Search for: All records

Large, well described gaps exist in both what we know and what we need to know to address the biodiversity crisis. Artificial intelligence (AI) offers new potential for filling these knowledge gaps, but where the biggest and most influential gains could be made remains unclear. To date, biodiversity-related uses of AI have largely focused on tracking and monitoring of wildlife populations. Rapid progress is being made in the use of AI to build phylogenetic trees and species distribution models. However, AI also has considerable unrealized potential in the re-evaluation of important ecological questions, especially those that require the integration of disparate and inherently complex data types, such as images, video, text, audio and DNA. This Review describes the current and potential future use of AI to address seven clearly defined shortfalls in biodiversity knowledge. Recommended steps for AI-based improvements include the re-use of existing image data and the development of novel paradigms, including the collaborative generation of new testable hypotheses. The resulting expansion of biodiversity knowledge could lead to science spanning from genes to ecosystems — advances that might represent our best hope for meeting the rapidly approaching 2030 targets of the Global Biodiversity Framework. 

Abstract Following the failure to fully achieve any of the 20 Aichi biodiversity targets, the future of biodiversity rests in the balance. The Convention on Biological Diversity's Kunming–Montreal Global Biodiversity Framework (GBF) presents the opportunity to preserve nature's contributions to people (NCPs) for current and future generations by conserving biodiversity and averting extinctions. There is a need to safeguard the tree of life—the unique and shared evolutionary history of life on Earth—to maintain the benefits it bestows into the future. Two indicators have been adopted within the GBF to monitor progress toward safeguarding the tree of life: the phylogenetic diversity (PD) indicator and the evolutionarily distinct and globally endangered (EDGE) index. We applied both to the world's mammals, birds, and cycads to show their utility at the global and national scale. The PD indicator can be used to monitor the overall conservation status of large parts of the evolutionary tree of life, a measure of biodiversity's capacity to maintain NCPs for future generations. The EDGE index is used to monitor the performance of efforts to conserve the most distinctive species. The risk to PD of birds, cycads, and mammals increased, and mammals exhibited the greatest relative increase in threatened PD over time. These trends appeared robust to the choice of extinction risk weighting. EDGE species had predominantly worsening extinction risk. A greater proportion of EDGE mammals (12%) had increased extinction risk compared with threatened mammals in general (7%). By strengthening commitments to safeguarding the tree of life, biodiversity loss can be reduced and thus nature's capacity to provide benefits to humanity now and in the future can be preserved. 

Networks of species interactions underpin numerous ecosystem processes, but comprehensively sampling these interactions is difficult. Interactions intrinsically vary across space and time, and given the number of species that compose ecological communities, it can be tough to distinguish between a true negative (where two species never interact) from a false negative (where two species have not been observed interacting even though they actually do). Assessing the likelihood of interactions between species is an imperative for several fields of ecology. This means that to predict interactions between species—and to describe the structure, variation, and change of the ecological networks they form—we need to rely on modelling tools. Here, we provide a proof-of-concept, where we show how a simple neural network model makes accurate predictions about species interactions given limited data. We then assess the challenges and opportunities associated with improving interaction predictions, and provide a conceptual roadmap forward towards predictive models of ecological networks that is explicitly spatial and temporal. We conclude with a brief primer on the relevant methods and tools needed to start building these models, which we hope will guide this research programme forward. This article is part of the theme issue ‘Infectious disease macroecology: parasite diversity and dynamics across the globe’.