European assessment of the conservation status of steppe birds, and another paper on the exposure of sandgrouse populations to photovoltaic infrastructure.
I obtained my PhD in Ecology and Evolutionary Biology at the University of Reading (UK), where I studied the drivers of wildlife mortality on roads in Latin America using spatial analyses, trait-based models, and machine learning techniques. Specificallly, my research identified 1) areas in Latin America with a higher wildlife mortality on roads and species traits that increase roadkill risk, 2) priority areas for research and conservation, 3) landscape and road features associated with increased risk. I also created and currently lead REMFA, a citizen science project to collect roadkill data in Ecuador, which proved valuable for 4) evaluating these impacts at the country level. In addition, using the data collected in the field, I expanded my research into other areas, resulting in publications in Genetics, and Parasitology.
Nevertheless, my starting point in science was my MSc in Conservation Biology at the Pontificia Universidad Católica del Ecuador, where I carried out the first systematic assessment of road impacts on wild tetrapods in Ecuador, laying the foundations for road ecology research in the country.
I am deeply curious and fascinated about understanding the patterns that rule life. Then I am constantly exploring new tools that allow improving data analysis.
Nevertheless, my starting point in science was my MSc in Conservation Biology at the Pontificia Universidad Católica del Ecuador, where I carried out the first systematic assessment of road impacts on wild tetrapods in Ecuador, laying the foundations for road ecology research in the country.
I am deeply curious and fascinated about understanding the patterns that rule life. Then I am constantly exploring new tools that allow improving data analysis.
Life is more than academia, and I also love other activities that involve music, going to concerts, movies, travelling, knowing new places, new cultures, and trying new beers!
Please, feel free to contact me. I will be happy to discuss any potential collaborations.
Please, feel free to contact me. I will be happy to discuss any potential collaborations.
Contact
[Contact picture]
Pablo Medrano-Vizcaíno, PhD
Postdoctoral Fellow
Department of Computer Science
Oklahoma State University
NEWS!
New Preprint! 21st of May 2026
Explainable AI reveals the quantitative hierarchical architecture of global bird extinction risk
Identifying what makes species vulnerable to extinction requires accounting for complex biological and environmental interactions. Due to their high predictive accuracy, machine learning methods have been widely used for these assessments; however, relying on black-box models offers limited interpretability. Here, using a comprehensive dataset of anthropogenic, ecological, morphological, demographic, and biogeographical variables from 9,053 species (81% of birds worldwide), we applied Inductive Logic Programming (ILP), an explainable artificial intelligence framework, to generate explicit and quantitative IF-THEN rules with confidence scores for bird extinction risk. Our approach revealed that extinction vulnerability follows a hierarchical structure, shaped by interactions among range size, morphological traits, and human pressures. The framework recovered well-established knowledge, while also revealing previously undescribed extinction patterns. For example, consistent with prior evidence, species with geographic ranges below ∼13,500 km² were identified as higher risk (88% confidence). Nevertheless, this threshold shifted to ∼3,270 km² when human impacts were removed, revealing quantitatively how anthropogenic activities expand the pool of vulnerable species beyond those at risk due to biological and biogeographical traits alone. Beyond established patterns, species with tail length >304 mm were identified as higher risk (82% confidence), a pattern not previously documented. ILP models achieved 91% overall accuracy, slightly lower than Random Forest (93%), but notably better than Neural Networks (83%). These results show that ILP can offer high accuracy results with full interpretability, also providing quantitative transition thresholds that clarify the structural architecture of extinction risk, and translate complex ecological interactions into actionable tools for conservation.
Explainable AI reveals the quantitative hierarchical architecture of global bird extinction risk
Identifying what makes species vulnerable to extinction requires accounting for complex biological and environmental interactions. Due to their high predictive accuracy, machine learning methods have been widely used for these assessments; however, relying on black-box models offers limited interpretability. Here, using a comprehensive dataset of anthropogenic, ecological, morphological, demographic, and biogeographical variables from 9,053 species (81% of birds worldwide), we applied Inductive Logic Programming (ILP), an explainable artificial intelligence framework, to generate explicit and quantitative IF-THEN rules with confidence scores for bird extinction risk. Our approach revealed that extinction vulnerability follows a hierarchical structure, shaped by interactions among range size, morphological traits, and human pressures. The framework recovered well-established knowledge, while also revealing previously undescribed extinction patterns. For example, consistent with prior evidence, species with geographic ranges below ∼13,500 km² were identified as higher risk (88% confidence). Nevertheless, this threshold shifted to ∼3,270 km² when human impacts were removed, revealing quantitatively how anthropogenic activities expand the pool of vulnerable species beyond those at risk due to biological and biogeographical traits alone. Beyond established patterns, species with tail length >304 mm were identified as higher risk (82% confidence), a pattern not previously documented. ILP models achieved 91% overall accuracy, slightly lower than Random Forest (93%), but notably better than Neural Networks (83%). These results show that ILP can offer high accuracy results with full interpretability, also providing quantitative transition thresholds that clarify the structural architecture of extinction risk, and translate complex ecological interactions into actionable tools for conservation.
Book chapters published! 30th of April 2026
Finally published: “Road Ecology: Synthesis and Perspectives”. This Springer Nature book covers the foundations of Road Ecology research, and I’m very happy to have participated as an author of two chapters:
“Species Traits in Road Ecology: Defining
Intrinsic Vulnerability” https://doi.org/10.1007/978-3-032-16641-8_39
“Charting the Path Ahead: Key Research
Priorities in Road Ecology” https://doi.org/10.1007/978-3-032-16641-8_50
Finally published: “Road Ecology: Synthesis and Perspectives”. This Springer Nature book covers the foundations of Road Ecology research, and I’m very happy to have participated as an author of two chapters:
“Species Traits in Road Ecology: Defining
Intrinsic Vulnerability” https://doi.org/10.1007/978-3-032-16641-8_39
“Charting the Path Ahead: Key Research
Priorities in Road Ecology” https://doi.org/10.1007/978-3-032-16641-8_50
💡
New paper in Conservation Biology! 19th of April 2026
Is species richness alone enough to inform conservation decisions? And how exposed is biodiversity to expanding solar infrastructure? Our new study "Identifying the exposure of taxonomic, functional, and phylogenetic diversity of steppe birds to renewable energy development", published in Conservation Biology tackles both.
https://doi.org/10.1111/cobi.70291
We used steppe birds (Europe’s most threatened bird group) in Spain (their main stronghold) to assess:
✅ Taxonomic diversity (species richness)
✅ Functional diversity (ecological roles)
✅ Phylogenetic diversity (evolutionary history)
Results:
→ Combining Taxonomic, Functional, and Phylogenetic diversity is significantly more effective for conservation
→ Prioritizing species richness alone results in losing approximately 50% of functional diversity and 66% of phylogenetic diversity.
Next, we overlaid our multifaceted diversity map with existing photovoltaic infrastructure and found that 53% of Spain’s top multidimensional biodiversity areas already host solar installations, indicating that biodiversity is likely already under substantial pressure.
Our results highlight the need to integrate multiple biodiversity dimensions into conservation planning — and advance an energy transition truly compatible with nature.
Is species richness alone enough to inform conservation decisions? And how exposed is biodiversity to expanding solar infrastructure? Our new study "Identifying the exposure of taxonomic, functional, and phylogenetic diversity of steppe birds to renewable energy development", published in Conservation Biology tackles both.
https://doi.org/10.1111/cobi.70291
We used steppe birds (Europe’s most threatened bird group) in Spain (their main stronghold) to assess:
✅ Taxonomic diversity (species richness)
✅ Functional diversity (ecological roles)
✅ Phylogenetic diversity (evolutionary history)
Results:
→ Combining Taxonomic, Functional, and Phylogenetic diversity is significantly more effective for conservation
→ Prioritizing species richness alone results in losing approximately 50% of functional diversity and 66% of phylogenetic diversity.
Next, we overlaid our multifaceted diversity map with existing photovoltaic infrastructure and found that 53% of Spain’s top multidimensional biodiversity areas already host solar installations, indicating that biodiversity is likely already under substantial pressure.
Our results highlight the need to integrate multiple biodiversity dimensions into conservation planning — and advance an energy transition truly compatible with nature.