Skills

Statistical modelling: GLM, GAM, mixed-effects, hierarchical models
Spatial modelling: species distribution models, spatiotemporal analysis, spatial autocorrelation, spatial forecasting
Machine learning: supervised & unsupervised models (regression, clustering, Random Forests, Gradient Boosting, MaxEnt); model evaluation, feature scaling, and cross-validation.
Bayesian inference: hierarchical & spatiotemporal models, detection–abundance separation
Hybrid modelling: integration of mechanistic and statistical frameworks for process-based forecasting
Forecasting & simulation: population viability, simulation-based forecasting, scenario testing
Multivariate analysis: PCA, correlation structure analysis, ordination methods
Model evaluation: cross-validation (incl. spatial CV), calibration & error metrics (RMSE/MAE, PPCs)
Model interpretation: feature importance, partial dependence, SHAP, mechanistic interpretation of predictive models
Probability modelling: hypergeometric, Monte Carlo simulation

Languages: R, Python, SQL, JAGS
Python data stack: pandas, NumPy, scikit-learn; OOP (composition, inheritance/polymorphism); CLI apps (argparse/click); regex; logging & error handling
Data acquisition & I/O: CSV/Excel/JSON, PDF parsing basics, HTTP APIs (requests), web scraping (BeautifulSoup/lxml)
Databases & storage: SQLite, Microsoft Access; SQL querying (SELECT/JOIN/AGGREGATE, CTEs/window functions – foundational)
Reproducible workflows: version control (Git/GitHub – branching/PRs), environments (renv, venv/conda), parallel processing
Visualisation: R (ggplot2/base), Python (matplotlib, Plotly, Seaborn)
Geospatial/remote sensing: raster/vector processing, spatial joins, satellite-derived metrics (terra/sf or equivalents)
Testing & quality: unit tests with pytest, assertions, data validation checks
Packaging & docs: module structure, docstrings/type hints, README/usage examples
Web & apps: GitHub Pages (this site), Shiny apps (R)
Data preprocessing (missing-value handling, feature engineering).
Data integration (joining large relational datasets, APIs + SQL combo).

Pattern detection in complex, high-dimensional datasets
Forecasting to predict trends, risks, and opportunities
Tailored statistical analysis aligned to data & objectives
Decision-support tools: interactive apps/dashboards for stakeholders
Workflow optimisation: high-performance/parallel pipelines, memory-efficient geoprocessing
Translation to action: clear, actionable recommendations for managers & policy
Data-driven frameworks for strategic decision-making
Model interpretability

Writing: lead & co-author on peer-reviewed papers; clear technical documentation
Speaking: conference talks, workshops, stakeholder briefings; tailored to technical & non-technical audiences