15 March 2025 in Nature Communications
As climate change accelerates, human societies face growing exposure to disasters and stress, highlighting the urgent need for effective early warning systems (EWS). These systems monitor, assess, and communicate risks to support resilience and sustainable development, but challenges remain in hazard forecasting, risk communication, and decision-making. This perspective explores the transformative potential of integrated Artificial Intelligence (AI) modeling. We highlight the role of AI in developing multi-hazard EWSs that integrate Meteorological and Geospatial foundation models (FMs) for impact prediction. A user-centric approach with intuitive interfaces and community feedback is emphasized to improve crisis management. To address climate risk complexity, we advocate for causal AI models to avoid spurious predictions and stress the need for responsible AI practices. We highlight the FATES (Fairness, Accountability, Transparency, Ethics, and Sustainability) principles as essential for equitable and trustworthy AI-based Early Warning Systems for all. We further advocate for decadal EWSs, leveraging climate ensembles and generative methods to enable long-term, spatially resolved forecasts for proactive climate adaptation.
8 March 2024 in Global Change Biology
Wood density is a fundamental property related to tree biomechanics and hydraulic function while playing a crucial role in assessing vegetation carbon stocks by linking volumetric retrieval and a mass estimate. This study provides a high‐resolution map of the global distribution of tree wood density at the 0.01° (~1 km) spatial resolution, derived from four decision trees machine learning models using a global database of 28,822 tree‐level wood density measurements. An ensemble of four top‐performing models combined with eight cross‐validation strategies shows great consistency, providing wood density patterns with pronounced spatial heterogeneity. The global pattern shows lower wood density values in northern and northwestern Europe, Canadian forest regions and slightly higher values in Siberia forests, western United States, and southern China. In contrast, tropical regions, especially wet tropical areas, exhibit high wood density. Climatic predictors explain 49%–63% of spatial variations, followed by vegetation characteristics (25%–31%) and edaphic properties (11%–16%). Notably, leaf type (evergreen vs. deciduous) and leaf habit type (broadleaved vs. needleleaved) are the most dominant individual features among all selected predictive covariates. Wood density tends to be higher for angiosperm broadleaf trees compared to gymnosperm needleleaf trees, particularly for evergreen species. The distributions of wood density categorized by leaf types and leaf habit types have good agreement with the features observed in wood density measurements. This global map quantifying wood density distribution can help improve accurate predictions of forest carbon stocks, providing deeper insights into ecosystem functioning and carbon cycling such as forest vulnerability to hydraulic and thermal stresses in the context of future climate change.
26 January 2024 in Environmental Research Letters
The Amazon rainforest is considered one of the Earth’s tipping elements and may lose stability under ongoing climate change. Recently a decrease in tropical rainforest resilience has been identified globally from remotely sensed vegetation data. However, the underlying theory assumes a Gaussian distribution of forest disturbances, which is different from most observed forest stressors such as fires, deforestation, or windthrow. Those stressors often occur in power-law-like distributions and can be approximated by α-stable Lévy noise. Here, we show that classical critical slowing down (CSD) indicators to measure changes in forest resilience are robust under such power-law disturbances. To assess the robustness of CSD indicators, we simulate pulse-like perturbations in an adapted and conceptual model of a tropical rainforest. We find few missed early warnings and few false alarms are achievable simultaneously if the following steps are carried out carefully: first, the model must be known to resolve the timescales of the perturbation. Second, perturbations need to be filtered according to their absolute temporal autocorrelation. Third, CSD has to be assessed using the non-parametric Kendall-τ slope. These prerequisites allow for an increase in the sensitivity of early warning signals. Hence, our findings imply improved reliability of the interpretation of empirically estimated rainforest resilience through CSD indicators.
25 January 2025 in Scientific Data
With climate extremes’ rising frequency and intensity, robust analytical tools are crucial to predict their impacts on terrestrial ecosystems. Machine learning techniques show promise but require well-structured, high-quality, and curated analysis-ready datasets. Earth observation datasets comprehensively monitor ecosystem dynamics and responses to climatic extremes, yet the data complexity can challenge the effectiveness of machine learning models. Despite recent progress in deep learning to ecosystem monitoring, there is a need for datasets specifically designed to analyse compound heatwave and drought extreme impact. Here, we introduce the DeepExtremeCubes database, tailored to map around these extremes, focusing on persistent natural vegetation. It comprises over 40,000 globally sampled small data cubes (i.e. minicubes), with a spatial coverage of 2.5 by 2.5 km. Each minicube includes (i) Sentinel-2 L2A images, (ii) ERA5-Land variables and generated extreme event cube covering 2016 to 2022, and (iii) ancillary land cover and topography maps. The paper aims to (1) streamline data accessibility, structuring, pre-processing, and enhance scientific reproducibility, and (2) facilitate biosphere dynamics forecasting in response to compound extremes.
13 February 2025 in Journal of Advances in Modeling Earth Systems
Accurately describing the distribution of in the atmosphere with atmospheric tracer transport models is essential for greenhouse gas monitoring and verification support systems to aid implementation of international climate agreements. Large deep neural networks are poised to revolutionize weather prediction, which requires 3D modeling of the atmosphere. While similar in this regard, atmospheric transport modeling is subject to new challenges. Both, stable predictions for longer time horizons and mass conservation throughout need to be achieved, while IO plays a larger role compared to computational costs. In this study we explore four different deep neural networks (UNet, GraphCast, Spherical Fourier Neural Operator and SwinTransformer) which have proven as state‐of‐the‐art in weather prediction to assess their usefulness for atmospheric tracer transport modeling. For this, we assemble the CarbonBench data set, a systematic benchmark tailored for machine learning emulators of Eulerian atmospheric transport. Through architectural adjustments, we decouple the performance of our emulators from the distribution shift caused by a steady rise in atmospheric . More specifically, we center input fields to zero mean and then use an explicit flux scheme and a mass fixer to assure mass balance. This design enables stable and mass conserving transport for over 6 months with all four neural network architectures. In our study, the SwinTransformer displays particularly strong emulation skill: 90‐day and physically plausible multi‐year forward runs. This work paves the way toward high resolution forward and inverse modeling of inert trace gases with neural networks.