South Asian monsoon precipitation depends on the thermodynamic structure of the lower troposphere, but how its ingredients combine to shape precipitation remains unclear, partly because this dependence is nonlocal in the vertical. We use symbolic distillation, which combines neural networks and symbolic regression, to discover interpretable precipitation equations from 21 years of June-August reanalysis data. Neural networks first learn the vertical thermodynamic structure most relevant to precipitation, condensing each variable into a single interpretable feature not tied to a particular vertical grid. Then, symbolic regression derives closed-form equations from these features and the surface state. Our best equation explains 1.5 times as much precipitation variance as a widely used buoyancy-based diagnostic and recovers about 85% of neural network skill while using about a thousand times fewer parameters. Unlike the buoyancy diagnostic, which adds moisture and instability, the equations treat them as competing controls, with the heaviest precipitation occurring when the lower free troposphere is humid. Over ocean, sensible heating is associated with additional precipitation mainly when near-surface air is warm and moist, improving predicted precipitation and its diurnal cycle. Although the learned features were optimized only for precipitation prediction, the equations largely respond to each feature as expected from convective physics, consistent with the reanalysis. These responses reduce the dependence of monsoon precipitation on the entire vertical column to a few simple, testable constraints that could guide data-driven precipitation models to make them more physically consistent.
Wind profiles in the atmospheric boundary layer (ABL) drive short-range forecasting and wind-energy siting, yet sparse radiosonde coverage forces practitioners to interpolate them from a handful of physical predictors. We benchmark modern tabular learners against analytical parameterizations on 158,097 IGRA soundings. CatBoost, TabM, and FT-Transformer reduce RMSE to 1.3-1.6 m/s, against approximately 3 m/s for power-law and Monin-Obukhov fits; once the predictor set is fixed the three architectures differ by less than 0.05 m/s, so accuracy is driven by predictors rather than architecture. A cohort analysis of within-bin profile dispersion places an empirical floor of approximately 1.77 m/s on any point-wise predictor that uses standard radiosonde features, consistent with prior eddy-viscosity inversions. A one-dimensional Fourier Neural Operator applied as a post-hoc corrector to frozen tabular predictions reduces near-surface RMSE on U.S. stations from 1.5 to 1.2 m/s, while leaving upper-layer error unchanged. Further gains should come from new predictors rather than larger models.
Extreme events in chaotic systems are difficult to learn from short trajectories because they are controlled by finite-time instabilities rather than by frequently observed bulk dynamics. We propose a mechanism-aware conditioning plug-in framework that turns a nudged ensemble of an imperfect model into a non-intrusive sensor of the local instability geometry. In the small-noise regime, the ensemble covariance has the same finite-time deformation kernels that govern local instability, providing a Jacobian-free proxy for local amplifications around a trajectory. A small Feature-Wise Linear Modulation (FiLM) network injects the ensemble geometry into an otherwise unchanged backbone without modifying the low-fidelity model simulator. We demonstrate this interface in two settings: a Transformer-style residual-attention corrector for a controlled low-dimensional chaotic system and a probabilistic recurrent STORN corrector for topographic two-layer quasi-geostrophic (QG) flow. In the low-dimensional benchmark, leading ensemble-covariance directions identify transient instabilities that are also detected by Optimally Time-Dependent (OTD) modes. FiLM conditioning improves 99th-percentile exceedance-frequency errors over an otherwise identical unconditioned Transformer. In QG, an ensemble-conditioned FiLM-STORN model substantially improves long-horizon rare-event statistics in the data-limited regime, including density-tail errors, exceedance frequencies, and spatial exceedance-area distributions relative to an unconditioned STORN trained on the same data. On averaged high-threshold exceedance diagnostics, it also outperforms the unconditioned baseline STORN trained with 20 times more expensive trajectory data. These results show that local instability geometry is not merely interpretable post hoc, but an actionable conditioning signal for data-efficient rare-event emulation.
Separating externally forced trends from internal climate variability is a fundamental challenge in climate science, particularly when analyzing observational records that exist only as a single realization. We show that a single climate realization can be decomposed into forced and internal components by treating external forcing as a dynamical driver within a linear stochastic system, an idea grounded in pullback attractor theory. This addresses a central challenge for climate projection and for detecting and attributing the forced response. Existing single-realization methods rely on linear inverse models (LIMs), which ignore forcing, or linear regression, which omits dynamics. Here we introduce PullbackDMDc, a method grounded in non-autonomous dynamical systems theory and dynamic mode decomposition with control (DMDc), incorporating pullback attractor estimation to decompose a single climate realization into spatial modes and their associated forced and internal components, yielding a physically interpretable picture of the underlying dynamics. After testing on a synthetic system with a known forced response, we illustrate the utility of PullbackDMDc for Earth System Model (ESM) evaluation by applying it to near-surface air temperature and sea-level pressure from reanalysis and four ESM large ensembles. PullbackDMDc estimates the forced response with skill matching or exceeding established baselines and helps select forcing predictors against model-based ground truth. Its internal-variability components reveal that ESMs qualitatively capture interannual and decadal modes while exhibiting systematic differences relative to each other and to observations. Skillful forced-response estimation and a novel decomposition position PullbackDMDc as a practical tool for single-realization climate analysis and ESM evaluation.
Earth system models underpin climate projections, but their cost limits how many scenarios, ensemble members and impact pathways can be explored. Machine-learning weather models forecast as skillfully as physics-based models at a fraction of the cost, yet coupled to an ocean they have produced weak El Nino variability or have learned it from climate-model output, and none carries the climate through rivers to the people exposed to it. Here we present Rescene-ESM, an Earth system model whose coupler, YAHO, yokes a frozen 20.8-million-parameter AI weather model to physically formulated ocean, sea-ice, land, river, carbon and energy components constrained by observations. Adding the couplings one at a time shows what each contributes: over a climatological ocean the AI atmosphere varies from year to year by a third of the observed amount over the oceans, and an interactive mixed layer, an equatorial wave ocean, the residual of the observed sea surface temperature (SST) equation as stochastic forcing and the land's moisture flux raise this step by step and bring El Nino and its teleconnections, leaving the mean climate almost unchanged. The full model simulates about 1,000 years per day on one graphics processing unit, holds the observed climate for a thousand years without drift, reproduces the observed 1979-2022 global warming, carries forced change with a physically based structure around the frozen network (transient climate response 1.60 K), routes runoff to 212 river gauges with a median seasonal-cycle correlation of 0.79 and, driven by emissions, separates the heatwave exposure of an SSP1 and an SSP3 world by a factor of 4.7 in 2081-2100, three-quarters of it through the warmer climate.
Assessing climate risks requires projections of daily temperature distributions, including rare and spatially widespread extremes. Climate simulations are costly and biased, while correcting them toward observations risks suppressing inter-model differences. We train a single machine-learning emulator, a conditional diffusion model, on seventeen CMIP6 models and ERA5 reanalysis to generate spatially coherent daily temperature fields conditioned on model identity, date, and CO2-equivalent concentration. At sampling time, diffusion guidance reduces model biases by steering each emulated climate-model distribution toward observations, with its strength selected through perfect-model experiments using withheld simulated futures. Observational influence decreases with projection horizon and forcing. Across seventeen synthetic targets, guidance more than halves median biases in the 1st and 99th percentiles of daily temperature, improves probabilistic scores and reliability, and reduces median annual global-mean temperature RMSE by 32-57% across three emission scenarios. In a detailed benchmark, guidance also outperforms established bias corrections on daily-field probabilistic scores. Efficient sampling generates large ensembles without further climate simulations. For example, our framework corrects CMIP6's roughly threefold historical overestimate of extreme-heat coverage, yet projects that concurrent extremes will affect nearly half of global land on a typical day in the 2080s under SSP3-7.0.
End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fraction of its cost. These systems are deterministic and issue no uncertainty. Here we render the Aardvark Weather model probabilistic by attaching one stochastic mechanism to each component: learned, input-dependent noise at the observation encoder, aimed at the uncertainty inherited from the observing system, and Monte Carlo dropout in the processor, aimed at the uncertainty of the learned dynamics. The resulting nested ensemble attributes forecast spread to the two sources through a law-of-total-variance decomposition, cross-checked by withholding observation streams. Probabilistic finetuning significantly improves the mean forecast, by 11% on average across variables and lead times. The ensemble is close to calibrated against ERA5 through the medium range, is at least as accurate as the deterministic model at weather stations while beating it in relative economic value at every lead time, and remains considerably behind the operational ECMWF IFS ensemble. The encoder branch behaves as observation-driven uncertainty. Component-attributed uncertainty makes end-to-end forecasts more transparent, a step toward observation-driven digital twins of the atmosphere.
Accurate Surface Solar Irradiance (SSI) estimation is increasingly important for photovoltaic energy monitoring and forecasting. The recently introduced Meteosat Third Generation (MTG) satellite constellation provides imaging data with higher spatial resolution compared to the Meteosat Second Generation (MSG) satellite constellation, but its benefits for machine-learning-based SSI retrieval are not well established. We compare multi-resolution convolutional neural network models for 10-minute SSI retrieval over Northern Europe (Estonia) using either MSG/SEVIRI or MTG/FCI satellite imagery. We evaluate model performance against ground-based pyranometer measurements from eight Estonian meteorological stations using site-based cross-validation with a temporally independent test year and multiple training seeds. Model performance is also compared with the SARAH-3 physics-based satellite SSI product. The FCI-only model significantly outperformed the SEVIRI-only model under overcast and cloudy conditions, reducing RMSE by 5.1 W/m^2 and 6.5 W/m^2, respectively. However, under partly cloudy or clear skies, there was no statistically significant difference in RMSE between the FCI-only and the SEVIRI-only models. In all-sky conditions, the RMSE of the FCI-only model was 5.1 W/m^2 lower on average, but this difference was not statistically significant after Bonferroni correction. Compared with physics-based SARAH-3, the FCI-only model yielded skill scores of 28% under overcast conditions, 19% under cloudy conditions, and 17% overall. Furthermore, both models underperformed SARAH-3 in clear-sky conditions. These results show that higher-resolution MTG/FCI imagery improves CNN-based SSI retrieval when clouds dominate irradiance variability, but also indicate that higher resolution alone is insufficient to address clear-sky limitations in machine-learning-based SSI retrieval.
AI weather prediction models are released with 32-bit (fp32) weights and run in fp32 by default, although current GPUs compute much faster in 16-bit formats. We run five publicly available models -- Aurora, Pangu-Weather, FourCastNet, SFNO and FastNet -- on a single 16 GB GPU from 52 initial dates in 2024, in fp32 and with their networks in half precision (fp16), and verify the forecasts against ERA5. The physical state must stay in fp32: converting the whole model rounds it in physical units, which in fp16 overflows and in bf16 discards meaningful information. With the state, its normalisation and denormalisation in fp32, running the network in fp16 changes the global RMSE by at most 1.4%, and by about 0.5% or less for four of the five models, equivalent to less than one hour of lead time up to day 8 and at most two hours at day 10. The differences show no systematic pattern by region, scale or for tropical and extratropical storms, apart from a small tropical penalty in FourCastNet, and fp16 leaves the CRPS, spread and calibration of Aurora's ensemble almost unchanged. No value overflowed fp16's numeric range (+/-65,504); the largest stay 38 to 544 times below it. A 10-day forecast in fp16 is 1.3-3.5 times faster than in fp32 and uses 1.4-3.7 times less energy. Sensitivity experiments show that rules of thumb from other applications of reduced precision carry over only partly: the first and last layers dominate for some models but not for others, and no type of layer is sensitive on its own. For running AI weather models on a single GPU, fp16 with the state in fp32 is practically lossless at a fraction of the cost. bf16, often preferred for its wider range, is as fast but less accurate than fp16 for every model, and simple 8-bit quantisation costs far more skill.
Weather fronts are transition regions between air masses with contrasting thermodynamic properties and are associated with mid-latitude precipitation and severe weather. We investigate machine learning (ML) methods for detecting weather fronts and quantify the contribution of reanalysis data to performance. We compare two configurations of the same ML model for pixel-wise frontal classification over the North Atlantic and Europe: (1) using only geostationary infrared satellite observations, and (2) additionally using 28 ERA5 reanalysis fields. The satellite-only model achieves a neighbourhood critical success index at a 150 km tolerance (CSI@150) of $0.402$, which lies within the range of agreement between analyses from different meteorological services. The satellite$+$ERA5 model achieves $0.575$, an improvement of $0.173$. Our analysis shows that low-level winds are the least predictable from the satellite representation ($R^2 = 0.23$, compared with $0.88$ for temperature), while removing winds or moisture causes the largest decreases in detection performance.
Differentiable weather models allow atmospheric initial conditions to be directly optimized to shadow a known trajectory, which we take from a reanalysis dataset. Here, we extend this optimization to include the forecast model, GraphCast, using low-rank adaptation (LoRA). We compare model optimization with initial-condition (IC) optimization, and then joint optimization, where both are tuned simultaneously. When compared against a control forecast initialized with reanalysis data, LoRA and IC optimization individually produce similar improvements. We find similar results when IC and LoRA are jointly optimized across a spectrum of solutions where a tuning coefficient smoothly shifts the weight of the joint optimization from all-LoRA to all-IC; forecast improvement is not unique to the relative contributions of model and IC corrections. To better discriminate the source of error, we introduce a second model, Pangu-Weather, as a supervisor that gates IC updates during joint optimization. This gated optimization is the same as before, except that IC updates at each epoch are accepted only when they improve the forecasts of both models; otherwise, only the LoRA update is accepted. Results show that this cross-model constraint substantially improves agreement between the two models in their response to the same optimized ICs, narrowing the gap in mean forecast error reduction from 64% to 10%. Moreover, when used together, the LoRA and IC corrections from the gated optimization yield GraphCast forecast improvements similar to those from the ungated optimization. These results imply that model error that is encoded in the ungated ICs is shifted to the LoRA corrections via gating, yielding IC corrections that may provide better analysis estimates.
Every weather forecast is uncertain, and decisions from flood warnings to energy trading depend on how well that uncertainty is quantified. Machine-learning (ML) ensembles now quantify it better than the best physics-based ensemble, yet two things about them remain opaque: whether their skill requires hundreds to thousands of accelerator-days of training, and how a network with a simple source of randomness produces a spread that follows the flow. Here we introduce Sonny-ENS, an ensemble of three 68.9-million-parameter networks with Monte Carlo dropout, trained on the continuous ranked probability score (CRPS) in 2.7 A40 GPU-days. On 2022, it has a lower CRPS than the European Centre for Medium-Range Weather Forecasts ensemble (ENS) on 96% of 570 targets and an 8.3% lower mean CRPS at lead times of 1-10 days. It outperforms the operational GenCast on 69% of the targets, and a 51-member, 15-day forecast takes 69 s on one GPU. Ablations identify the ingredients of this skill, and a Kolmogorov-Arnold sparse autoencoder shows that dropout injects uncertainty mainly in the tropics, whereas the spread grows where the atmosphere is baroclinically unstable (spatial correlation 0.91 with the Eady growth rate). Skillful probabilistic weather forecasts are therefore within reach of a single GPU server.
This study presents a novel application of image-to-image generative adversarial networks (GANs) to produce a complete tropical cyclone (TC) surface wind field diagnosis from a single frame of satellite infrared brightness temperature (IR). Because TC surface wind fields are infrequently observed, we train on two data sets. The first contains 3,323 image pairs of IR and wind fields from Weather Research and Forecasting Model (WRF) simulations (WRF2WRF). The second contains 11,886 real IR satellite images paired with parametric wind fields built on the extended best-track data set (IBTrACS) of TC intensities and wind radii (GOES2PARA). Both models, conditioned on storm intensity, motion, and latitude, transform single-channel IR into wind fields over 6$^{\circ} \times$ 6$^{\circ}$ (WRF2WRF) and 7$^{\circ} \times$ 7$^{\circ}$ (GOES2PARA) domains, at 256 $\times$ 256 pixel resolution. GOES2PARA captures outer wind field asymmetries, enabling diagnosis of 64, 50, and 34-knot wind radii (R64, R50, R34) in each quadrant. WRF2WRF also produces detailed rainbands and eyewall asymmetries. Pixel-wise RMSE against held out truth demonstrates realistic wind field generation with mean RMSE of 6.4 knots (GOES2PARA) and 7.2 knots (WRF2WRF). Compared against IBTrACS, WRF2WRF achieved mean absolute errors (MAE) of 14.8 nautical miles (NM) for radius of maximum wind (RMW) and 25.9 NM for R34. GOES2PARA achieved 10.0 NM MAE for RMW and 25.9 NM for R34. Against Synthetic Aperture Radar wind fields GOES2PARA yielded a lower mean pixel-wise error (RMSE 12.1 kt, MAE 9.5 kt) than WRF2WRF (RMSE 13.9 kt, MAE 11.3 kt). Unlike many existing operational surface wind speed algorithms, our image-to-image models provide updated wind fields with every new satellite image.
Rapid intensification (RI) is one of the most dangerous and unpredictable phases of tropical cyclones, and its environmental and structural drivers are difficult to identify and separate in observations. Here we introduce CausalVisionRI, a causal-prior-constrained deep-learning system for 24-h RI warning in the western North Pacific. It integrates infrared remote sensing imagery, atmospheric and oceanic fields, and an observationally discovered causal graph into a unified model. The graph and eight sign-verified effects on 24-h intensity change provide an auditable causal prior for training. Discovered from 522 cyclones in 2000-2017, it identifies causal pathways linking atmospheric and oceanic conditions, the cyclone's dynamical and structural state, and its 24-h intensity change. On a forward holdout covering 2020-2024 and 3,004 records, the five-member ensemble achieves a Brier skill score (BSS) of 0.259 relative to a fixed development climatology, significantly exceeding four reference systems; the three LDA baselines reach at most 0.105. It also attains higher detection rates than a published knowledge-block scheme and a reconstructed contrastive-learning scheme at matched false-detection rates under our USA 30-kt standard and the published RITCF standard. Ablations show that the graph pathway adds 0.032 BSS across the holdout and 0.063 over 2020-2021, with a significant contribution in one ensemble member. A deep-learning model constrained by observationally discovered causal structure thus offers a new route to physically informed RI warning.
Earth system models (ESMs) rely on parameterizations to represent unresolved processes such as convection, cloud microphysics, and turbulence. However, translating advances in physical understanding into stable, validated parameterizations and integrating them into ESMs often takes years. Agentic AI could accelerate this process and enable more systematic exploration of design choices. Using warm-rain collision-coalescence as a test case, we evaluate agents' ability to synthesize scientific literature, reimplement published bulk parameterizations, and propose new functional forms as differentiable JAX code. We compare conventional parameterizations, data-driven emulators, and agent-generated closures against high-fidelity superdroplet simulations, repeating unattended experiments across ten language models. With expert guidance or iterative feedback, agents produced executable, differentiable, mass-conserving code, although unattended performance depended strongly on the scheme and language model. Iterative feedback lowered median rollout error for eight of ten models. Retuned physical schemes matched or outperformed many learned parameterizations at substantially lower computational cost, but two of 100 unattended agent-generated closures achieved slightly lower rain-mass error than the most accurate retuned scheme on held-out simulations.
Satellite-derived bathymetry (SDB) is often proposed as a low-cost complement to multibeam surveys of ports, but its accuracy is seldom measured on an area the model has never seen. We test SDB in the turbid, shallow and tidal waters of the Abu Dhabi coast against 285,619 multibeam soundings from twelve surveys at six port areas, reduced to Lowest Astronomical Tide. The Stumpf ratio, the Lyzenga transform, a monotonic gradient-boosted tree model (LightGBM) and a U-Net ensemble were trained on 72 Sentinel-2 images and tested in transfer to an unseen site and with local control (about 20% of a site's soundings, spatial blocks beyond a 225 m buffer). The validation design changed the result more than the model: the same LightGBM model gave 0.57 m RMSE under a random pixel split, 1.30 m under spatial blocks and 1.66 m at an unseen site. In transfer the Stumpf ratio (1.45 m) was not beaten by LightGBM, the U-Net or Lyzenga. With local control a hybrid of the tree output and the band ratio reached 1.11 m over 0-11 m, 67% of pixels within the IHO S-44 Order 2 tolerance and a conformal 95% interval with 95% observed coverage; in clear water it reached 0.29-0.53 m. The seabed could not be read beyond 11 m, and summer images were five to six times more turbid than winter ones. ICESat-2 ATL24 agreed with the surveys to 0.25 m after a depth-dependent offset was removed. A 60 m reconnaissance mosaic of 17,200 km2 of the UAE coast, calibrated cell by cell on ICESat-2 without any vessel survey, reached 1.42 m RMSE on held-out blocks over half of the product. Sentinel-2 SDB with about a hundred control depths per image is a usable reconnaissance and change-monitoring tool in these waters to about 10 m; it does not meet S-44 Order 1 without local control, and accuracies from random splits should not be taken as operational accuracy.
Atmospheric fronts are associated with much of the high-impact weather in the mid-latitudes, yet their identification and classification remain largely manual and subjective. Existing deep learning approaches rely primarily on gridded reanalysis or forecast data, limiting their applicability to satellite observations available for time-critical applications. We introduce SATFRONT, a machine learning framework for detecting cold, warm, and occluded fronts over Europe from geostationary satellite observations, with reanalysis data as an optional additional input. The model is trained on frontal analyses from five European national meteorological services and evaluated against UK Met Office analyses for 2024. Using satellite observations alone, SATFRONT achieves a Critical Success Index (CSI) of 0.428 at a 150 km tolerance, within the range of agreement between analyses from different meteorological services (0.277-0.501) and higher than that of an operational rule-based front detector that uses satellite data (0.133). Adding ERA5 reanalysis increases the CSI to 0.591. ERA5 substantially improves the placement of individual fronts, although its effect on their annual spatial distribution varies by front type. These results demonstrate that cold, warm, and occluded fronts can be detected directly from geostationary satellite observations, providing a basis for automated frontal analyses at the high temporal frequency required for time-critical applications.
Accurate precipitation forecasting remains elusive as physics-based models struggle to resolve mesoscale convection and machine learning often yields physically inconsistent, blurred results that consistently underestimate extreme events. We present FitzRoy, the first system that simultaneously achieves state-of-the-art predictive skill and physical realism over the continental United States. Through a reinforced diffusion framework, where a conditional discrete diffusion model is refined via reinforcement learning, FitzRoy effectively resolves the long-standing trade-off between pointwise accuracy and structural fidelity. Across lead times up to 24 hours, FitzRoy consistently matches or exceeds state-of-the-art models while preserving structural realism and capturing extreme events. Its low-latency inference further enables deployment in real-time operational settings. In case studies such as the 2025 Texas Hill Country floods and the 2026 Missouri floods, FitzRoy signals record-breaking accumulations that existing models largely missed. By bridging the gap between realism and skill, FitzRoy establishes a new frontier for high-fidelity precipitation forecasting.
Preserving fine-scale structure without degrading spatial accuracy is a central challenge for kilometre-scale machine-learning weather prediction (MLWP). We introduce a loss based on the dual-tree complex wavelet transform that constrains atmospheric fields jointly by scale, location, and orientation. We evaluate its performance using an experimental joint global--regional FastNet configuration, which produces \SI{1.5}{km} forecasts over the UK alongside $\sim$\SI{31}{km} global forecasts. Relative to both mean-squared error (MSE) and an FFT-based spectral objective, the wavelet loss substantially improves spectral fidelity. Compared with MSE training, it maintains similar pointwise performance, improves neighbourhood-based verification, and produces sharper precipitation fields with more realistic intensity distributions. These results demonstrate that spatially localised wavelet constraints can preserve multiscale atmospheric structure while largely avoiding the loss of pointwise accuracy associated with globally supported spectral objectives.
Existing noise mitigation strategies for wind farms usually consist in reducing turbines power output, without accounting for the wake interactions between them and the noise emission directivity. This leads to over-conservative policies and unexploited wind power. Yet, turbine yaw can simultaneously affect wake interactions and the direction of noise emission, offering an additional degree of freedom for farm-level noise control. We therefore propose Noise Steering, a model-free reinforcement learning (RL) strategy that jointly controls turbine yaw angles and power setpoints to maximise farm power while satisfying a local noise constraint in a defined region. To enable training at a reduced computational cost, a low-fidelity acoustic model is coupled with the steady-state FLORIS simulator. The RL agent effectively learns how to redirect wakes and noise directivity away from the protected region while redistributing power across the farm. On a six-turbine test farm, the policy satisfies the 40 dB noise constraint throughout the full range of turbulent winds, with an average power deficit of only 2% relative to greedy unimpeded control, and up to 7.7% at high wind speeds. In comparison, the industry-standard noise-reduced operation (NRO) baseline here generates an average power loss of 17%. When deployed in the higher-fidelity FASTFarm simulator, the policy largely retains its performance under steady and turbulent inflow, despite differences in simulation fidelity. These results demonstrate the potential of combining yaw control and power derating through RL to improve the power-noise trade-off in wind farm operation.