Biodiversity monitoring and forecasting

How can we best catalyse and champion the development of new AI and data-driven methods for monitoring and forecasting biodiversity change?


Rapid and severe biodiversity loss has been associated with chemical pollution, habitat loss, unsustainable use of resources, invasive species, and climate change on a global scale. Severe biodiversity decline poses serious threats to environmental and human health, socio-economic wellbeing, and food security. Conservation efforts have historically focused on species-centric ecological surveys that require specialist skills, are low throughput, and are not representative of ecosystem-level changes. Inadequate monitoring and forecasting of biodiversity loss in the face of multiple threats is becoming a bottleneck to the formulation and implementation of strategies to mitigate and reverse biodiversity loss. The Biodiversity monitoring and forecasting interest group will meet these challenges by leveraging the expertise of the Turing network, and co-developing with stakeholders, high throughput systemic AI-powered approaches for monitoring and forecasting biodiversity change.

Explaining the science

Anthropogenic climate change, combined with land use changes and other causes, is increasingly impacting the composition and distribution of our ecosystems. The resulting significant decline in global biodiversity is resulting in severe impacts to natural resources, food security, and is degrading important ecosystem services that are vital to human health. Without any intervention, current projections show continuing and even accelerating species extinctions, loss of habitats, and changes in the distribution and abundance of species populations over the next century.  

Conservation and management strategies that maintain and restore biodiversity can help to reduce some of the negative impacts of climate change. However, in order to develop the necessary resilience, we need a better understanding of how biodiversity is changing at both a global and local scale. This requires developing robust and distributed approaches for performing biodiversity monitoring and forecasting at an unprecedented spatial and temporal scale. AI-powered solutions, coupled with new techniques and tools for large-scale data collection, offer the potential to fill this gap.  


  • Promote and closely align to the Turing’s goals of developing and advancing the integration of AI and data science into solutions for real-world problems facing humanity. 
  • Bring together cross-disciplinary expertise to identify opportunities and methodology for addressing the urgent needs for powerful AI and data science tools in biodiversity, conservation, and habitat monitoring. 
  • Become a recognised body of excellence uniting national expertise in tackling a suite of data-driven biodiversity problems. 
  • Identify and help foster interdisciplinary funding streams, grant opportunities, and collaborations within the remit of the interest group and beyond.

How to get involved

Click here to request sign-up and join

Talking points

How can new advances in AI assist faster and smarter data collection, result in more accurate and powerful analysis methods, and provide better predictive power to guide interventions and policy changes in the context of biodiversity monitoring and forecasting? 

Questions of interest include, but are not limited to, the following: 


  • Smart sensors and edge computing hardware to monitor organismal behaviour and habitats  
  • Machine learning methods for automated identification of species from images, video, and sound 
  • Integrating human observation data and high throughput sequencing technologies 
  • Inference of local biodiversity from proxy data for business applications  
  • Data processing and inference methods to interpolate between observations in sparse datasets  
  • Tools for data visualisation, interaction, and dashboarding 


  • Novel methods for forecasting of population time series 
  • Methods to measure spatio-temporal inter-specific interactions from observation data, integrating priors from other observations 
  • Prediction of species ranges and abundances  
  • Monitoring changes in migratory patterns  
  • Prediction of extinction risks  
  • Predictive models for ecological/biodiversity indicators  
  • Predictions of spread of biodiversity hazards  

Contact info

[email protected]