Environmental Analytics
Data-Driven Solutions for
Climate & Biodiversity
We apply production-grade data science to environmental challenges — from environmental impact assessments and biodiversity monitoring to carbon market analytics and climate risk modelling. Member of the Environment Institute of Kenya.
Capabilities
Environmental Data Science at Scale
Reproducible, transparent, and auditable environmental analytics — built with the same engineering rigour we apply across all our work.
Environmental Impact Assessment (EIA/ESIA)
Reproducible analytical workflows for environmental impact assessments that go beyond static reports. We build R-based pipelines that make EIA data transparent, auditable, and reusable.
- Reproducible ESIA workflows — Version-controlled analysis code, automated reporting, and transparent methodology
- Regulatory compliance analytics — Structured evaluation against EMCA 1999 and 2025 amendment requirements
- Spatial impact modelling — Geospatial analysis of project footprints, buffer zones, and sensitive areas
- Open-source tooling — Our kenyaEIAFetcher package provides programmatic access to Kenya’s EIA database
EIA/ESIA EMCA Reproducibility Quarto
library(kenyaEIAFetcher)
projects <- fetch_eia_projects(
county = “Nairobi”,
sector = “Energy”,
year_range = c(2020, 2025)
)
report <- generate_esia_report(
projects,
template = “compliance_review”,
output = “quarto”
)
Biodiversity & Conservation
Rigorous biodiversity data analytics using the Global Biodiversity Information Facility (GBIF) and other ecological datasets. We build quality assessment pipelines that ensure conservation decisions are based on reliable data.
- GBIF data quality assessment — Automated detection of coordinate errors, taxonomic inconsistencies, and temporal gaps
- Species distribution modelling — Spatial prediction of species occurrence under current and future climate scenarios
- Ecological monitoring systems — Dashboards and reporting tools for tracking biodiversity indicators over time
- Conservation planning support — Data-driven prioritisation of conservation areas and interventions
GBIF Species Modelling Ecological Data rgbif
library(rgbif)
library(sf)
occurrences <- occ_search(
country = “KE”,
hasCoordinate = TRUE,
limit = 50000
)
clean_data <- occurrences |>
flag_coordinate_issues() |>
validate_taxonomy() |>
remove_duplicates()
Carbon Markets & Climate Risk
Quantitative methods applied to the emerging carbon market ecosystem. We bridge environmental science and financial analytics to support organisations navigating voluntary and compliance carbon markets.
- Carbon credit analytics — Statistical analysis of carbon credit pricing, market trends, and regime detection
- GHG inventory systems — Automated greenhouse gas accounting pipelines aligned with international standards
- Climate risk assessment — Data-driven evaluation of physical and transition risks for projects and portfolios
- Verification & additionality — Statistical methods for assessing the credibility and permanence of carbon offset projects
Carbon Markets GHG Accounting Climate Risk NDCs Time Series
library(depmixS4)
library(forecast)
model <- depmix(
price ~ 1,
data = carbon_prices,
nstates = 3,
family = gaussian()
)
emissions <- compute_ghg(
activity_data,
factors = “IPCC_2019”
)
Geospatial Analysis & Remote Sensing
Spatial data underpins much of our environmental work. We use R’s powerful geospatial ecosystem to analyse satellite imagery, model spatial relationships, and create interactive mapping tools.
- Satellite data processing — Land use classification, vegetation indices (NDVI), and change detection
- Spatial impact analysis — Buffer analysis, overlay operations, and environmental sensitivity mapping
- Interactive mapping — Leaflet-based dashboards for stakeholder engagement and project monitoring
- Urban environmental analysis — Heat island mapping, green infrastructure planning, and air quality modelling
sf terra leaflet mapview NDVI Remote Sensing
library(sf)
library(terra)
library(leaflet)
ndvi <- rast(“sentinel_ndvi.tif”)
counties <- st_read(“kenya_counties.gpkg”)
ndvi_stats <- extract(
ndvi, counties,
fun = “mean”
) |>
classify_vegetation()
Credentials & Commitment
Our environmental work is backed by professional membership, open-source contributions, and domain expertise.
Environment Institute of Kenya
Professional member of the EIK, Kenya’s professional body for environmental practitioners. Our work aligns with national environmental governance standards.
Open-Source Contributor
Our
kenyaEIAFetcher R package provides programmatic access to Kenya’s EIA database — advancing environmental data transparency.
Reproducible Science
Every environmental analysis is version-controlled, documented, and fully reproducible. We advocate for transparency in environmental governance and decision-making.
Environmental Insights
Selected writing on environmental data science, reproducibility, and sustainability.
A critical evaluation of Kenya’s environmental impact assessments and the case for reproducible analytical workflows.
Comprehensive data quality assessment and cleaning workflows for GBIF biodiversity data from Kenya.
Data-driven solutions for sustainable urban development in informal settlements using R.
Where environmental science meets finance — quantitative methods for the emerging carbon market ecosystem.
Ready to Tackle Environmental Challenges with Data?
From EIA analytics to carbon market modelling, we bring rigorous data science to environmental decision-making.