Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Integrating impacts and cascading hazards to drought monitoring could improve prediction and mitigation of drought events. This Perspective discusses the limitations of existing indicators, the cascading hazards associated with drought and the importance of assessing drought impacts.
Differentiable modelling is an approach that flexibly integrates the learning capability of machine learning with the interpretability of process-based models. This Perspective highlights the potential of differentiable modelling to improve the representation of processes, parameter estimation, and predictive accuracy in the geosciences.
Methods to integrate Earth system modelling (ESM) with deep learning offer promise for advancing understanding of Earth processes. This Perspective explores the development and applications of hybrid Earth system modelling, a framework that integrates neural networks into ESM throughout the modelling lifecycle.
Although model projections indicate increased El Niño/Southern Oscillation (ENSO) variability in the future, contemporary impacts of anthropogenic forcing on ENSO variability have been difficult to ascertain. This Perspective discusses these contemporary effects, outlining that an increase in post-1960 ENSO variability is likely related to greenhouse gas forcing.
Extreme weather and climate events could increase ecosystem disturbances and, potentially, destabilize ecosystems, but different feedbacks between climate and ecosystems are often not accounted for. This Perspective proposes a framework to characterize ecoclimatic events and understand the role of human activities in driving them.