HCHannah Mary Christensen

Hannah Mary Christensen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hannah Mary Christensen has a total of 285 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Comment on egusphere-2026-5890

    by Emma Ford, Manuela I. Brunner, Hannah M. Christensen, Elizabeth Lewis, Simon Moulds, Lorna Shires, Louise Slater

    Machine-learning (ML) models are increasingly used to estimate flood magnitudes and infer their controls through post-hoc feature importance analysis. However, feature importance does not directly measure hydrological process importance nor infer physical causality. The extent to which feature importance is robust to changes in ML model type (e.g., decision-tree versus neural networks), evaluation setting (e.g., held-out catchments versus held-out years), and predictor information (e.g., static versus dynamic attributes) is an important area of research if ML-based inference is to support flood-generation understanding. Therefore, we systematically evaluate predictive skill and feature importance across 518 catchments in Great Britain, using two ML model types: (i) an event-based Random Forest (RF) trained directly on flood magnitude events; and (ii) a sequence-based Long Short-Term Memory (LSTM) network trained on continuous rainfall-runoff observations, which is subsequently evaluated on the same held-out events as the RF. We test performance and feature importance for the flood magnitude events across a spectrum of evaluation settings, predictor changes, training seeds, and sequence lengths. We assess performance at both the pooled and the within-catchment level, in order to distinguish between inter- and intra-catchment skill. The RF achieved higher predictive skill in every directly comparable model fit (e.g., pooled R2 = 0.86 versus 0.68 for the LSTM, under temporal evaluation), reflecting that its event-focused structure is suitable for addressing the task at hand. Notably, for both models pooled skill substantially exceeded within-catchment skill, indicating that much of the apparent skill reflects differences between catchments. The two models failed for different reasons in predicting the largest flood magnitudes, as the RF displayed a magnitude-dependent bias, while the LSTM showed a consistent underestimation. Both models relied predominantly on short-timescale precipitation, with temperature and potential evapotranspiration being utilized over longer timescales. Static attributes performed two separable functions, namely suppressing a baseflow-index structured bias in predicted flood magnitude and shifting antecedent precipitation usage toward shorter timescales. Our findings demonstrate that similar predictive skill can be supported by different feature importance structures, and emphasize the need to test feature importance robustness before inferring process conclusions in future work.

  • Open Access

    Comment on egusphere-2026-5397

    by Simon L. L. Michel, Kristian Strommen, Hannah M. Christensen

    Regional climate projections are usually sharpened by constraining models’ forced responses toward observations, a step that filters out internal variability and works well mainly where the signal-to-noise ratio is high. Here we side-step this limitation with deep learning, treating internal variability not as noise to remove but as part of the future to predict and of the uncertainty to report. A U-Net trained on 290 simulations from 40 CMIP6 Earth System Models maps the 1980 to 2025 evolution of surface air temperature onto decadal-mean monthly climatologies from the 2030s to the 2090s under SSP2-4.5, keeping the forced response and internal variability together. Tested on entirely withheld model families, the forecasts are skilful and empirically calibrated out-of-sample. Within a model's own ensemble, a forecast predicts the future of the specific member it was given more accurately than the futures of that model's other members, a skill that persists to the 2090s, notably over the subpolar North Atlantic, Europe, North America and Southern Ocean. The forecasts also generalise to a next-generation eddy-rich model whose resolved physics lies outside the training distribution, supporting application to real-world data. When applied to observations, the framework reduces uncertainty in global-mean warming similarly to observational constraints, while also providing spatially coherent local predictions. This shows that our deep learning approach can estimate the distribution of future local climate, conditioned on the recent observed trajectory, encompassing uncertainty arising from both forced response and internal variability realisations. This extends observationally constrained projection toward calibrated predictions at the local scale and seasonal resolution where adaptation decisions are made.

  • Open Access

    What do machine learning models learn about floods?

    by Emma Ford, Manuela I. Brunner, Hannah M. Christensen, Elizabeth Lewis, Simon Moulds, Lorna Shires, Louise Slater

    Machine-learning (ML) models are increasingly used to estimate flood magnitudes and infer their controls through post-hoc feature importance analysis. However, feature importance does not directly measure hydrological process importance nor infer physical causality. The extent to which feature importance is robust to changes in ML model type (e.g., decision-tree versus neural networks), evaluation setting (e.g., held-out catchments versus held-out years), and predictor information (e.g., static versus dynamic attributes) is an important area of research if ML-based inference is to support flood-generation understanding. Therefore, we systematically evaluate predictive skill and feature importance across 518 catchments in Great Britain, using two ML model types: (i) an event-based Random Forest (RF) trained directly on flood magnitude events; and (ii) a sequence-based Long Short-Term Memory (LSTM) network trained on continuous rainfall-runoff observations, which is subsequently evaluated on the same held-out events as the RF. We test performance and feature importance for the flood magnitude events across a spectrum of evaluation settings, predictor changes, training seeds, and sequence lengths. We assess performance at both the pooled and the within-catchment level, in order to distinguish between inter- and intra-catchment skill. The RF achieved higher predictive skill in every directly comparable model fit (e.g., pooled R2 = 0.86 versus 0.68 for the LSTM, under temporal evaluation), reflecting that its event-focused structure is suitable for addressing the task at hand. Notably, for both models pooled skill substantially exceeded within-catchment skill, indicating that much of the apparent skill reflects differences between catchments. The two models failed for different reasons in predicting the largest flood magnitudes, as the RF displayed a magnitude-dependent bias, while the LSTM showed a consistent underestimation. Both models relied predominantly on short-timescale precipitation, with temperature and potential evapotranspiration being utilized over longer timescales. Static attributes performed two separable functions, namely suppressing a baseflow-index structured bias in predicted flood magnitude and shifting antecedent precipitation usage toward shorter timescales. Our findings demonstrate that similar predictive skill can be supported by different feature importance structures, and emphasize the need to test feature importance robustness before inferring process conclusions in future work.

  • Open Access

    Comment on egusphere-2026-5397

    by Simon L. L. Michel, Kristian Strommen, Hannah M. Christensen

    Regional climate projections are usually sharpened by constraining models’ forced responses toward observations, a step that filters out internal variability and works well mainly where the signal-to-noise ratio is high. Here we side-step this limitation with deep learning, treating internal variability not as noise to remove but as part of the future to predict and of the uncertainty to report. A U-Net trained on 290 simulations from 40 CMIP6 Earth System Models maps the 1980 to 2025 evolution of surface air temperature onto decadal-mean monthly climatologies from the 2030s to the 2090s under SSP2-4.5, keeping the forced response and internal variability together. Tested on entirely withheld model families, the forecasts are skilful and empirically calibrated out-of-sample. Within a model's own ensemble, a forecast predicts the future of the specific member it was given more accurately than the futures of that model's other members, a skill that persists to the 2090s, notably over the subpolar North Atlantic, Europe, North America and Southern Ocean. The forecasts also generalise to a next-generation eddy-rich model whose resolved physics lies outside the training distribution, supporting application to real-world data. When applied to observations, the framework reduces uncertainty in global-mean warming similarly to observational constraints, while also providing spatially coherent local predictions. This shows that our deep learning approach can estimate the distribution of future local climate, conditioned on the recent observed trajectory, encompassing uncertainty arising from both forced response and internal variability realisations. This extends observationally constrained projection toward calibrated predictions at the local scale and seasonal resolution where adaptation decisions are made.

  • Open Access

    From climate projections to trajectory-conditioned local predictions

    by Simon L. L. Michel, Kristian Strommen, Hannah M. Christensen

    Regional climate projections are usually sharpened by constraining models’ forced responses toward observations, a step that filters out internal variability and works well mainly where the signal-to-noise ratio is high. Here we side-step this limitation with deep learning, treating internal variability not as noise to remove but as part of the future to predict and of the uncertainty to report. A U-Net trained on 290 simulations from 40 CMIP6 Earth System Models maps the 1980 to 2025 evolution of surface air temperature onto decadal-mean monthly climatologies from the 2030s to the 2090s under SSP2-4.5, keeping the forced response and internal variability together. Tested on entirely withheld model families, the forecasts are skilful and empirically calibrated out-of-sample. Within a model's own ensemble, a forecast predicts the future of the specific member it was given more accurately than the futures of that model's other members, a skill that persists to the 2090s, notably over the subpolar North Atlantic, Europe, North America and Southern Ocean. The forecasts also generalise to a next-generation eddy-rich model whose resolved physics lies outside the training distribution, supporting application to real-world data. When applied to observations, the framework reduces uncertainty in global-mean warming similarly to observational constraints, while also providing spatially coherent local predictions. This shows that our deep learning approach can estimate the distribution of future local climate, conditioned on the recent observed trajectory, encompassing uncertainty arising from both forced response and internal variability realisations. This extends observationally constrained projection toward calibrated predictions at the local scale and seasonal resolution where adaptation decisions are made.

  • Open Access

    Error in ERA5 2‐m temperature identified using GraphCast

    by Hannah M. Christensen, Jack Barker, Bobby Antonio, Massimo Bonavita, Mohamed Dahoui, Patricia de Rosnay

    Reanalyses such as the European Centre for Medium‐Range Weather Forecasts (ECMWF) Reanalysis Version 5 (ERA5) have long been foundational for weather and climate science. They have also found a new use case, as training and verification data for machine‐learnt weather prediction (MLWP) models. Here we compare short‐lead‐time (6 h) forecasts from the MLWP model GraphCast against ERA5. In doing so, we identify a recurrent, spatially coherent error in 2‐m temperature centred on the Ethiopian Highlands, which occurs predominantly at 0600 UTC. We find that the same error feature is present in other MLWP models trained on ERA5. We show that these error events arise from errors in ERA5 that are also present in the ECMWF operational analysis. They arise from the two‐dimensional (2D) optimal interpolation procedure, when surface reports that are temporally displaced compared with the background forecast are assimilated. This produces spuriously warm analysis increments over Ethiopia on approximately 7% of dates at 0600 UTC across the reanalysis record. The spread from the ensemble of data assimilation partially flags these cases but is underdispersive. We assess the impact on a MLWP system trained on ERA5. While the MLWP model can largely ignore these unphysical error events, a small systematic degradation in forecast skill over the region is observed. We discuss the implications for using reanalysis as truth in machine‐learning training and verification, and recommend simple changes to reduce such artefacts in future analyses.

  • Open Access

    Local temperatures rapidly depart from historical experience beyond 1.5°C

    by Simon Michel, Hannah Christensen

    Local temperatures increasingly exceed values without precedent in the historical record 1,2 , but when these excursions become permanent 3,4 is uncertain due to the underestimated role of internal climate variability 5 . Here we recast the problem in probabilistic terms by asking, for a given global warming level 2,6,7 , how likely is it that annual mean local temperature will remain above its 1850-1999 maximum through 2100, given the preceding climate history. We train a neural network 8 on 408 CMIP6 simulations 9 under SSP2-4.5 10 , the emissions trajectory closest to current policy commitments 11-13 , and obtain calibrated probabilities skilful under out-of-sample validation. Applied to observations, regions where temperatures remain above their historical maximum are confined to just 2.2% of global land area at 1.5°C, but expand rapidly thereafter, reaching nearly half the present-day global population 14 and 35% of aboveground biomass 15 by 2°C, and most of humanity and nearly 80% of aboveground biomass by 3°C. Current policy trajectories 11,13 will therefore commit a rapidly growing share of humanity and Earth’s ecosystems to twenty-first century local temperatures sustained above their historical maxima.

  • Open Access

    New insights into decadal climate variability in the North Atlantic revealed by data-driven dynamical models

    by Andrew J. Nicoll, Hannah M. Christensen, Chris Huntingford, Doug Smith

    The Atlantic Multidecadal Variability (AMV) and the North Atlantic Oscillation (NAO) are the dominant modes of oceanic and atmospheric variability in the North Atlantic, respectively, and are key sources of predictability from seasonal to decadal timescales. However, the physical processes and feedback mechanisms linking the AMV and NAO, and the role of diabatic processes in these feedbacks, remain debated. We present a data-driven dynamical modelling framework which captures coupled decadal variability in AMV, NAO, and North Atlantic precipitation. Applying equation discovery methods to observational data, we identify low-order models consisting of three coupled ordinary differential equations. These models reproduce observed decadal variability and show robust out-of-sample predictive skill on multi-annual to decadal lead times. The resulting model dynamics include a distinct quasi-periodic 20-year oscillation consistent with a damped oceanic mode of variability. Notably, precipitation-related terms feature prominently in the low-order models, suggesting an important role for latent heat release and freshwater fluxes in mediating ocean–atmosphere interactions. We propose new feedback mechanisms between North Atlantic sea surface temperature and the NAO, with precipitation acting as a dynamical bridge. Overall, these results illustrate how equation discovery can provide mechanistic hypotheses and new insight beyond conventional analyses of observations and climate model simulations.

  • Open Access

    A generative likelihood framework for high-resolution climate model evaluation

    by Lilli Johanna Freischem, Tim Reichelt, Ronald Clark, Philip Stier, Hannah Christensen

    Next-generation high-resolution (km-scale) climate models promise unprecedented accuracy in climate projections, but realizing their potential requires robust methods to quantify how well simulations align with real-world observations. Average-based metrics conventionally used for climate model evaluation ignore the physics encoded in the fine-scale structures of km-scale simulations. To overcome this limitation, we propose a novel, statistically principled evaluation methodology based on the likelihood function of a generative image model. Our method provides a continuous similarity metric derived from the likelihood distribution of observation and simulation snapshots, which can redefine the evaluation, intercomparison, and parameter tuning of high-resolution climate models. We demonstrate the applicability and interpretability of this method by evaluating convective clouds simulated by two state-of-the-art global km-scale models, using their outgoing infrared radiation fields. This work establishes a scalable pathway toward observation-based evaluation of next-generation climate simulations.