Forecasting future states of the environment with machine learning: a case study on water scarcity

Journal of Industrial Ecology, vol. 30, pp. 1285–1298

Abstract

Recent research has emphasized the need to adapt life cycle inventories and life cycle impact assessments to account for changes in future scenarios. This is mostly achieved by using Integrated Assessment Models (IAMs), which combine environmental and economic data to develop prospective life cycle inventories (LCIs). However, running complex IAMs to simulate scenarios is computationally expensive, and the resulting data is not always aligned with the geographical scope of background inventories. This study explores the potential of machine learning (ML) to create prospective water-scarcity characterisation factors by forecasting the AWARE factor for ~ 9700 watersheds globally. Historical time series of water-scarcity characterisation factors are generated using the global freshwater model WaterGAP v2.2d and the AWARE method. Several ML models are trained on these historical datasets and benchmarked using symmetric mean absolute percentage error (sMAPE). The best-performing model, N-Beats, is then used to forecast AWARE values through 2032. The results demonstrate that ML can produce spatially and temporally explicit forecasts with reasonable accuracy (median sMAPE ~ 28%). However, the models primarily capture seasonal patterns rather than long-term structural trends and the results are sensitive to the quality and representativeness of the training data. This study highlights both the potential and the limitations of time series forecasting for developing prospective characterisation factors in life cycle assessment. Graphical abstract

Authors 7

1. Niklas Engberg corresponding

   Delft University of Technology

   Affiliation as printed

   Faculty of Industrial Design Engineering, Delft University of Technology, Delft, The Netherlands

2. Carlos Felipe Blanco corresponding Aachen Institute of Environmental Sciences (CML)

   Leiden University · Netherlands Organisation for Applied Scientific Research

   Affiliation as printed

   Circularity and Sustainability Impact Group, Netherlands Organisation for Applied Scientific Research (TNO), Utrecht, The Netherlands

   Institute of Environmental Sciences (CML), Leiden University, Leiden, The Netherlands

3. Valerio Barbarossa corresponding Aachen Institute of Environmental Sciences (CML)

   Leiden University · Netherlands Environmental Assessment Agency

   Affiliation as printed

   Global Sustainability, PBL Netherlands Environmental Assessment Agency, The Hague, The Netherlands

   Institute of Environmental Sciences (CML), Leiden University, Leiden, The Netherlands

4. Conny A. Bakker corresponding

   Delft University of Technology

   Affiliation as printed

   Faculty of Industrial Design Engineering, Delft University of Technology, Delft, The Netherlands

5. Ruud Balkenende corresponding

   Delft University of Technology

   Affiliation as printed

   Faculty of Industrial Design Engineering, Delft University of Technology, Delft, The Netherlands

6. Justin Z. Lian corresponding Aachen Institute of Environmental Sciences (CML)

   Leiden University

   Affiliation as printed

   Institute of Environmental Sciences (CML), Leiden University, Leiden, The Netherlands

7. Benjamin Sprecher corresponding

   Delft University of Technology

   Affiliation as printed

   Faculty of Industrial Design Engineering, Delft University of Technology, Delft, The Netherlands