Network science and explainable AI-based life cycle management of sustainability models

• Published in: PloS one 2024-06, Vol.19 (6), p.e0300531
• Main Authors: Ipkovich, Ádám, Czvetkó, Tímea, A Acosta, Lilibeth, Lee, Sanga, Nzimenyera, Innocent, Sebestyén, Viktor, Abonyi, János
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Biology and Life Sciences; Case studies; Changing environments; Computer and Information Sciences; Conservation of Natural Resources - methods; Data analysis; Data science; Decision making; Earth Sciences; Ecology and Environmental Sciences; Economic growth; Environment models; Environmental changes; Explainable artificial intelligence; Fluid dynamics; Forecasts and trends; Humans; Hungary; Intervention; Learning algorithms; Life cycles; Machine Learning; Models, Theoretical; Network analysis; Physical Sciences; Physical simulation; Renewable resources; Research and Analysis Methods; Social networks; Structural equation modeling; Sustainability; Sustainability management; Sustainable Development; Variables; Water resources; Water reuse; Water stress
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0300531

Model-based assessment of the potential impacts of variables on the Sustainable Development Goals (SDGs) can bring great additional information about possible policy intervention points. In the context of sustainability planning, machine learning techniques can provide data-driven solutions throughout the modeling life cycle. In a changing environment, existing models must be continuously reviewed and developed for effective decision support. Thus, we propose to use the Machine Learning Operations (MLOps) life cycle framework. A novel approach for model identification and development is introduced, which involves utilizing the Shapley value to determine the individual direct and indirect contributions of each variable towards the output, as well as network analysis to identify key drivers and support the identification and validation of possible policy intervention points. The applicability of the methods is demonstrated through a case study of the Hungarian water model developed by the Global Green Growth Institute. Based on the model exploration of the case of water efficiency and water stress (in the examined period for the SDG 6.4.1 & 6.4.2) SDG indicators, water reuse and water circularity offer a more effective intervention option than pricing and the use of internal or external renewable water resources.