arXiv subjects

Reto Knutti

Publications and source records attributed to Reto Knutti.

11 recordsLinked to original sources

arXiv2026

Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models

Machine-learning weather models (MLWMs) now match or outperform operational numerical weather prediction (NWP) at global medium-range forecasting, at far lower inference cost. Many deployed MLWMs are deterministic, producing a single forecast with no estimate of its own uncertainty, whereas a growing family of trained-probabilistic models generate calibrated ensembles directly, at the price of a dedicated training run. We ask instead how much uncertainty can be extracted from a deterministic checkpoint that already exists, without retraining it. Where physical ensembles represent model uncertainty by stochastically perturbing parametrisation tendencies, we perturb the network's raw weight tensors at inference time, a scheme we call stochastically perturbed weights (SPW). We also ask whether it works, where and on which scales to inject the noise, and where it fails. A three-phase ablation across four deterministic backbones, Aurora, GraphCast, SFNO, and AIFS, selects one production baseline per model, benchmarked against the trained-probabilistic AIFS-ENS, FourCastNet 3 and Atlas as well as the operational ECMWF ensemble (IFS-ENS) over 112 initialisation times. At a 240 h (10-day) lead time the SPW ensembles reach continuous ranked probability skill scores (CRPSS) between 0.04 and 0.13 below the best trained-probabilistic baseline, at zero marginal training cost. No injection site works across models: the productive tensor group is architecture-specific, so SPW is at present a tuning procedure rather than a plug-and-play recipe. Its main failure mode is a coherent whole-field offset that overdisperses the domain mean, and restricting the noise to coarse scales or perturbing the initial conditions each repair part of it.

cs.LG↗

arXiv2026

Statistical Noise and Missing Forcing Limit Estimates of Earth's Feedback from Prescribed Sea-Surface Temperature Simulations

Earth's feedback parameter measures how the Earth system responds to forcing and is inversely proportional to climate sensitivity. Sea-surface temperature (SST) patterns can modulate the value of the feedback parameter. Differences between observed and simulated SSTs have raised the question how the observed SSTs evolution impacts the global feedback. The standard method for estimating this effect uses observed SSTs prescribed to an atmospheric model with fixed pre-industrial atmospheric forcing. This method makes two assumptions: first, that the observed SSTs capture all relevant effects from the forcing, so that prescribing a time-varying forcing is unnecessary; second, that the temporal variations in the feedback parameter are driven by the evolving SST pattern and can be estimated via moving-window regressions. We test these assumptions by running controlled experiments in which SSTs from fully-coupled historical simulations are prescribed to an atmospheric model. We find that the prescribed-SST experiments fail to capture the coupled feedback evolution. This is explained by two effects: First, the absence of prescribed atmospheric forcing, and second, statistical noise arising from the computation of moving-window regressions. We find no evidence of any significant relationship between evolving SST patterns and changes in the feedback time series in a 4000-year pre-industrial control simulation. Any trends in the feedback parameter detected on timescales shorter than ~100 years are indistinguishable from statistical noise, making their attribution to the evolving SST pattern extremely difficult. Our results imply that prescribed SST simulations offer limited potential for inferring temporal changes in Earth's parameter over the observational period.

physics.ao-ph↗

arXiv2026

Uncertainty in wind and solar projections depends on global and regional climate models

Ensembles of regional-global climate model combinations show substantial spread in projected wind and solar resources. Using 31 RCM-GCM pairs, we quantify the sources of this spread with a spatially and seasonally resolved variance decomposition, separating contributions from RCMs and GCMs. For both wind speed and solar radiation, RCMs dominate the variability in the absolute historical fields. In contrast, projected changes in wind speed are largely controlled by the driving GCMs, except in mountainous regions where RCM-induced variance becomes larger than that induced by GCMs. For solar radiation, contributions are strongly season-dependent, with RCMs dominating in summer and GCMs in winter. Our findings support that GCM and RCM variability together define the uncertainty of wind and solar climate projections. This provides guidance for designing climate model ensembles that better support uncertainty-aware energy system decisions under climate change.

physics.ao-ph↗

arXiv2026

AI-Assisted Scientific Assessment: A Case Study on Climate Change

The emerging paradigm of AI co-scientists focuses on tasks characterized by repeatable verification, where agents explore search spaces in 'guess and check' loops. This paradigm does not extend to problems where repeated evaluation is impossible and ground truth is established by the consensus synthesis of theory and existing evidence. We evaluate a Gemini-based AI environment designed to support collaborative scientific assessment, integrated into a standard scientific workflow. In collaboration with a diverse group of 13 scientists working in the field of climate science, we tested the system on a complex topic: the stability of the Atlantic Meridional Overturning Circulation (AMOC). Our results show that AI can accelerate the scientific workflow. The group produced a comprehensive synthesis of 79 papers through 104 revision cycles in just over 46 person-hours. AI contribution was significant: most AI-generated content was retained in the report. AI also helped maintain logical consistency and presentation quality. However, expert additions were crucial to ensure its acceptability: less than half of the report was produced by AI. Furthermore, substantial oversight was required to expand and elevate the content to rigorous scientific standards.

cs.CL↗

arXiv2025

Climate change impacts on net load under technological uncertainty in European power systems

Renewable energy sources play a major role in future net-zero energy systems. However, achieving energy system resilience remains challenging, since renewables depend on weather fluctuations, and future energy systems are subject to major design uncertainty. Existing literature mostly treats these types of uncertainty separately. Therefore, the assessment of uncertainties surrounding climate change and energy system design, and particularly their interactions, is insufficiently understood. To close this gap, we evaluate net load to assess energy system stress without relying on perfect foresight, while maintaining temporal and spatial correlations of the climate system. Net load is calculated from hourly historical and future climate model data translated to energy variables. To scope the extent of plausible energy systems, we consider eight different design scenarios inspired by the European Ten-Year Network Development Plan (TYNDP) and different levels of transmission expansion. We find that climate change impacts on net load are highly sensitive to the energy system design, implying that energy systems can be designed so that they are either hindered or helped by climate change. Furthermore, within a system scenario, climate change can change the frequency and seasonality of high net load events and their technological and meteorological composition. Wind-dominated systems with currently electrified heating levels, for instance, feature a 30% increase of high net load events under climate change, mostly in summer and fall, while fully electrified net zero systems are impacted by high net load events in winter and spring, which decrease by 50% with climate change. Our work thus calls for a wider perspective on energy-climate stress that captures the non-linear interactions of climate change and system design uncertainty, thereby overcoming the current focus on cold Dunkelflauten.

physics.soc-ph↗

arXiv2025

Bridging CORDEX and CMIP6: Machine Learning Downscaling for Wind and Solar Energy Droughts in Central Europe

Reliable regional climate information is essential for assessing the impacts of climate change and for planning in sectors such as renewable energy; yet, producing high-resolution projections through coordinated initiatives like CORDEX that run multiple physical regional climate models is both computationally demanding and difficult to organize. Machine learning emulators that learn the mapping between global and regional climate fields offer a promising way to address these limitations. Here we introduce the application of such an emulator: trained on CMIP5 and CORDEX simulations, it reproduces regional climate model data with sufficient accuracy. When applied to CMIP6 simulations not seen during training, it also produces realistic results, indicating stable performance. Using CORDEX data, CMIP5 and CMIP6 simulations, as well as regional data generated by two machine learning models, we analyze the co-occurrence of low wind speed and low solar radiation and find indications that the number of such energy drought days is likely to decrease in the future. Our results highlight that downscaling with machine learning emulators provides an efficient complement to efforts such as CORDEX, supplying the higher-resolution information required for impact assessments.

stat.AP↗

arXiv2025

CLINB: A Climate Intelligence Benchmark for Foundational Models

Evaluating how Large Language Models (LLMs) handle complex, specialized knowledge remains a critical challenge. We address this through the lens of climate change by introducing CLINB, a benchmark that assesses models on open-ended, grounded, multimodal question answering tasks with clear requirements for knowledge quality and evidential support. CLINB relies on a dataset of real users' questions and evaluation rubrics curated by leading climate scientists. We implement and validate a model-based evaluation process and evaluate several frontier models. Our findings reveal a critical dichotomy. Frontier models demonstrate remarkable knowledge synthesis capabilities, often exhibiting PhD-level understanding and presentation quality. They outperform "hybrid" answers curated by domain experts assisted by weaker models. However, this performance is countered by failures in grounding. The quality of evidence varies, with substantial hallucination rates for references and images. We argue that bridging this gap between knowledge synthesis and verifiable attribution is essential for the deployment of AI in scientific workflows and that reliable, interpretable benchmarks like CLINB are needed to progress towards building trustworthy AI systems.

cs.AI↗

arXiv2025

EnScale: Temporally-consistent multivariate generative downscaling via proper scoring rules

The practical use of future climate projections from global circulation models (GCMs) is often limited by their coarse spatial resolution, requiring downscaling to generate high-resolution data. Regional climate models (RCMs) provide this refinement, but are computationally expensive. To address this issue, machine learning (ML) models can learn the downscaling function, mapping coarse GCM outputs to high-resolution fields. Among these, generative approaches aim to capture the full conditional distribution of RCM data given coarse-scale GCM data, which is characterized by large variability and thus challenging to model accurately. We introduce EnScale, a generative ML framework emulating the full GCM-to-RCM map by training on multiple pairs of GCM and corresponding RCM data. It first adjusts large-scale mismatches between GCM and coarsened RCM data, followed by a super-resolution step to generate high-resolution fields. To efficiently model the high-dimensional output, the super-resolution step employs a novel class of sparse local stochastic layers. Both steps employ generative models optimized with the energy score, a proper scoring rule. Compared to state-of-the-art ML downscaling approaches, our setup reduces computational cost by about one order of magnitude. EnScale jointly emulates multiple variables -- temperature, precipitation, solar radiation, and wind -- spatially consistent over Central Europe. In addition, we propose a variant EnScale-t that enables temporally consistent downscaling. We establish a comprehensive evaluation framework across various categories including calibration, spatial and temporal structure, extremes, and multivariate dependencies. Comparison with diverse benchmarks demonstrates EnScale(-t)'s competitive performance and computational efficiency, offering a promising approach for accurate and temporally consistent RCM emulation.

physics.ao-ph↗

arXiv2025

Climate2Energy: a framework to consistently include climate change into energy system modeling

Supply and demand in future energy systems depend on the weather. We therefore need to quantify how climate change and variability impact energy systems. Here, we present Climate2Energy (C2E), a framework to consistently convert climate model outputs into energy system model inputs, covering all relevant types of renewable generation and demand for heating and cooling. C2E performs bias correction, uses established open-source tools where possible, and provides outputs tailored to energy system models. Moreover, C2E introduces a new hydropower model based on river discharge. We analyze dedicated hourly CESM2 Climate Model Simulations under the SSP3-7.0 scenario in Europe, covering climate variability through multiple realizations. We find large reductions in heating demand (-10% to -50%) and Southern European hydropower potentials (-10% to -40%) and increases in cooling demand (>100%). Based on stochastic optimizations with AnyMOD, we confirm that energy systems are highly sensitive to climate conditions, particularly on the demand side.

physics.soc-ph↗

arXiv2022

Robust detection and attribution of climate change under interventions

Fingerprints are key tools in climate change detection and attribution (D&A) that are used to determine whether changes in observations are different from internal climate variability (detection), and whether observed changes can be assigned to specific external drivers (attribution). We propose a direct D&A approach based on supervised learning to extract fingerprints that lead to robust predictions under relevant interventions on exogenous variables, i.e., climate drivers other than the target. We employ anchor regression, a distributionally-robust statistical learning method inspired by causal inference that extrapolates well to perturbed data under the interventions considered. The residuals from the prediction achieve either uncorrelatedness or mean independence with the exogenous variables, thus guaranteeing robustness. We define D&A as a unified hypothesis testing framework that relies on the same statistical model but uses different targets and test statistics. In the experiments, we first show that the CO2 forcing can be robustly predicted from temperature spatial patterns under strong interventions on the solar forcing. Second, we illustrate attribution to the greenhouse gases and aerosols while protecting against interventions on the aerosols and CO2 forcing, respectively. Our study shows that incorporating robustness constraints against relevant interventions may significantly benefit detection and attribution of climate change.

stat.ML↗

arXiv2019

A direct approach to detection and attribution of climate change

We present here a novel statistical learning approach for detection and attribution (D&A) of climate change. Traditional optimal D&A studies try to directly model the observations from model simulations, but practically this is challenging due to high-dimensionality. Dimension reduction techniques reduce the dimensionality, typically using empirical orthogonal functions, but as these techniques are unsupervised, the reduced space considered is somewhat arbitrary. Here, we propose a supervised approach where we predict a given external forcing, e.g., anthropogenic forcing, directly from the spatial pattern of climate variables, and use the predicted forcing as a test statistic for D&A. We want the prediction to work well even under changes in the distribution of other external forcings, e.g., solar or volcanic forcings, and therefore formulate the optimization problem from a distributional robustness perspective.

stat.AP↗