Towards globally customizable ecosystem service models
Scientists, stakeholders and decision makers face trade-offs between adopting simple or complex approaches when modeling ecosystem services (ES). Complex approaches may be time- and data-intensive, making them more challenging to implement and difficult to scale, but can produce more accurate and locally specific results. In contrast, simple approaches allow for faster assessments but may sacrifice accuracy and credibility. The ARtificial Intelligence for Ecosystem Services (ARIES) modeling platform has endeavored to provide a spectrum of simple to complex ES models that are readily accessible to a broad range of users. In this paper, we describe a series of five Tier 1 ES models that users can run anywhere in the world with no user input, while offering the option to easily customize models with context-specific data and parameters. This approach enables rapid ES quantification, as models are automatically adapted to the application context. We provide examples of customized ES assessments at three locations on different continents and demonstrate the use of ARIES’ spatial multi-criteria analysis module, which enables spatial prioritization of ES for different beneficiary groups. The models described here use publicly available global- and continental-scale data as defaults. Advanced users can modify data input requirements, model parameters or entire model structures to capitalize on high-resolution data and context-specific model formulations. Data and methods contributed by the research community become part of a growing knowledge base, enabling faster and better ES assessment for users worldwide. By engaging with the ES modeling community to further develop and customize these models based on user needs, spatiotemporal contexts, and scale(s) of analysis, we aim to cover the full arc from simple to complex assessments, minimizing the additional cost to the user when increased complexity and accuracy are needed.
J. Martínez-López, K. J. Bagstad, S. Balbi, A. Magrach, B. Voigt, I. N. Athanasiadis, M. Pascual, S. Willcock, F. Villa, Towards globally customizable ecosystem service models, Science of the Total Environment, 650:2325-2336, 2019, doi:10.1016/j.scitotenv.2018.09.371.
You might also enjoy (View all publications)
- A weakly supervised framework for high-resolution crop yield forecasts
- Learning latent representations for operational nitrogen response rate prediction
- Simulation-assisted machine learning for operational digital twins