Using artificial intelligence to optimize ecological restoration for climate and biodiversity

The restoration of degraded ecosystems can provide critical contributions to help mitigate climate change and bend the curve of biodiversity loss. Depending on the primary objective - such as maximizing carbon storage or protecting threatened species - and within the boundaries of budget constraints, different spatial priorities have been identified at global and regional levels. Funding mechanisms to support such work comprise public sources, philanthropy, and the private sector, including the sales of carbon and biodiversity credits. However, effectively exploring tradeoffs between restoration objectives and estimating the price of biodiversity and carbon credits to design financially viable projects remain challenging. Here we harness the power of artificial intelligence in our software CAPTAIN, which we further develop to identify spatial priorities for ecological restoration that maximize multiple objectives at once and which allows a robust evaluation of biodiversity and climate outcomes. We find through a series of realistic simulations that even low-to-moderate consideration of biodiversity in restoration projects leads to the selection of restored areas that substantially improve the conservation of threatened species, although this can result in a decrease in total carbon captured. We propose a data-driven valuation of biodiversity credits in relation to carbon credits, enabling the design of a blended financial model that could support restoration efforts even in areas previously excluded for economic reasons. This study shows how the use of a robust methodological framework can lead to significant improvements in outcomes for climate and nature, while minimizing costs.