Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning operations”

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 307 records · Page 17

A review of machine learning in building load prediction

The surge of machine learning in recent years has been empowering engineer modeling in various fields. The decreasing hardware cost, increasing data accessibility, and advances of building automation system (BAS) allow the collection and storage of a significant amount of building operation data. The two facts provide great opportunities of applying machine learning to building energy systems modeling and analysis. There are a great number of research papers on this topic but there lacks a comprehensive and general review to summarize the current development, limitations, gaps and future trend. In this review paper series, machine learning techniques in building energy system modeling and analysis are reviewed under the organization and logic of the machine learning definition by Tom M. Mitchell: a computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. This paper is the first part of the review paper series, which focuses on building load prediction. First, the applications of building load prediction model (task T) are reviewed. Then, the modeling algorithms improving machine learning performance and accuracy (performance P) are reviewed. At the same time, the literature on the data perspective for modeling (experience E), including data engineering from sensors level to data level, pre-processing, feature extraction and selection, is reviewed. Finally, what is well-studied and what is lacking but with great potential are concluded; the gaps between present and future utilization of machine learning techniques are identified; the future trend and development are also predicted. The target readers of this paper are not only researchers from the building side who can get exposed to cutting edge machine learning tools, but also those from machine learning side who can understand the potential and challenge to apply machine learning in buildings.

Liang, Zhang↗

Machine Learning Enabled Quantitative Risk Assessment of Aerial Wildfire Response

Aerial wildfire operations are high risk and account for a large number of firefighter deaths. Increasing intensity of wildfires is driving a surge in aerial operations, while simultaneously there is growing interest in improving system safety and performance. In this work, wildfire aviation mishaps documented using the SAFECOM system are analyzed using a previously developed framework for hazard extraction and analysis of trends (HEAT). Hazards and specific failure modes are extracted from the narrative data in SAFECOM forms using natural language processing techniques. Metrics for each hazard are calculated, including frequency, rate, and severity. We examine whether these metrics change over time, and whether they are related to metadata, such as region and aircraft type. The results of the hazard analysis are presented in a risk matrix, identifying the highest and lowest risk hazards based on rate of occurrence and average severity. Results identify jumper operations hazards as high-risk, in addition to bucket drop failures, cargo let down failures, and severe weather as medium risk.

machine learning↗

Modernizing Accelerator Responsiveness and Controls in Operations

Accelerators increasingly use artificial intelligence (AI) and machine learning (ML) software and workflows for a variety of tasks, from optimization to fault detection and recovery. Efficient and sustainable application of these technologies necessitates specialized and facility-specific infrastructure commitments. Accelerator facilities also introduce unique radiation and security hazards, placing additional demands on operational infrastructure. These needs further escalate the prioritization of effective collaboration models and associated funding mechanisms and legal frameworks.

43 PARTICLE ACCELERATORS↗

Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms

Here in this work we present a non-intrusive model reduction method to learn low-dimensional models of dynamical systems with non-polynomial nonlinear terms that are spatially local and that are given in analytic form. In contrast to state-of-the-art model reduction methods that are intrusive and thus require full knowledge of the governing equations and the operators of a full model of the discretized dynamical system, the proposed approach requires only the non-polynomial terms in analytic form and learns the rest of the dynamics from snapshots computed with a potentially black-box full-model solver. The proposed method learns operators for the linear and polynomially nonlinear dynamics via a least-squares problem, where the given non-polynomial terms are incorporated on the right-hand side. The least-squares problem is linear and thus can be solved efficiently in practice. The proposed method is demonstrated on three problems governed by partial differential equations, namely the diffusion–reaction Chafee–Infante model, a tubular reactor model for reactive flows, and a batch-chromatography model that describes a chemical separation process. The numerical results provide evidence that the proposed approach learns reduced models that achieve comparable accuracy as models constructed with state-of-the-art intrusive model reduction methods that require full knowledge of the governing equations.

42 ENGINEERING↗

A Graphical User Interface for the Deep Underground Neutrino Experiment Robotic Test Stand

In preparation for DUNE, Fermilab along with six other institutions are testing cold electronics for quality control before components placed in the far detector. We test them by using a robotic arm that places these chips into sockets on a computer board that will test their functionality. Up until now, the chips have been tested using a command line script that drives a state machine to conduct tests step-by-step. In order to lower the skill barrier to conduct tests and to speed up the quality control process, I was tasked to create a graphical user interface that would allow users to use buttons, text boxes, and drop-down menus to input information and tell the testing state machine how to operate. I had to learn about the Python package Tkinter to start the process of widget placement. I further developed a pause feature unused in the previous command line script that would allow the user to shut down testing gracefully, bring the robotic arm to go back to ground state, and go forward or backward a step in the testing process. After completing the basic functionality of the GUI, I started testing production chips with the GUI to debug. Some issues were found, which required me to further develop parts of the inherited state machine code. The code for the GUI has now been pushed into the copy the DUNE/FD_CE git repository and will soon be merged with the official DUNE/FD_CE repository so that the other institutions testing DUNE cold electronics can use and expand upon it.

Gutierrez Villanueva, Jaziel [Fermilab]↗

Landslide Likelihood Prediction using Machine Learning Algorithms

The supply of electricity via power plants is criticalto the operation of many critical infrastructure systems in mod-ern society. Natural hazards can disrupt the power supply, causepower outages that can halt economic growth, and impede emer-gency response until power is restored. The proposed work aimsto predict the landslides likelihood in these critical infrastructurelocations in the Northeastern USA using integrated databases ofexplanatory variables and machine learning algorithms. First,data related to landslides are obtained and merged, includingtopographic, soil moisture, and precipitation-related data. Fiveregression algorithms, namely: Random Forest, Extreme Gradi-ent Boosting (XGBoost), K-Nearest Neighbor regression (KNN),Linear Support Vector Regressor (SVR), and Linear regression,are utilized to predict the landslide probability and evaluatedon the dataset. The accuracy of the models is assessed by usingstatistical metrics such as mean absolute error (MAE), meansquared error (MSE), and root mean squared error (RMSE).The study results show that Random Forest outperformed othermodels with the mutual information feature selection method.It achieved an MSE of 0.0011 with mutual information-basedfeature selection and an MSE of 0.00157 without feature selection.KNN regressor outperformed the other models with an MSEof 0.00139 with correlation-based information selection. Theproposed landslide identification model with Random Forestalgorithm shows outstanding robustness and great potential intackling the landslide likelihood prediction by employing MLalgorithms.

Vasundhara Acharya↗

Monitoring Airspace Complexity and Determining Contributing Factors

The national airspace has evolved over many years to accommodate increased traffic demand [1] while simultaneously maintaining one of the safest forms of transportation [2], [3]. One of the reasons for this success is the ability of the system and the operators to adapt and accommodate to situations that routinely disrupt optimal operations. These situations may include: adverse weather, delays, early arrivals, equipment outages, and other factors that are outside the operators ability to control. These factors can lead to states where automation is unable to properly handle these issues and therefore air traffic controllers and pilots have to intervene, ultimately increasing communication between operators resulting in higher workload. As controller workload increases to handle sub-optimal operating conditions this can be viewed as an increase in complexity. The reasoning for this is because humans are now required to make tactical decisions in response to external factors, resulting in a departure from the strategic plan where operations would be more efficiently managed. Human operators control airspace complexity under rigid regulations that are constantly changing. The airspace is divided into sectors and the number of aircraft assigned to each controller is limited for safe handling. There has been past work that devised airspace complexity metrics in commercial aviation and related these metrics to controller workload (e.g., [4],[5]). The upper bounds on the system load are pre-determined. Such bounds on complexity make for a safe system, but the system cannot scale and adapt to autonomous, dense, and heterogeneous traffic, including the many types of Unmanned Aerial Vehicles (UAVs) envisioned to be added to the operations. We hypothesize that, as traffic density and heterogeneity grow, and other key metrics change, there will be phase transitions at which the way traffic should be managed changes significantly [6]. We offer a method for in-time detection of contributing factors that lead to phase transitions, characterized by increased complexity. To the best of our knowledge, there is no tool similar to our proposed effort that identifies such contributing factors or precursor patterns. To define the scope we are proposing to measure complexity from the viewpoint of the Terminal Radar Approach Control Facilities (TRACON) controller’s perspective. In particular we are analyzing arrivals into KSFO. With safety as the top concern for airspace operators, it is important to recognize that as density and heterogeneity grow, the focus of the system will change. Times of the day when the airspace has low density and heterogeneity, the flights will follow more efficient paths where the aircraft move on established routes that are more or less directly to the destination. However, when density and heterogeneity increases, the system will begin changing focus to avoiding conflicts and collisions and route the flights in a more flexible way. Higher flexibility requires more communication and coordination between controllers and pilots which the current automation is unable to handle. This paper proposes a novel approach that monitors airspace complexity at multiple scales, uses a Machine Learning-based tool that predicts when operations will transition to a regime of greater complexity, and identifies actions that can reduce the complexity while still maintaining efficient and safe operations. We demonstrate our proposed approach using data from multiple complementary sources. This includes, but is not limited to: historical aircraft surveillance data from NASA’s Sherlock Data Warehouse [7], METAR weather data, and airport configuration data from Aviation System Performance Metrics (ASPM). The surveillance data flight paths are sampled at a variable sample rate — increasing as the aircraft approaches the airport. This is due to how Sherlock manages flight track stitching between different radar facilities which have different sampling rates. The weather and performance data are logged at defined intervals throughout the day at a courser refresh rate. In addition to the logged data and metrics, we leverage pre-defined Standard Terminal Arrival Routes (STARs) procedures to characterize the path of each flight. Each flight files for one of these routes in the flight plan well before entering the terminal airspace, and approximately follows the route until it leaves the STAR, typically on the final fix of a runway transition. However, most flights do not always fly the full STAR procedure to completion [8], but the majority do adhere to the fixes within the common route of the procedure. Our approach leverages fixes in the common route of each of the STARs to build a reference path to the airport. This allows us to characterize the flight paths in what we are defining as the “maneuvering area” (the airspace between the STAR and before the flight is lined up on the runway’s final approach) to determine how off nominal the flights are to calculate its complexity score. Determining airspace complexity is a concept that does not have a concrete answer. In designing this metric, we consider what increases the workload for the air traffic controllers. Consequently more specialized vectoring maneuvers results in higher workload. Accordingly, we start with a theory: each flight has a direct path it takes from the STAR’s common route to the final approach’s outer marker fix for the flight’s landing runway. It is important to note that the direct path is only used as a reference. If the majority of the flights have a large consistent offset as compared to other routes it does not necessarily mean that those flights have higher complexity. We are merely building a distribution based on this direct path for that particular STAR and runway pair to determine the normal mode of operations for that route. Flights that are in the upper tail of these distributions will result in higher complexity scores and flights that fly in the median will represent the normal mode of operations and therefore will have lower complexity scores. Since flights following each STAR route take different paths to the airport, we have a different distribution for each STAR route and therefore can model these distributions to compute a complexity score from their respective normalized distributions. To evaluate the effectiveness of our proposed airspace complexity metric we will compare against an established approach based on trajectory clustering [9]. This unsupervised learning technique consists of the following steps: (1) identify the general maneuvering areas (waypoints) by performing $\kappa$-means or DBSCAN clustering on locations where aircraft frequently turn based on the surveillance radar track data, (2) map flight trajectories onto sequences of waypoints, and (3) cluster the sequences based on their common subsequences. From a high-level perspective, this baseline model learns nominal operations in the airspace through the sequence of waypoints that are representative of where aircraft change direction and defines deviations from the nominal operations as “complex.” Therefore, more deviations from the nominal operations correspond to higher complexity values. For our validation, we re-implemented this technique and tune model hyper-parameters to correctly detect waypoints for the arrival traffic into the San Francisco bay area. We will compute the complexity measure over a one-year period using our proposed technique as well as the baseline. Our validation will be based on each technique’s ability to detect a set of undesirable outcomes (e.g., go-arounds, holding patterns, average time in the airspace, etc.). Since our current complexity metric is derived from the offset from the direct reference path, it’s important to understand what causes these offsets. In many of the flights with high offset distance, flights performing holding patterns and S turns can be observed. These maneuvering tactics are utilized to add distance between the aircraft and the destination runway to prevent multiple flights from having conflicting arrival times. In order to predict a rise in complexity (or the precursor to complexity), it’s necessary to be able to identify these potential conflicts (which in turn, result in higher offsets). To do this, we define a “representative flight” for each STAR route and runway pair. This flight is approximately the path the flight would take if there was a clear path with no other flights in the airspace — including the time remaining to the airport. We first identify the flights for a given STAR runway pair using the offset to the reference path distributions that fall between the 44-55 percentiles. This yields the flights that conform to the most normal mode of operation. Each of these flights is partitioned based on the percent complete from the entry point into the maneuvering areas from 0\% – 100\% complete. Then for each percent “bin”, we take the median value of the flight’s latitude/longitude coordinates, airspeed, and (non causal) time remaining to the airport to construct a lookup table for each percent complete bin on a given route. As a flight enters the maneuvering area, we can find the estimated arrival time of a flight to the airport by finding the closest point to the representative path’s percent complete bin (relative to the flight’s current position at any snapshot in the airspace) and therefore retrieve the corresponding remaining time left on the “representative path”. We assume that the flight will follow the representative path to completion when deriving these estimates. We can then compare these estimated arrival times against other flights for the same snapshot in time to identify potential conflicts. If more flights are estimated to arrive within a tolerance window than there are runways available, then we have a potential conflict. We can use this derived measure along with other factors expected to add disruption to the operation such as weather and runway configuration changes as an input to machine learning tools to detect precursors that increases in our complexity measure. This novel method will assist in uncovering insights into the contributing factors that lead to increased complexity that may allow for in-time responses to avoid reaching a high complexity state in the airspace.

complexity↗

Crack fault diagnosis of rotating machine in nuclear power plant based on ensemble learning

Crack faults in rotating machines can cause machine shutdown or scrapping, endangering the normal operation and safety of nuclear power plants. Intelligent diagnostic techniques based on machine learning have the potential to diagnose crack faults. However, problems such as scarcity of field fault data and high noise of plant measurements pose challenges to the application of machine learning. Here this study proposes an ensemble learning approach to mitigate the negative impacts of the problems. Ensemble learning is a strategy for combining multiple machine learning models into a composite model. The basic idea of ensemble learning is that even if one model makes a mistake, other models can correct it. Case studies based on bearing and gear system fault experiments show that the proposed ensemble learning models have better diagnostic results than the single model in the presence of noise and small data.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation

Particle accelerators are extremely complex systems that are expected to operate on high availability. Predicting impending failures only by utilizing data collected from diagnostic equipment already on board can help operators to avoid installing expensive sensors, unscheduled downtime and associated costs. For this purpose we explore the predictive power of Machine Learning algorithms to detect faulty beams prior to the failure. In this study, we propose a Machine Learning approach to model mapping from a pair of sensors located across the accelerator. While the model is trained to represent normal operation, we evaluate the predictive performance on known faulty beam pulses. We also investigate the model performance on unseen data through k-fold cross-validation. Then we recap the analysis with a neural architecture search and hyperparameter optimization study to fine tune our initial model. In conclusion, this paper will also introduce a sustainable framework that can standardize Machine Learning workflow applied to particle accelerators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Model-Free Probabilistic Forecasting of Nodal Voltages in Distribution Systems

As the penetration of distributed energy resources (DERs) into distribution systems increases, so does the interest in forecasting relevant system variables to help mitigate the associated challenges. One such challenge is the more frequent occurrence of excessive voltages in distribution systems with higher shares of DERs. Accurate and reliable estimates together with forecasts of system states (i.e., nodal voltages) will therefore play a key role in improving the utilization of these variable and uncertain sources while mitigating potential operational risks. Whilst recent literature has explored machine learning (ML) methods for voltage estimation and their extrapolation for a short-time period into the future, few have taken uncertainty quantification into account, and these methods have not yet been translated into operations. This paper discusses the advantages offered by probabilistic voltage forecasts and proposes a non-parametric Bayesian method suitable for forecasting nodal voltages at short-term time horizons while accounting for uncertainties in load and distributed photovoltaic (PV) generation. We demonstrate the value of the proposed Gaussian process (GP) model for a case study using historical forecasts and observation data.

distribution system↗

Demonstration of acoustic monitoring for structural health of microreactors: Through use of neural networks and resonant ultrasound spectroscopy

Nuclear microreactors prioritize modularity and portability and are intended to be a cost-effective technology for non-conventional nuclear markets. As such, the development of microreactors into a safe and feasible solution for energy security applications will necessitate the development of non-destructive technologies to monitor the integrity of inaccessible reactors components during operation. This demonstration applies linear and nonlinear acoustic techniques, in combination with machine learning, to detect and classify mechanical changes (stress and damage) in a test article which are broadly representative of potential operating challenges within a functioning microreactor. All necessary data has been collected for this demonstration, with minor experimental issues identified that can be addressed in follow-on work. Motivated by the expected conditions within a functioning microreactor, we have demonstrated our monitoring techniques on a core-block-like test article using an unstructured excitation source that approximates the noisy acoustic environment expected during reactor operation. At all stress states mechanically applied to the test article, a machine learning model using an artificial neural network was able to classify with 100% accuracy whether a 3D laser vibrometry point measurement was made on an intact or artificially defective test article. Further, model predictions about whether the defect interface was rough or smooth were 95% accurate, indicating the ability of acoustic techniques to recover defect characteristics. Resonant ultrasound spectroscopy (RUS) was also applied to the dataset to provide further quantitative insights about material properties. RUS analysis was ultimately hampered by several minor experimental and data issues, limiting results to certain cases for this demonstration. Last, analysis using nonlinear RUS exhibited sensitivity to changing levels of applied stresses for each intact and defective state. As presented in this demonstration, acoustic monitoring exhibits sensitivity to stress changes, which are of concern due to high thermal gradients expected during startup and operation. Further, our techniques distinguish between measurements made on intact and damaged test articles.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Digital twin framework for PIP-II linac: AI-driven multi-scale modeling from ion source to 800 MeV

The PIP-II superconducting linac at Fermilab is designed to deliver multi-megawatt proton beams for neutrino physics and other high-intensity applications. To expedite commissioning and enhance operational reliability, we have developed an EPICS-based data flow framework that seamlessly integrates digital twins (DT) with physical twins (PT). These digital twins comprise high-fidelity beam dynamics models or data-driven surrogate models connected to their physical counterparts through real-time diagnostics and advanced machine-learning algorithms.Central to this framework is Linac_Gen, an accelerated simulation tool that incorporates convolutional neural networks, random forests, and genetic algorithms to provide up to a tenfold speedup in optimizing the accelerator geometry model. An EPICS translator layer ensures interoperability by efficiently mapping lattice parameters across diverse simulation platforms.Our EPICS-based framework supports multiple operational modes—monitoring, passive learning, closed-loop control, and online learning—covering the entire machine lifecycle. By leveraging HPC resources and multi-objective optimization techniques, the digital twin enables adaptive trajectory correction, real-time fault detection, and predictive modeling of beam stability. This comprehensive approach paves the way for robust, high-intensity operation and data-driven accelerator R&D at Fermilab.

Pathak, Abhishek [Fermilab]↗

Estimation of the Surface Fluxes for Heat and Momentum in Unstable Conditions with Machine Learning and Similarity Approaches for the LAFE Data Set

Abstract Measurements of three flux towers operated during the land atmosphere feedback experiment (LAFE) are used to investigate relationships between surface fluxes and variables of the land–atmosphere system. We study these relations by means of two machine learning (ML) techniques: multilayer perceptrons (MLP) and extreme gradient boosting (XGB). We compare their flux derivation performance with Monin–Obukhov similarity theory (MOST) and a similarity relationship using the bulk Richardson number (BRN). The ML approaches outperform MOST and BRN. Best agreement with the observations is achieved for the friction velocity. For the sensible heat flux and even more so for the latent heat flux, MOST and BRN deviate from the observations while MLP and XGB yield more accurate predictions. Using MOST and BRN for latent heat flux, the root mean square errors (RMSE) are 107 Wm $$^{-2}$$ - 2 and 121 Wm $$^{-2}$$ - 2 , respectively, as well as the intercepts of the regression lines are $$\approx 110$$ ≈ 110 Wm $$^{-2}$$ - 2 . For the ML methods, the RMSEs reduce to 31 Wm $$^{-2}$$ - 2 for MLP and 33 Wm $$^{-2}$$ - 2 for XGB as well as the intercepts to just 4 Wm $$^{-2}$$ - 2 for MLP and $$-1$$ - 1 Wm $$^{-2}$$ - 2 for XGB with slopes of the regression lines close to 1, respectively. These results indicate significant deficiencies of MOST and BRN, particularly for the derivation of the latent heat flux. In fact, in contrast to the established theories, feature importance weighting demonstrates that the ML methods base their improved derivations on net radiation, the incoming and outgoing shortwave radiations, the air temperature gradient, and the available water contents, but not on the water vapor gradient. The results imply that further studies of surface fluxes and other turbulent variables with ML techniques provide great promise for deriving advanced flux parameterizations and their implementation in land–atmosphere system models.

54 ENVIRONMENTAL SCIENCES↗

Predicting biomass comminution: Physical experiment, population balance model, and deep learning

An extended population balance model (PBM) and a deep learning-based enhanced deep neural operator (DNO+) model are introduced for predicting particle size distribution (PSD) of comminuted biomass through a large knife mill. Experimental tests using corn stalks with varied moisture contents, mill blade speeds, and discharge screen sizes are conducted to support model development. A novel mechanism in the extended PBM allows for including additional input parameters such as moisture content, which is not possible in the original PBM. The DNO+ model can include influencing factors of different data types such as moisture content and discharge screen size, which significantly extends the engineering applicability of the standard DNO model that only admits feed PSD and outcome PSD. Test results show that both models are remarkably accurate in the calibration or training parameter space and can be used as surrogate models to provide effective guidance for biomass preprocessing design.

09 BIOMASS FUELS↗

Automating Sensor Characterization with Bayesian Optimization

The development of novel instrumentation requires an iterative cycle with three stages: design, prototyping, and testing. Recent advancements in simulation and nanofabrication techniques have significantly accelerated the design and prototyping phases. Nonetheless, detector characterization continues to be a major bottleneck in device development. During the testing phase, a significant time investment is required to characterize the device in different operating conditions and find optimal operating parameters. The total effort spent on characterization and parameter optimization can occupy a year or more of an expert's time. In this work, we present a novel technique for automated sensor calibration that aims to accelerate the testing stage of the development cycle. This technique leverages closed-loop Bayesian optimization (BO), using real-time measurements to guide parameter selection and identify optimal operating states. We demonstrate the method with a novel low-noise CCD, showing that the machine learning-driven tool can efficiently characterize and optimize operation of the sensor in a couple of days without supervision of a device expert.

Cuevas-Zepeda, Julian [Chicago U., KICP; Chicago U↗

Improved Diagnosis of Precipitation Type with LightGBM Machine Learning

Abstract Existing precipitation-type algorithms have difficulty discerning the occurrence of freezing rain and ice pellets. These inherent biases are not only problematic in operational forecasting but also complicate the development of model-based precipitation-type climatologies. To address these issues, this paper introduces a novel light gradient-boosting machine (LightGBM)-based machine learning precipitation-type algorithm that utilizes reanalysis and surface observations. By comparing it with the Bourgouin precipitation-type algorithm as a baseline, we demonstrate that our algorithm improves the critical success index (CSI) for all examined precipitation types. Moreover, when compared with the precipitation-type diagnosis in reanalysis, our algorithm exhibits increased F1 scores for snow, freezing rain, and ice pellets. Subsequently, we utilize the algorithm to compute a freezing-rain climatology over the eastern United States. The resulting climatology pattern aligns well with observations; however, a significant mean bias is observed. We interpret this bias to be influenced by both the algorithm itself and assumptions regarding precipitation processes, which include biases associated with freezing drizzle, precipitation occurrence, and regional synoptic weather patterns. To mitigate the overall bias, we propose increasing the precipitation cutoff from 0.04 to 0.25 mm h −1 , as it better reflects the precision of precipitation observations. This adjustment yields a substantial reduction in the overall bias. Finally, given the strong performance of LightGBM in predicting mixed precipitation episodes, we anticipate that the algorithm can be effectively utilized in operational settings and for diagnosing precipitation types in climate model outputs. Significance Statement Freezing rain can have significant impacts on transportation and infrastructure, making accurate prediction of precipitation types crucial. In this study, we use a machine learning method known as LightGBM to predict precipitation types. We show that the new algorithm performs better than the existing methods for all precipitation types examined. Additionally, we compute a freezing-rain climatology over the eastern United States. Although the resulting climatology pattern corresponds well to observations, the algorithm overpredicts freezing-rain occurrence. We argue that this bias can be substantially reduced by increasing the precipitation cutoff from 0.04 to 0.25 mm h −1 . Overall, this work highlights the potential of the LightGBM algorithm for both weather forecasting and diagnosing precipitation types in climate models.

Meteorology & Atmospheric Sciences↗