Home

Over a million species face extinction, highlighting the urgent need for conservation policies that maximize the protection of biodiversity to sustain its manifold contributions to people’s lives. Here we present a novel framework for spatial conservation prioritization based on reinforcement learning that consistently outperforms available state-of-the-art software using simulated and empirical data.

For successful conservation of biodiversity, it is vital to know whether protected areas in increasingly fragmented landscapes effectively safeguard species. However, how large habitat fragments must be, and what level of protection is required to sustain species, remains poorly known. We compiled a global dataset on almost 2000 bird species in 741 forest fragments varying in size and protection status, and show that protection is associated with higher bird occurrence, especially for threatened species. Protection becomes increasingly effective with increasing size of forest fragments.

The ocean contains an abundance of biodiversity that is vital to global food security. However, marine biodiversity is declining. Marine protected areas and marine reserves have been used to protect biodiversity, conserve threatened species and rebuild exploited species, but are perceived as restrictive to fishing, which has slowed progress towards ocean protection targets. Here, we perform a spatial prioritisation of the ocean to protect biodiversity, threatened species and food security.

Deciding when to protect threatened species habitat when complete knowledge about the habitat extent is uncertain is a common problem in conservation. More accurate habitat mapping improves conservation outcomes once that habitat is protected. However, delaying protection to improve accuracy can lead to species decline or, at worst, local extinction when threats to that habitat continue unabated before protection is implemented. Hence, there is a trade-off between gaining knowledge and taking conservation action.