Recent evaluations of the current state of the Earth system (e.g., the latest assessment of the nine Planetary Boundaries) emphasize the alarming decline in Earth’s resilience, stability, and life-support systems. Human activities are driving us beyond critical planetary boundaries, marking the onset of the Anthropocene, in which humanity has become a geological force that is significantly altering global processes and environments. Earth’s stability depends on complex, non-linear interactions between biophysical processes and human influences. These include the carbon cycle, atmospheric dynamics, oceans, large ecosystems, the cryosphere, and disruptions driven by socio-economic pressures. As these pressures grow, the risk of breaching self-regulating feedbacks in the Earth system increases, raising the likelihood that critical components such as large ice sheets, the Atlantic Meridional Overturning Circulation, and biomes like the Amazon rainforest could be pushed beyond tipping points. Such shifts may trigger abrupt, large-scale, and potentially irreversible changes that threaten ecosystems and human societies alike. To address this challenge, frequent and comprehensive assessments of planetary boundaries are needed. For this, we could leverage recent technological advances in Earth observation and AI-based solutions, such as large language models and geospatial foundation models. However, efficiently and effectively deploying these techniques requires expertise across various domains, including geosciences, remote sensing, data science, socio-environmental sciences, and related disciplines. This session invites contributions from geoscientists, climate modelers, remote sensing specialists, ecologists, and data scientists to explore how planetary boundaries can be more effectively measured and assessed. We aim to foster interdisciplinary collaboration to identify critical thresholds, understand feedback mechanisms, and quantify resilience at planetary scales. We welcome diverse methods, from Earth system modeling and remote sensing to data-driven analyses and conceptual frameworks, with particular interest in work on stability indicators, non-linear feedbacks, and cascading system-wide effects.