Machine learning for ecosystem services

Abstract Recent developments in machine learning have expanded data-driven modelling (DDM) capabilities, allowing artificial intelligence to infer the behaviour of a system by computing and exploiting correlations between observed variableswithin it. Machine learning algorithms may enable the use of increasingly available ‘big data’ and assist applying ecosystem servicemodels across scales, analysing and predicting the flows of these services to disaggregated beneficiaries. We use the Weka and ARIES software to produce two examples of DDM: firewooduse in South Africa and biodiversity value in Sicily, respectively. Our South African example demonstrates that DDM (64–91% accuracy) can identify the areas where firewooduse is within the top quartile with comparable accuracy as conventional modelling techniques (54–77% accuracy). The Sicilianexample highlights how DDM can be made more accessible to decision makers, who show both capacity and willingness to engage with uncertainty information. Uncertainty estimates, produced as part of the DDM process, allow decision makers to determine what level of uncertainty is acceptable to them and to use their own expertise for potentially contentious decisions. We conclude that DDM has a clear role to play when modelling ecosystem services, helping produce interdisciplinary models and holistic solutions to complex socio-ecological issues.