English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Increasingly complex, non-linear World-Earth system models are used fordescribing the dynamics of the biophysical Earth system and the socio-economicand socio-cultural World of human societies and their interactions. Identifyingpathways towards a sustainable future in these models for informing policymakers and the wider public, e.g. pathways leading to a robust mitigation ofdangerous anthropogenic climate change, is a challenging and widelyinvestigated task in the field of climate research and broader Earth systemscience. This problem is particularly difficult when constraints on avoidingtransgressions of planetary boundaries and social foundations need to be takeninto account. In this work, we propose to combine recently developed machinelearning techniques, namely deep reinforcement learning (DRL), with classicalanalysis of trajectories in the World-Earth system. Based on the concept of theagent-environment interface, we develop an agent that is generally able to actand learn in variable manageable environment models of the Earth system. Wedemonstrate the potential of our framework by applying DRL algorithms to twostylized World-Earth system models. Conceptually, we explore thereby thefeasibility of finding novel global governance policies leading into a safe andjust operating space constrained by certain planetary and socio-economicboundaries. The artificially intelligent agent learns that the timing of aspecific mix of taxing carbon emissions and subsidies on renewables is ofcrucial relevance for finding World-Earth system trajectories that aresustainable on the long term.

Deep reinforcement learning in World-Earth system models to discover sustainable management strategies