Biodiversity continues to decline and the financing gap over the next ten years is estimated to be significant. Philanthropy and taxpayer funds will be insufficient in addressing the financing gap required to mitigate biodiversity loss. I aim to contribute to addressing this challenge through my work by developing insights about the role of private financing in bridging this financial gap.
I am a member of the cross-faculty working group at the Melbourne Biodiversity Institute, and Chief Investigator at the Centre for Nature-Positive Climate Transitions.
with Samuel Hickman, Matthew Cantele, Monika Dyndo, Jennifer Willetts, Rachel Morgain, William Geary, and Brendan Wintle
Under review
Business activity drives economic prosperity but can also degrade biodiversity, imposing regulatory, reputational, and operational risks. Under Global Biodiversity Framework Target 15, large and transnational companies must disclose nature-related financial risks, prompting investors to adopt emerging biodiversity impact software tools. We compare eight widely used tools via methodological review and analysis of impact ratings for a sample of 500 large publicly traded U.S. companies. We demonstrate that rankings of company impact exhibit low correlation between most tools. These tools rely on non-standardized methodologies and workflows that lack clear theoretical foundation, peer-review and scrutiny. Modelling assumptions often appear disconnected from actual onground or supply chain impacts. We conclude that reliance on any single tool may lead to investment decisions that fail to adequately mitigate risk or reflect investor preferences. Reliable nature impact assessment in finance requires more transparent, spatially explicit methodologies, supported by improved corporate disclosures.
Decision-Making Under Complexity Environmental and Social Risk
with Sarah Bekessy, Mark Burgman, William Geary, Oğuzhan Karakaş, Hannah Layman, Annalisa Tonetto, and Brendan Wintle
Biodiversity loss poses significant risks to investment portfolios, yet these risks remain largely underexplored in financial decision-making. This paper highlights the need for the development and use of robust metrics to measure the impacts and dependencies of firms on biodiversity. We find that current approaches to measuring a firm's impact on nature suffer from several shortcomings. These include incomplete data on firm activities, supply chains, and natural systems. In addition, many impact modeling and assessment methodologies are inconsistent, and in some cases, incoherent. There has been limited testing of the reliability of nature impact and dependency assessment tools in real-world investment settings. Finally, there is a lack of understanding among business and finance actors about how these tools work and how to interpret their outputs. We propose integrating spatially explicit and ecologically grounded metrics into firm valuation models to improve the assessment of biodiversity-related risks. This approach enables investors to identify underpriced risks and generate returns exceeding benchmark performance by aligning portfolios with sustainability goals. By bridging the gap between ecological science and finance, we provide actionable insights to reduce risks and thereby enhance portfolio performance while addressing critical biodiversity challenges.
Decision-Making Under Complexity Environmental and Social Risk
with Robert Turnbull, Damien J. Mannion, Jessie Wells, Kabir Manandhar Shrestha, Rebecca Runting
Accepted in the Journal of Remote Sensing
Accurate land cover change prediction is vital for informed land management, and deep learning offers a flexible solution capable of capturing complex ecological patterns. This paper presents Themeda, a modeling framework using artificial neural networks that predict land cover category probability distributions based on historical data. It integrates ConvLSTM and a novel Temporal U-Net architecture, extending the U-Net with LSTM layers for multi-scale temporal processing, enabling fine-grained local and broader spatial pattern capture. Leveraging 33 years of historical data from the world's largest intact savanna, Themeda incorporates diverse spatio-temporal features like rainfall, temperature, elevation, soil types, land use, and fire scars. Themeda overcomes limitations of current spatio-temporal models by processing temporal data at multiple spatial scales, capturing local and regional ecological changes effectively. It achieves a 93.4% pixel-wise validation accuracy on FAO Level 3 classes and a KL divergence of 1.65e-03 for aggregated land cover predictions in 4000 m x 4000 m areas, surpassing baseline persistence models. The model maintains high performance on unseen test years, demonstrating robust generalizability. The probabilistic outputs and multi-scale temporal processing have significant implications for enhancing cellular automata and land use planning models and could be adapted for ecological forecasting in other regions.
Decision-Making Under Complexity Environmental and Social Risk
Review of nature-related financial disclosures, materiality assessment process and outcomes (for a commercial bank), with Billy Geary, Sam Hickman, Rachel Morgain, Dale Wright, Hendri Wijaya, Brendan Wintle
Evaluating Biodiversity Impact Assessment Tools for Financial Institutions: A Comprehensive Review (for a global investment manager), with Matthew Cantele, Lakshmi Palaparambil Dinesh, Billy Geary, Sam Hickman, Brendan Wintle