About

We aim to harness the big data and the AI revolution to develop innovative technological approaches to assess nature recovery in both fine detail and at large spatial scales.

We are in the midst of an exponential proliferation of data about our environment from sources as varied as a new generation of satellite sensors, social media posts and time-lapse cameras with image recognition. In concert with this data richness, there is immense potential to use AI/machine learning to fuse, interpret and correlate data to work at both fine spatial resolution and large spatial scale in the midst of significant complexity.

For the first time we have the potential to map and model ecological connectivity across whole countries, map different farming approaches or infrastructure in fine detail and track the connectivity of biodiversity associated with different farming landscapes. We will advance state-of-the-art AI approaches to combine different sources of data, including drones, satellite, survey data and social media, that are robust to a range of environmental scenarios, data noise and model reliability.

We will initially focus on three machine learning tasks to address the information requirements of our programmes:

  • The exploitation of existing machine learning technology and subsequent identification and filling of methodological gaps
  • Novel methods for data interpretation
  • Requirements for hardware, imagery and human intervention for cost-efficient, scalable data analytics.

Projects

Theme outputs

    Huanyuan Zhang-Zheng, Stephen Adu-Bredu, Akwasi Duah-Gyamfi, Sam Moore, Shalom D. Addo-Danso, Lucy Amissah, Riccardo Valentini, Gloria Djagbletey, Kelvin Anim-Adjei, John Quansah, Bernice Sarpong, Kennedy Owusu-Afriyie, Agne Gvozdevaite, Minxue Tang, Maria C. Ruiz-Jaen, Forzia Ibrahim, Cécile A. J. Girardin, Sami Rifai, Cecilia A. L. Dahlsjö, Terhi Riutta, Xiongjie Deng, Yuheng Sun, Iain Colin Prentice, Imma Oliveras Menor & Yadvinder Malhi (2024). Contrasting carbon cycle along tropical forest aridity gradients in West Africa and Amazonia. Nature Communications.

    Here we present a detailed field assessment of the carbon budget of multiple forest sites in Africa, by monitoring 14 one-hectare plots along an aridity gradient in Ghana, West Africa. When compared with an equivalent aridity gradient in Amazonia, the studied West African forests generally had higher productivity and lower carbon use efficiency (CUE). The West African aridity gradient consistently shows the highest NPP, CUE, GPP, and autotrophic respiration at a medium-aridity site, Bobiri. Notably, NPP and GPP of the site are the highest yet reported anywhere for intact forests. Widely used data products substantially underestimate productivity when compared to biometric measurements in Amazonia and Africa. Our analysis suggests that the high productivity of the African forests is linked to their large GPP allocation to canopy and semi-deciduous characteristics.

    Publications
    LCNR supported
    • Society
    • Scale
    • Remote sensing

    Jesús Aguirre-Gutiérrez, Nicola Stevens, Erika Berenguer (2023). Valuing the functionality of tropical ecosystems beyond carbon. Trends in Ecology & Evolution.

    Land-based carbon sequestration projects, such as tree planting, are a prominent strategy to offset carbon emissions. However, we risk reducing natural ecosystems to one metric – carbon. Emphasis on restoring ecosystems to balance ecosystem services, biodiversity conservation, and carbon sequestration is a more appropriate strategy to protect their functioning.

    Publications
    LCNR supported
    • Scale
    • Remote sensing

    Aguirre‐Gutiérrez, Jesús, et al. (2019). Drier tropical forests are susceptible to functional changes in response to a long‐term drought. Ecology Letters 22.5: 855-865.

    Publications
    LCNR associated
    • Scale
    • Remote sensing
See all outputs for this theme