<p>Demand for applying ES models in decision-making has increased across the world. However, despite advances in modelling approaches for ES, adopting either discipline-specific models or more holistic multi-ES models is time and data intensive, especially in data sparse areas and areas where ES modelling has not been well established. Many of the main challenges are rooted in model parameters/assumptions and processes biased to specific ecosystem, policy, and data contexts for which ES models were initially developed or established. ES modelling, therefore, needs to be improved to cover wider ecosystem, policy, and data conditions, and fast enough for use during decision-making timeframes. The aim of this research is to facilitate ES model parameterisation and adaptation to enhance ES model applicability, especially in data sparse areas and areas where ES modelling has not been well established. It will ultimately reduce efforts required to produce ES modelling and assessments.</p>