Biodiversity is declining at an unprecedented rate, underscoring the critical role of protected areas (PAs) in conserving threatened species and ecosystems. Yet, many of these are increasingly dismissed as "paper parks" due to poor management. Park rangers play a vital role in PA effectiveness by detecting and potentially deterring illegal activities. However, limited funding for PA management has led to low patrol frequency and detection rates, reducing the overall deterrent effect of ranger efforts. This resource scarcity often results in non-systematic patrol strategies, which are sub-optimal given that illegal hunters tend to be selective in where and when they operate.
The situation is poised to become more challenging as countries expand PA coverage under the Kunming-Montreal Global Biodiversity Framework—aiming to increase global PA area from 123 million km2 to 153 million km2 by 2030. Without a substantial boost in enforcement capacity, both existing and newly designated PAs will remain vulnerable. Continued overexploitation of wildlife threatens not only species survival but also ecosystem integrity and the well-being of local communities who rely on wildlife for food and income.
This project aims to combine data from rangers in multiple African protected areas and hunters around a single protected area (Nigeria) to improve the deterrence effect of ranger patrols by optimising ranger efforts and provide information on the economic impacts of improved ranger patrols on community livelihoods and well-being. We plan to deploy our models to rangers in the field via SMART, which is used in > 1000 PAs globally to facilitate monitoring and data collection during patrols.
The two main aims are to:
- develop an accessibility layer using long-term ranger-collected data
- validate the results of this layer, as well as those from other models developed, using ranger insights.
This work involves collaborating with the Wildlife Conservation Society (WCS) Nigeria team and rangers from Cross River National Park—who are already active collaborators in this project. They have provided ranger patrol data, contributed valuable on-the-ground perspectives for interpreting the data, and engaged with preliminary model outputs.
1 Hannah's McLoone in summer 2025
Hannah McLoone spent the summer of 2025 on the first of the two aims, building an accessibility layer from GPS tracks logged by rangers every few minutes on patrol. Two streams of work came out of this. The first is figuring out where the paths are, separating the routes rangers habitually walk from the deviations they make around obstacles or to investigate snares. This began as kernel density estimation over the GPS points and then became a Brownian bridge model, simulating movement between consecutive fixes and summing the resulting densities, with the bridge variance estimated from the observed straightness of the tracks rather than chosen by hand.
The second idea was to map how fast rangers move. The patrol data was stored as a shapefile with no timestamps, and interpolating from the rangers' sparse waypoints would have cost accuracy. Once SMART supplied GPX with full time information, calculating speed followed from the Haversine distance between consecutive fixes.
Predicting that speed surface from landscape covariates proved harder. Population density, elevation, forest condition, water presence and monthly weather were assembled through GEE at 90m, which is the best resolution those layers share. Tree-based methods did pretty ok, which suggests real non-linearity and feature interaction, but a tuned random forest on the full dataset still did not perform well.
Hannah's excellent weekly notes record the first half of the project here. Well done!
- Week 1: identifying footpaths with kernel density estimation
- Week 2: deriving speed from GPX and directional speed maps
- Week 3: landscape features and first predictive models
- Week 4: Brownian bridges and the variance parameter
- Week 5: Earth Engine pipeline, resolution and spatial autocorrelation
- Week 6: variograms for block size, weather data and tuning
2 Smera Sachin in summer 2026
Smera Sachin is picking up where Hannah left off a year later, joining us from Harvard where she is a CS undergrad just finishing her first year.
Rather than one park and rangers alone, her project uses hunter and ranger GPS data from two Nigerian national parks, Okwangwo and Oban, alongside environmental and socioeconomic covariates. Modelling both sides is extremely helpful because deterrence is about where hunters go given where rangers go. We can't easily figure this out from patrol tracks on their own.
More on this as Smera writes up her work later this year!