Click and drag to select area. Press ESC to cancel.
High zoom
Satellite shows more detail
Active Filters
Selected Area
Custom region
Movement Type
Selected Parks
Jan 2020 - Dec 2024tdToday3dLast 3 days7dLast 7 days14dLast 14 days30dLast 30 days90dLast 90 dayscmoCurrent month+
Welcome Back
Create Account
Upload Conservation Data
5 Megapixels of Global Conservation
A transparent map of global conservation effort
In 2017, the OECD estimated global biodiversity finance at USD 78-91 billion, while potentially harmful investments reached USD 500 billion. Despite this spending, we lack a comprehensive map of where conservation effort actually happens on the ground.
With Earth's surface at 510 million km², dividing into 100 km² pixels gives us 5.1 million pixels – the resolution of an average digital camera in 2010. We aim to create a transparent map showing conservation patrol coverage for each of these pixels.
This tool monitors 162 African keystone protected areas covering 2.1 million km², tracking fire events, deforestation, settlements, and patrol effort to ensure accountability and reveal where resources are needed most.
Quick Start
Click a park to see fire, settlement & deforestation data
Use time slider to filter data by date range
Upload GPX to add patrol tracks (upload button)
Star parks to save and generate reports
Bell icon shows fire alerts & notifications
Data Layers
Fire Activity – Satellite detections grouped into trajectories with origin/destination
Settlements – Built-up areas classified by type and distance to park
Deforestation – Forest loss events clustered and classified by cause
Patrol Tracks – GPS coverage intensity in 10×10 km grid cells
River Turbidity & Mining – Sediment plumes and bare-earth pits along rivers, signs of alluvial mining
How We Process Data
Fire Detection (v5)
Source: NASA VIIRS satellite (375m resolution, 12-hour revisit)
Daily download at 3am UTC from FIRMS NRT API + 30km buffer
Fires clustered using DBSCAN (5km radius) into groups
Groups tracked across days using 12-hour time windows
Trajectories smoothed to eliminate zigzag artifacts
Movement direction, speed, and trajectory quality calculated
Position classified: stopped inside, transited, entirely outside
Settlement Detection
Source: EU Global Human Settlement Layer (10m resolution)
Built-up pixels clustered into settlement polygons
Classified: village, hamlet, farm compound, mining camp
Distance to park boundary and nearest road calculated
Deforestation Analysis
Source: Hansen Global Forest Change (30m resolution)
Annual tree cover loss 2001-2024
Clustered into events (5km radius)
Classified: agricultural clearing, logging, charcoal production
Near-real-time: GFW integrated alerts (GLAD-S2/RADD, ~10m) with 100km buffer — one park rescanned per day
River Turbidity & Mining Detection
Source: Sentinel-2 L2A imagery (10m), sampled along OSM waterways
Flags abrupt turbidity onsets vs. upstream median — the signature of alluvial mining
Companion pit scanner finds bright bare-earth clusters near rivers, verified for persistence across scenes
Rotation: one park scanned per day; each park revisited on a rolling cycle
Patrol Tracking
Upload GPX tracks from GPS devices or apps
Tracks split into 10×10 km grid cells
Movement classified: foot (<7 km/h), vehicle (7-80), aircraft (>80) with subtypes: boat, fixed-wing, rotor-wing from trajectory analysis
Intensity = % of 1km subcells visited in each grid cell
Connect to external GPS tracking services (e.g. EarthRanger / PAMDAS) to automatically
fetch patrol tracks daily. Tracks are anonymised — no names or personal data are stored.
Only person, vehicle, and aircraft tracks are fetched; animal collar data is excluded.
Credential security
Passwords are encrypted with AES-256-GCM before storage — they are never saved in plaintext
and never passed as command-line arguments. The encryption key is stored separately with
restricted file permissions. Disabling a source immediately purges its stored password.