Hello there!
My name is Blas, and I am a spatial data scientist and engineer in AgTech, holding a PhD in computational ecology and an MSc in geographic information systems.
My expertise lies at the intersection of spatial and temporal modeling, soil and plant ecology, remote sensing, machine learning, and environmental dynamics and monitoring.
I’m deeply passionate about crafting automated data and modeling pipelines to tackle complex environmental challenges.
Currently, I lead the Environmental Data Team at Biome Makers Inc. In this role, I research and develop cutting-edge smart farming technologies, create essential R packages to enhance our Data Science Department’s capabilities, and oversee the design and maintenance of an environmental data infrastructure to further empower our flagship product, BeCrop®.
My tech stack is built entirely on open-source tools: I rely on R and git+ GitHub for collaborative software development and version control. For pipeline design, I harness the power of targets, and to encapsulate code I employ renv and docker.
For GIS tasks, I turn to industry-standard tools like GRASS GIS, Quantum GIS, and PostGIS.
My data management and processing are handled by PostgreSQL, DuckDB, Apache Arrow, and Apache Spark.
Computationally-intensive pipelines find their home in my tiny home-cluster managed by slurm.
For developing and deploying REST APIs, I turn to plumber, while interactive apps are crafted with Shiny. My interactive reports come to life using either Rmarkdown or Quarto.
Before delving into AgTech, I honed my research and technical skills during a successful academic career in Computational Ecology. I worked in world-class labs in Spain ( IISTA and Maestre Lab), Denmark ( Jens-Christian Svenning Lab), and Norway ( EECRG).
My research primarily focused on unveiling the environmental drivers shaping the distribution of biological diversity in space and time. During this journey, I developed scientific R packages for various purposes, such as time-series comparison and analysis of lagged effects, spatial modeling with Random Forest, and ecological simulation.
Throughout this journey, I collaborated with 210 esteemed coauthors from 22 countries to publish 49 research papers in reputable peer-reviewed journals. To date, our collective work has garnered over 1600 citations. Notably, three of these papers have received recognition as ‘most downloaded papers’ in prestigious journals, and two have been honored as ‘editor’s picks’.
In my leisure time, I cherish moments with my family, tinker on the piano with enthusiasm (regardless of the results!), embrace the serenity of the sea on my stand-up paddle board, and continue my passion for developing R packages.
I’m always eager to connect with fellow data enthusiasts, researchers, and professionals. Feel free to connect with me on LinkedIn to explore potential collaborations and discussions within our shared field.
Ph.D. in Computational Ecology, 2006 - 2009
University of Granada
UNIGIS International Masters Degree in Geographical Information Sys-tems, 2007 - 2009
University of Girona
Masters Degree in Management and Environmental Auditing, 2005 - 2006
University of Cadiz
Degree in Biology, 1999 - 2003
University of Granada
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
100%
R package for multicollinearity management in data frames with numeric and categorical variables.
R package for spatial regression with Random Forest
This is a spatio-temporal simulation of the effect of fire regimes on the population dynamics of five forest species during the Lateglacial-Holocene transition (15-7 cal Kyr BP) at El Portalet, a subalpine bog located in the central Pyrenees region (1802m asl, Spain)
Agent-based model coded with Netlogo to simulate range shift of Quercus pyrenaica populations in Sierra Nevada (Spain) using a realistic dispersal model with different levels of complexity.
R package to compare multivariate time-series.
R package to assess ecological memory in multivariate time-series.
R package to simulate pollen production of mono-specific tree populations over millennia.
Fairy circles (FCs) are intriguing regular vegetation patterns that have only been described in Namibia and Australia so far. We conducted a global and systematic assessment of FC-like vegetation patterns and discovered hundreds of FC-like locations on three continents. We also characterized the range of environmental conditions that determine their presence, which is restricted to narrow and specific soil and climatic conditions. Areas showing FC-like vegetation patterns also had more stable productivity over time than surrounding areas having non-FC patterns. Our study provides insights into the ecology and biogeography of these fascinating vegetation patterns and the first atlas of their global distribution.
Although density-dependent processes and their impacts on population dynamics are key issues in ecology and conservation biology, empirical evidence of density-dependence remains scarce for species or populations with low densities, scattered distributions, and especially for managed populations where densities may vary as a result of extrinsic factors (such as harvesting or releases). Here, we explore the presence of density-dependent processes in a reinforced population of North African Houbara bustard (Chlamydotis undulata undulata). We investigated the relationship between reproductive success and local density, and the possible variation of this relationship according to habitat suitability using three independent datasets. Based on eight years of nests monitoring (more than 7000 nests), we modeled the Daily Nest Survival Rate (DNSR) as a proxy of reproductive success. Our results indicate that DNSR was negatively impacted by local densities and that this relationship was approximately constant in space and time: (1) although DNSR strongly decreased over the breeding season, the negative relationship between DNSR and density remained constant over the breeding season; (2) this density-dependent relationship did not vary with the quality of the habitat associated with the nest location. Previous studies have shown that the demographic parameters and population dynamics of the reinforced North African Houbara bustard are strongly influenced by extrinsic environmental and management parameters. Our study further indicates the existence of density-dependent regulation in a low-density, managed population.
Here we synthesize the biogeography of key organisms (vascular and non‐vascular vegetation and soil microorganisms), attributes (functional traits, spatial patterns, plant‐plant and plant‐soil interactions) and processes (productivity and land cover) across global drylands. We finish our review discussing major research gaps, which include: i) studying regular vegetation spatial patterns, ii) establishing large‐scale plant and biocrust field surveys assessing individual‐level trait measurements, iii) knowing whether plant‐plant and plant‐soil interactions impacts on biodiversity are predictable and iv) assessing how elevated CO2 modulates future aridity conditions and plant productivity.
We introduce distantia (v1.0.1), an R package providing general toolset to quantify dissimilarity between ecological time‐series, independently of their regularity and number of samples. The functions in distantia provide the means to compute dissimilarity scores by time and by shape and assess their significance, evaluate the partial contribution of each variable to dissimilarity, and align or combine sequences by similarity.
Paper published in the section “Editor’s Choice” of the Ecography journal. It received an award for the number of downloads during the 12 months after its publication.
This paper was highlighted in the Editor’s Picks section of the Science Journal, and was among the top downloaded articles from the Journal of Biogeography during the 12 months after its publication.
The Mediterranean Basin is threatened by climate change, and there is an urgent need for studies to determine the risk of plant range shift and potential extinction. In this study, we simulate potential range shifts of 176 plant species to perform a detailed prognosis of critical range decline and extinction in a transformed mediterranean landscape. Particularly, we seek to answer two pivotal questions: (1) what are the general plant‐extinction patterns we should expect in mediterranean landscapes during the 21st century? and (2) does dispersal ability prevent extinction under climate change?.
We generated 380 S‐SDMs of 1224 tree species in Mesoamerica by combining 19 distribution modelling methods with 20 different thresholds using presence‐only data from the Global Biodiversity Information Facility. We compared the predicted richness and composition with inventory data obtained from the BIOTREE‐NET forest plot database. We designed two indicators of predictive performance that were based on the diversity factors used to measure species turnover: a (shared species between the observed and predicted compositions), b and c (the exclusive species of the predicted and observed compositions respectively) and compared them with the Sorensen and Beta‐Simpson turnover measures. Some modelling methods – especially machine learning and ensemble model forecasting methods performed significantly better than others in minimizing the error in predicted richness and composition. Our results also indicate that restrictive thresholds (with high omission errors) lead to more accurate S‐SDMs in terms of species richness and composition. Here, we demonstrate that particular combinations of modelling methods and thresholds provide results with higher predictive performance.