Search NASA⌕ Search

SEARCH · Search NASA

Results for “Weatherization training”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 289 records · Page 16

STS-114: Discovery Launch Readiness Press Conference

Michael Griffin, NASA Administrator; Wayne Hale, Space Shuttle Deputy Program Manager; Mike Wetmore, Director of Shuttle Processing; and 1st Lieutenant Mindy Chavez, Launch Weather Officer-United States Air Force 45th Weather Squadron are in attendance for this STS-114 Discovery launch readiness press conference. The discussion begins with Wayne Hale bringing to the table a low level sensor device for everyone to view. He talks in detail about all of the extensive tests that were performed on these sensors and the completion of these ambient tests. Chavez presents her weather forecast for the launch day of July 26th 2005. Michael Griffin and Wayne Hale answer questions from the news media pertaining to the sensors and launch readiness. The video ends with footage of Pilot Jim Kelly and Commander Eileen Collins conducting test flights in a Shuttle Training Aircraft (STA) that simulates Space Shuttle landing.

Source record↗

Optimization of a Multi-Stage ATR System for Small Target Identification

An Automated Target Recognition system (ATR) was developed to locate and target small object in images and videos. The data is preprocessed and sent to a grayscale optical correlator (GOC) filter to identify possible regionsof- interest (ROIs). Next, features are extracted from ROIs based on Principal Component Analysis (PCA) and sent to neural network (NN) to be classified. The features are analyzed by the NN classifier indicating if each ROI contains the desired target or not. The ATR system was found useful in identifying small boats in open sea. However, due to "noisy background," such as weather conditions, background buildings, or water wakes, some false targets are mis-classified. Feedforward backpropagation and Radial Basis neural networks are optimized for generalization of representative features to reduce false-alarm rate. The neural networks are compared for their performance in classification accuracy, classifying time, and training time.

false alarm rate↗

AI Foundation Models for Science: An Open Collaborative Initiative

Foundation Models (FMs), AI models designed to replace task-specific models, are increasingly being recognized for their versatility across numerous downstream applications. These models, trained using self-supervised techniques on any type of sequence data, circumvent the need for large annotated datasets, a major bottleneck in traditional AI model development. FMs can be applied to downstream tasks using few-shot learning and fine-tuning, significantly reducing the need for large labeled training datasets and computational resources. However, the development of FMs requires substantial resources, including access to data and compute power, expertise in the latest models, and specialized scientific knowledge for systematic evaluation. It is challenging for a single group to possess all these capabilities. To address this, NASA IMPACT has initiated an open collaborative effort, leveraging partnerships with the private sector and other groups within and outside NASA, to jointly build FMs. The overarching goal is to develop a consistent and collaborative approach to building FMs for high-value science datasets. This initiative has fostered collaboration within NASA and with external partners, including IBM Research, Clark University, DOE’s ORNL, ESA, and USGS. The effort focuses on identifying key datasets with a wide range of downstream applications, pretraining and building FMs using modified transformer architectures, evaluating compute infrastructure needs, and sharing models, pretraining and fine-tuning code, and data with the community. Furthermore, it aims to train the Earth science community to fine-tune these models for various downstream applications. Our initial effort resulted in the creation of a 100 million parameter HLS Geospatial Model within six months, which was released on HuggingFace. We are now expanding our scope to include data from weather and climate models and investigating multimodal models. We invite those interested in participating in this effort to join us by sharing their use cases, expertise, or data.

Rahul Ramachandran↗

Observing System Simulation Experiments to Determine the Impact of Spaceborne Differential Absorption Radar Measurements of Marine Surface Pressure on Numerical Weather Prediction

Surface air pressures over marine regions can potentially be measured by estimating the total atmospheric column oxygen content with differential absorption radar (DAR). A demonstration instrument, the Microwave Barometric Radar and Sounder (MBARS) has been funded by NASA for airborne missions in 2024 to show proof of concept. In this presentation, the potential use of such marine surface pressure observations from a spaceborne DAR platform to improve numerical weather prediction is examined using the NASA/GMAO global Observing System Simulation Experiment. Several aspects of the instrument are explored, including contamination by heavy precipitation and the expected error characteristics of the observations. Different orbit and scan configurations are compared, including various constellations of nadir smallsats and A-Train-type scanning configurations. The impacts of marine surface pressure observations are put into context with the current global observing network with a Forecast Sensitivity Observation Impact tool.

Nikki Privé↗

Regime Characterization of Offshore Wind Resource Using Unsupervised Learning

Predictability of wind resource conditions is critical for offshore wind design and operations. While many studies of extreme wind conditions focus on specific events such as low-level jets or ramps, these rely on threshold definitions that limit generality. Here we present a data-driven framework that combines principal component analysis (PCA), self-organizing maps (SOM), and k-means clustering to classify wind resource conditions as typical and anomalous from climatological data. Anomalies are defined not by fixed thresholds but by flagging samples located far from SOM node centers inside the baseline SOM structure. This reframes extremes as rare ebents and hence, likely difficult to anticipate by numerical weather prediction models. We applied this approach to 23 years (2000–2022) of hourly profiles from the NOW-23 hindcast model at the Humboldt Wind Energy Area. Classification is conducted on a feature space consisting of 10 m wind speed and direction, bulk shear and veer across 30–270 m, and a low-level jet index. Dimensionality reduction is achieved through PC. A 2 × 3 OM lattice trained on the PCA vectors identified six baseline regimes spanning weak to strong flow states. High quantization-error profiles are identified and re-clustered into four anomalous regimes. The baseline regimes exhibited clear seasonal and diurnal cycles. Meanwhile, the anomalous regimes represented <10 % of all hours but showed distinct combinations of speed, shear, and veer, when compared to the baseline regimes. Anomalous regimes are typically short-lived (~few hours), yet their transitions can lead to hub-height wind changes of −18 to +9 m s -1 . For a representative 15 MW turbine, these shifts imply rapid swings in capacity factor from near-full output to negligible generation. Validation with lidar buoy data showed 51% agreement in SOM labels across ~6,000 overlapping hours, with most mismatches confined to adjacent speed classes. HRRR comparisons further revealed that anomalous regimes were disproportionately associated with forecast biases exceeding 5 m s -1 . Together, these results reframe extremes in offshore wind from absolute maxima or minima to weather states that are difficult to anticipate from models.

17 WIND ENERGY↗

An Operational Configuration of the ARPS Data Analysis System to Initialize WRF in the NM'S Environmental Modeling System

The Weather Research and Forecasting (WRF) model is the next generation community mesoscale model designed to enhance collaboration between the research and operational sectors. The NM'S as a whole has begun a transition toward WRF as the mesoscale model of choice to use as a tool in making local forecasts. Currently, both the National Weather Service in Melbourne, FL (NWS MLB) and the Spaceflight Meteorology Group (SMG) are running the Advanced Regional Prediction System (AIRPS) Data Analysis System (ADAS) every 15 minutes over the Florida peninsula to produce high-resolution diagnostics supporting their daily operations. In addition, the NWS MLB and SMG have used ADAS to provide initial conditions for short-range forecasts from the ARPS numerical weather prediction (NWP) model. Both NM'S MLB and SMG have derived great benefit from the maturity of ADAS, and would like to use ADAS for providing initial conditions to WRF. In order to assist in this WRF transition effort, the Applied Meteorology Unit (AMU) was tasked to configure and implement an operational version of WRF that uses output from ADAS for the model initial conditions. Both agencies asked the AMU to develop a framework that allows the ADAS initial conditions to be incorporated into the WRF Environmental Modeling System (EMS) software. Developed by the NM'S Science Operations Officer (S00) Science and Training Resource Center (STRC), the EMS is a complete, full physics, NWP package that incorporates dynamical cores from both the National Center for Atmospheric Research's Advanced Research WRF (ARW) and the National Centers for Environmental Prediction's Non-Hydrostatic Mesoscale Model (NMM) into a single end-to-end forecasting system. The EMS performs nearly all pre- and postprocessing and can be run automatically to obtain external grid data for WRF boundary conditions, run the model, and convert the data into a format that can be readily viewed within the Advanced Weather Interactive Processing System. The EMS has also incorporated the WRF Standard Initialization (SI) graphical user interface (GUT), which allows the user to set up the domain, dynamical core, resolution, etc., with ease. In addition to the SI GUT, the EMS contains a number of configuration files with extensive documentation to help the user select the appropriate input parameters for model physics schemes, integration timesteps, etc. Therefore, because of its streamlined capability, it is quite advantageous to configure ADAS to provide initial condition data to the EMS software. One of the biggest potential benefits of configuring ADAS for ingest into the EMS is that the analyses could be used to initialize either the ARW or NMM. Currently, the ARPS/ADAS software has a conversion routine only for the ARW dynamical core. However, since the NIvIM runs about 2.5 times faster than the ARW, it is quite advantageous to be able to run an ADAS/NMM configuration operationally due to the increased efficiency.

Case, Jonathan↗

Spatiotemporal Super-Resolution with Generative Machine Learning for Creating Renewable Energy Resource Data Under Climate Change Scenarios

As we plan for a future with higher penetrations of renewables and increasing electrification, it becomes more important to understand how the electricity grid will operate under a variety of weather events. We must also consider that the weather our future grid will experience will be different and possibly more extreme than the historical weather that we have extensive data for. We can use data from global climate models (GCMs) to help understand how our climate may change over the next several decades, but there is often a significant gap between the low-resolution GCM data and the high-resolution weather data required to study power systems under specific weather events. Therefore, our objective in this work is to develop tools that can bridge this gap by using low-resolution GCM data to create realistic high-resolution weather datasets that can be used to study renewable energy generation and electricity demand. To accomplish this objective, we have developed a set of generative machine learning models that can rapidly downscale GCM daily average output data at an approximate grid resolution of 100km to hourly data at an approximate 4 km grid resolution. The models can be used to create high resolution data from nearly any GCM included in the Coupled Model Intercomparison Project (CMIP) Phase 5 or 6. Our methods include all datasets regularly used to study the integration of wind and solar power plants as well as changes in electricity demand due to heating and cooling loads. These models and datasets enable power systems modelers to study climate change-influenced weather events and their impact on the grid. We have downscaled and validated wind, solar, temperature, and humidity data with very promising results. The generative machine learning methods are computationally efficient and produce data that has similar statistical characteristics to current state-of-the-art historical datasets. We have trained initial generative models and produced an initial dataset collectively referred to as Sup3rCC: Super-Resolved Renewable Energy Resource Data with Climate Change Impacts. The data covers a (mostly) historical period from 2015-2025 and a future period from 2050-2059. We have also taken hypothetical high-electrification load data and scaled the heating and cooling loads with respect to the 2050-2059 high-resolution Sup3rCC meteorology. The results show how future levels of renewable energy generation and electrified load may be impacted by climate change, setting the stage for capacity expansion models to consider a dynamic climate through model years.

climate change↗

Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?

Current turbulence parameterizations in numerical weather prediction models at the mesoscale assume a local equilibrium between production and dissipation of turbulence. As this assumption does not hold at fine horizontal resolutions, improved ways to represent turbulent kinetic energy (TKE) dissipation rate (ϵ) are needed. Here, we use a 6-week data set of turbulence measurements from 184 sonic anemometers in complex terrain at the Perdigão field campaign to suggest improved representations of dissipation rate. First, we demonstrate that the widely used Mellor, Yamada, Nakanishi, and Niino (MYNN) parameterization of TKE dissipation rate leads to a large inaccuracy and bias in the representation of ϵ. Next, we assess the potential of machine-learning techniques to predict TKE dissipation rate from a set of atmospheric and terrain-related features. We train and test several machine-learning algorithms using the data at Perdigão, and we find that the models eliminate the bias MYNN currently shows in representing ϵ, while also reducing the average error by up to almost 40 %. Of all the variables included in the algorithms, TKE is the variable responsible for most of the variability of ϵ, and a strong positive correlation exists between the two. These results suggest further consideration of machine-learning techniques to enhance parameterizations of turbulence in numerical weather prediction models.

58 GEOSCIENCES↗

Enhance Low Level Temperature and Moisture Profiles Through Combining NUCAPS, ABI Observations, and RTMA Analysis

Thermodynamic information from low levels in the atmosphere is crucial for operational weather forecasts and meteorological researchers. The NOAA Unique Combined Atmospheric Processing System (NUCAPS) sounding products have been proven beneficial to fill the data gap between synoptic radiosonde observations (RAOBs). However, compared with the upper troposphere, the accuracy of NUCAPS soundings in the low levels still needs improvement. In this study, a deep neural network (DNN) is applied to fuse multiple data sources to enhance the NUCAPS temperature and moisture profiles in the lower atmosphere. The network is developed by combining satellite observations, including NUCAPS sounding retrievals and high resolution geostationary satellite observations from the Advanced Baseline Imager, and surface analysis from the Real-Time Mesoscale Analysis (RTMA) as inputs, while collocated soundings from ECMWF re-analysis version 5 are used as the benchmark for the training. The performance of the model is evaluated by using the independent testing data set, data from a different year, as well as collocated RAOBs, showing improvement to the temperature and moisture profiles by reducing the root-mean-squared-error (RMSE) by more than 30% in the lower atmosphere (from 700 hPa to surface) in both clear sky and partially cloudy conditions. A convective event from June 18, 2017 is presented to illustrate the application of the enhanced low level soundings on high impact weather events. The enhanced soundings from fused data capture the large surface-based convective available potential energy structures in the preconvection environment, which is very useful for severe storm nowcasting and forecasting applications.

54 ENVIRONMENTAL SCIENCES↗

Computer Model Calibration with Time Series Data Using Deep Learning and Quantile Regression

Computer models play a key role in many scientific and engineering problems. One major source of uncertainty in computer model experiments is input parameter uncertainty. Computer model calibration is a formal statistical procedure to infer input parameters by combining information from model runs and observational data. The existing standard calibration framework suffers from inferential issues when the model output and observational data are high-dimensional dependent data, such as large time series, due to the difficulty in building an emulator and the nonidentifiability between effects from input parameters and data-model discrepancy. To overcome these challenges, we, in this work, propose a new calibration framework based on a deep neural network (DNN) with long short-term memory layers that directly emulates the inverse relationship between the model output and input parameters. Adopting the “learning with noise” idea, we train our DNN model to filter out the effects from data-model discrepancy on input parameter inference. We also formulate a new way to construct interval predictions for DNN using quantile regression to quantify the uncertainty in input parameter estimates. Through a simulation study and real data application with the Weather Research and Forecasting Model Hydrological modeling system (WRF-Hydro), we show our approach can yield accurate point estimates and well-calibrated interval estimates for input parameters.

97 MATHEMATICS AND COMPUTING↗

Enhanced Pacific Northwest heat extremes and wildfire risks induced by the boreal summer intraseasonal oscillation

The occurrence of extreme hot and dry summer conditions in the Pacific Northwest region of North America (PNW) has been known to be influenced by climate modes of variability such as the El Niño-Southern Oscillation and other variations in tropospheric circulation such as stationary waves and blocking. However, the extent to which the subseasonal remote tropical driver influences summer heat extremes and fire weather conditions across the PNW remains elusive. Our investigation reveals that the occurrence of heat extremes and associated fire-conducive weather conditions in the PNW is significantly heightened during the boreal summer intraseasonal oscillation (BSISO) phases 6-7, by ~50–120% relative to the seasonal probability. The promotion of these heat extremes is primarily attributed to the enhanced diabatic heating over the tropical central-to-eastern North Pacific, which generates a wave train traveling downstream toward North America, resulting in a prominent high-pressure system over the PNW. The ridge, subsequently, promotes surface warming over the region primarily through increased surface radiative heating and enhanced adiabatic warming. The results suggest a potential pathway to improving subseasonal-to-seasonal predictions of heatwaves and wildfire risks in the PNW by improving the representation of BSISO heating over the tropical-to-eastern North Pacific.

54 ENVIRONMENTAL SCIENCES↗

Assessing Operational Total Lightning Visualization Products

In May 2003, NASA's Short-term Prediction Research and Transition (SPoRT) program successfully provided total lightning data from the North Alabama Lightning Mapping Array (NALMA) to the National Weather Service (NWS) office in Huntsville, Alabama. The major accomplishment was providing the observations in real-time to the NWS in the native Advanced Weather Interactive Processing System (AWIPS) decision support system. Within days, the NALMA data were used to issue a tornado warning initiating seven years of ongoing support to the NWS' severe weather and situational awareness operations. With this success, SPoRT now provides real-time NALMA data to five forecast offices as well as working to transition data from total lightning networks at Kennedy Space Center and the White Sands Missile Range to the surrounding NWS offices. The only NALMA product that has been transitioned to SPoRT's partner NWS offices is the source density product, available at a 2 km resolution in 2 min intervals. However, discussions with users of total lightning data from other networks have shown that other products are available, ranging from spatial and temporal variations of the source density product to the creation of a flash extent density. SPoRT and the Huntsville, Alabama NWS are evaluating the utility of these variations as this has not been addressed since the initial transition in 2003. This preliminary analysis will focus on what products will best support the operational warning decision process. Data from 19 April 2009 are analyzed. On this day, severe thunderstorms formed ahead of an approaching cold front. Widespread severe weather was observed, primarily south of the Tennessee River with multiple, weak tornadoes, numerous severe hail reports, and wind. This preliminary analysis is the first step in evaluation which product(s) are best suited for operations. The ultimate goal is selecting a single product for use with all total lightning networks to streamline training and science sharing.

Stano, Geoffrey T.↗

Preliminary Results of a U.S. Deep South Modeling Experiment Using NASA SPoRT Initialization Datasets for Operational National Weather Service Local Model Runs

A joint collaborative modeling effort among the NWS offices in Mobile, AL, and Houston, TX, and NASA Short-term Prediction Research and Transition (SPoRT) Center began during the 2011-2012 cold season, and continued into the 2012 warm season. The focus was on two frequent U.S. Deep South forecast challenges: the initiation of deep convection during the warm season; and heavy precipitation during the cold season. We wanted to examine the impact of certain NASA produced products on the Weather Research and Forecasting Environmental Modeling System in improving the model representation of mesoscale boundaries such as the local sea-, bay- and land-breezes (which often leads to warm season convective initiation); and improving the model representation of slow moving, or quasi-stationary frontal boundaries (which focus cold season storm cell training and heavy precipitation). The NASA products were: the 4-km Land Information System, a 1-km sea surface temperature analysis, and a 4-km greenness vegetation fraction analysis. Similar domains were established over the southeast Texas and Alabama coastlines, each with an outer grid with a 9 km spacing and an inner nest with a 3 km grid spacing. The model was run at each NWS office once per day out to 24 hours from 0600 UTC, using the NCEP Global Forecast System for initial and boundary conditions. Control runs without the NASA products were made at the NASA SPoRT Center. The NCAR Model Evaluation Tools verification package was used to evaluate both the positive and negative impacts of the NASA products on the model forecasts. Select case studies will be presented to highlight the influence of the products.

Wood, Lance↗

Bayesian inverse modeling of the atmospheric transport and emissions of a controlled tracer release from a nuclear power plant

Probability distribution functions (PDFs) of model inputs that affect the transport and dispersion of a trace gas released from a coastal California nuclear power plant are quantified using ensemble simulations, machine-learning algorithms, and Bayesian inversion. The PDFs are constrained by observations of tracer concentrations and account for uncertainty in meteorology, transport, diffusion, and emissions. Meteorological uncertainty is calculated using an ensemble of simulations of the Weather Research and Forecasting (WRF) model that samples five categories of model inputs (initialization time, boundary layer physics, land surface model, nudging options, and reanalysis data). The WRF output is used to drive tens of thousands of FLEXPART dispersion simulations that sample a uniform distribution of six emissions inputs. Machine-learning algorithms are trained on the ensemble data and used to quantify the sources of ensemble variability and to infer, via inverse modeling, the values of the 11 model inputs most consistent with tracer measurements. We find a substantial ensemble spread in tracer concentrations (factors of 10 to 10 3 ), most of which is due to changing emissions inputs (about 80%), though the cumulative effects of meteorological variations are not negligible. The performance of the inverse method is verified using synthetic observations generated from arbitrarily selected simulations. When applied to measurements from a controlled tracer release experiment, the inverse method satisfactorily determines the location, start time, duration and amount. In a 2 km × 2 km area of possible locations, the actual location is determined to within 200m. The start time is determined to within 5min out of 2h, and the duration to within 50min out of 4h. Over a range of release amounts of 10 to 1000kg, the estimated amount exceeds the actual amount of 146kg by only 32kg. The inversion also estimates probabilities of different WRF configurations. In conclusion, to best match the tracer observations, the highest-probability cases in WRF are associated with using a late initialization time and specific reanalysis data products.

54 ENVIRONMENTAL SCIENCES↗

Connecting Space to Village: Tethys Adoption Within SERVIR

The SERVIR program, a joint development initiative of National Aeronautics and Space Administration (NASA) and United States Agency for International Development (USAID), works in partnership with leading regional organizations world-wide to help developing countries use information provided by Earth observing satellites and geospatial technologies for managing climate risks and land use. SERVIR empowers decision-makers with tools, products, and services to act locally on critical issues related to four key areas: Food Security and Agriculture, Water and Water-related Disasters, Land Use/Land Cover and Ecosystems, Weather and Climate. SERVIR is improving awareness, increasing access to information, and supporting analysis to help people in West Africa, Eastern and Southern Africa, Hindu Kush-Himalaya (HKH), the Lower Mekong, South America and Mesoamerica. NASA funds an Applied Sciences Team (AST), composed of experts from universities and research institutions around the United States. Through AST, SERVIR adopted the Tethys platform introduced by Brigham Young University (BYU) for the implementation of tools to deliver scientific data to stakeholders in the Hindu Kush-Himalaya region. Several Tethys applications developed within SERVIR have raised interest amongst decision makers in the countries served by our regional hubs. They see these new apps as key vehicles to disseminate complex information related to weather models, hydrological models, and air quality monitoring, and as such the scope of our Tethys efforts continue to expand to other regions. As of July 2019, each one of the SERVIR hubs (with the exception of Amazonia, which has only recently started), have stood up Tethys portals and have at least one individual trained in the implementation and maintenance of a Tethys portal and in the creation of basic applications. HKH, with BYU's valuable support, has implemented very sophisticated applications that showcase the possibilities and the benefits that the Tethys platform brings.

Tethys↗

Fleet retrofit report

Flight tests are evaluated of an avionics system which aids the pilot in making two-segment approaches for noise abatement. The implications are discussed of equipping United's fleet of Boeing 727-200 aircraft with two-segment avionics for use down to Category 2 weather operating minima. The experience is reported of incorporating two-segment approach avionics systems on two different aircraft. The cost of installing dual two-segment approach systems is estimated to be $37,015 per aircraft, including parts, labor, and spares. This is based on the assumption that incremental out-of-service and training costs could be minimized by incorporating the system at airframe overhaul cycle and including training in regular recurrent training. Accelerating the modification schedule could add up to 50 percent to the modification costs. Recurring costs of maintenance of the installation are estimated to be of about the same magnitude as the potential recurrent financial benefits due to fuel savings.

Source record↗

Accelerating Radiation Computations for Dynamical Models With Targeted Machine Learning and Code Optimization

Abstract Atmospheric radiation is the main driver of weather and climate, yet due to a complicated absorption spectrum, the precise treatment of radiative transfer in numerical weather and climate models is computationally unfeasible. Radiation parameterizations need to maximize computational efficiency as well as accuracy, and for predicting the future climate many greenhouse gases need to be included. In this work, neural networks (NNs) were developed to replace the gas optics computations in a modern radiation scheme (RTE+RRTMGP) by using carefully constructed models and training data. The NNs, implemented in Fortran and utilizing BLAS for batched inference, are faster by a factor of 1–6, depending on the software and hardware platforms. We combined the accelerated gas optics with a refactored radiative transfer solver, resulting in clear‐sky longwave (shortwave) fluxes being 3.5 (1.8) faster to compute on an Intel platform. The accuracy, evaluated with benchmark line‐by‐line computations across a large range of atmospheric conditions, is very similar to the original scheme with errors in heating rates and top‐of‐atmosphere radiative forcings typically below 0.1 K day −1 and 0.5 W m −2 , respectively. These results show that targeted machine learning, code restructuring techniques, and the use of numerical libraries can yield material gains in efficiency while retaining accuracy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses

Atmospheric reanalyses are widely used to estimate the past atmospheric near-surface state over sea ice. They provide boundary conditions for sea ice and ocean numerical simulations and relevant information for studying polar variability and anthropogenic climate change. Previous research revealed the existence of large near-surface temperature biases (mostly warm) over the Arctic sea ice in the current generation of atmospheric reanalyses, which is linked to a poor representation of the snow over the sea ice and the stably stratified boundary layer in the forecast models used to produce the reanalyses. These errors can compromise the employment of reanalysis products in support of polar research. Here, we train a fully connected neural network that learns from remote sensing infrared temperature observations to correct the existing generation of uncoupled atmospheric reanalyses (ERA5, JRA-55) based on a set of sea ice and atmospheric predictors, which are themselves reanalysis products. The advantages of the proposed correction scheme over previous calibration attempts are the consideration of the synoptic weather and cloud state, compatibility of the predictors with the mechanism responsible for the bias, and a self-emerging seasonality and multidecadal trend consistent with the declining sea ice state in the Arctic. The correction leads on average to a 27% temperature bias reduction for ERA5 and 7% for JRA-55 if compared to independent in situ observations from the MOSAiC campaign (respectively, 32% and 10% under clear-sky conditions). These improvements can be beneficial for forced sea ice and ocean simulations, which rely on reanalyses surface fields as boundary conditions.

54 ENVIRONMENTAL SCIENCES↗