As climate change intensifies extreme heat, increases natural hazards and accelerates ecological decline, cities around the world are facing environmental pressure, creating an urgent need for climate-adaptive and data-driven landscape planning. Recent advances in earth observation and artificial intelligence (AI) now enable ecological and microclimatic processes to be analyzed at high spatial and temporal resolution, opening new pathways for evidence-basedlandscape strategies. However, despite rapid technological progress, it remains unclear how AI and data-driven methodologies can be operationalized within real-world planning to address climate-induced pressures at meaningful spatial scales. Focusing on the metropolitan context of Riyadh, Saudi Arabia, as a rapidly urbanizing city exposed to extreme climatic stress, our latest research shows that AI-enabled and data-driven landscape analytics enhance climate-adaptive planning by translating diffuse environmental signals into actionable design knowledge. Using the emerging frameworks UrbAlytics for remote-sensing-based environmental assessment, nAIture for nature-centered landscape modelling and LIM landscape information modelling®, we show how suchframeworkscouldenhance early detection of microclimatic stress, refine vegetation and land-cover diagnostics, and supportbetter informed, scenario-based design of green-infrastructure interventions. These applications support differentiated risk diagnostics, canopy-performance estimation, and microclimate-responsive spatial strategies. Taken together, these findings show that AI and data-driven models offer immediate opportunities to raise analytical precision, accelerate planning timelines and support more resilient, nature-positive and climate-adaptive urban landscapes when embedded in interdisciplinary expertise and critically interpreted.
Meißner et al. (Thu,) studied this question.