SEARCH · Engineering Papers

Results for “data classification”

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.

SourceResearch connectionFrom yearThrough year

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

At least 1,009 records · Page 56

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Adaptive Discovery and Mixed-Variable Optimization of Next Generation Synthesizable Microelectronic Materials

Design of new microelectronic materials is characterized by several challenges such as high-dimensionality of the atomic structure-composition variable space, formidable cost of directly using high-fidelity simulations for design optimization, dispersity in literature-reported similar materials and synthesis methods, complex physical mechanisms, and mixed qualitative and quantitative design variables that lead to a disjointed design space. Even though machine learning (ML) techniques have been employed to expedite materials innovation, existing methods treat ML and design optimization as two separate processes, failing to resolve the fundamental challenges associated with high dimensionality and mixed-variable complexity. We have developed a ML enhanced mixed-variable material design optimization framework to efficiently extract useful information from existing data in literature and physics-based simulations to guide the autonomous search for optimal materials. Our proposed framework is composed of four computational modules: (1) a natural language processing (NLP) based virtual screening module, (2) classification based concept exploration module, (3) a density functional theory (DFT)-based high-fidelity evaluation model, and (4) a novel latent-variable Gaussian process (LVGP) ML model for mixed-variable problems with uncertainty quantification, which seamlessly integrates with Bayesian Optimization (BO) and achieves superb efficiency through embedded physics-based dimension reduction. Our approach is demonstrated and validated using the testbed of functional materials exhibiting metal-insulation transitions (MITs), with the targeted reversible resistivity changes (∼10^5) near room temperature. At the end of the 30-month project, we have developed a series of new ML techniques using NLP, conditional variational autoencoders, active learning, latent-variable Gaussian processes, integrated with Bayesian optimization. Our project has resulted in new predicted MITs compounds and improved understanding of MITs microscopic mechanisms, which in turn will revolutionize microelectronics science to provide energy-saving solutions. Our research has improved both creativity and efficiency in transforming rare-event discoveries of new functional materials to persistent innovations. In addition to open-sourcing the online MIT database and the classification model, the LVGP open source code has been downloaded more than 15,000 times within two years. More than 40 MIT compounds have been identified and many have been pursued experimentally via collaborators. The research results are published in close to 20 collaborative papers in high-impact journals, such as Chem. Mater., Appl. Phys. Rev., Sci. Rep., among others of design space.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Growth, mortality, wood density, biomass data from BIONTE inventories in Manaus, Brazil

BIONTE (BIOmass and NuTrient Experiment) is a selective logging experiment established at the Experimental Station of Tropical Forestry (EEST, aka “ZF2”) field research station in the mid 1980s in the central Amazon (Higuchi et al. 1997, Amaral et al. 2019). Led by the National Institute for Amazon Research (INPA) in Brazil, the project aimed at assessing the effects of logging intensity on forest dynamics and enabling the creation of a model of forest management for the Central Amazon. The experiment included three levels of increasing selective logging intensity and controls, with 1 hectare sample plots (12 total) located at the center of 4 hectare treatment plots. The site’s Köppen classification is tropical rainforest (Af), characterized by high temperatures and humidity, with mean annual temperatures around 27 ℃ and mean annual precipitation around 2200 mm of rain. The vegetation has a high floristic diversity, the soils of the region are poor in nutrients, and the topography is characterized by plateaus (where BIONTE is located), and also valley bottoms and slopes. The inventory (growth and mortality) and biomass data included here covers the 1990 to 2019 period, with wood density being averaged from existing datasets. This dataset includes a data file in .csv file format and a .txt file, BIONTE_mortality-rates_headers.txt, that provides descriptions for the data file headers.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

A high-throughput workflow to analyze sequence-conformation relationships and explore hydrophobic patterning in disordered peptoids

Understanding how a macromolecule’s primary sequence governs its conformational landscape is crucial for elucidating its function, yet these design principles are still emerging for macromolecules with intrinsic disorder. Herein, we introduce a high-throughput workflow that implements a practical colorimetric conformational assay, introduces a semi-automated sequencing protocol using matrix-assisted laser desorption/ionization and tandem mass spectrometry (MALDI-MS/MS), and develops a generalizable sequence-structure algorithm. Using a model system of 20mer peptidomimetics containing polar glycine and hydrophobic N-butylglycine residues, we identified nine classifications of conformational disorder and isolated 122 unique sequences across varied compositions and conformations. Conformational distributions of three compositionally identical library sequences were corroborated through atomistic simulations and ion mobility spectrometry coupled with liquid chromatography. A data-driven strategy was developed using existing sequence variables and data-derived “motifs” to inform a machine-learning algorithm toward conformation prediction. Here, this multifaceted approach enhances our understanding of sequence-conformation relationships and offers a powerful tool for accelerating the discovery of materials with conformational control.

data-driven analysis↗

DOE OSTI2023

Deep neural network uncertainty quantification for LArTPC reconstruction

We evaluate uncertainty quantification (UQ) methods for deep learning applied to liquid argon time projection chamber (LArTPC) physics analysis tasks. As deep learning applications enter widespread usage among physics data analysis, neural networks with reliable estimates of prediction uncertainty and robust performance against overconfidence and out-of-distribution (OOD) samples are critical for their full deployment in analyzing experimental data. While numerous UQ methods have been tested on simple datasets, performance evaluations for more complex tasks and datasets are scarce. Here we assess the application of selected deep learning UQ methods on the task of particle classification using the PiLArNet monte carlo 3D LArTPC point cloud dataset. We observe that UQ methods not only allow for better rejection of prediction mistakes and OOD detection, but also generally achieve higher overall accuracy across different task settings. We assess the precision of uncertainty quantification using different evaluation metrics, such as distributional separation of prediction entropy across correctly and incorrectly identified samples, receiver operating characteristic curves (ROCs), and expected calibration error from observed empirical accuracy. We conclude that ensembling methods can obtain well calibrated classification probabilities and generally perform better than other existing methods in deep learning UQ literature.

47 OTHER INSTRUMENTATION↗

DOE OSTI2020

The chemical compositions of accreted and in situ galactic globular clusters according to SDSS/APOGEE

ABSTRACT Studies of the kinematics and chemical compositions of Galactic globular clusters (GCs) enable the reconstruction of the history of star formation, chemical evolution, and mass assembly of the Galaxy. Using the latest data release (DR16) of the SDSS/APOGEE survey, we identify 3090 stars associated with 46 GCs. Using a previously defined kinematic association, we break the sample down into eight separate groups and examine how the kinematics-based classification maps into chemical composition space, considering only α (mostly Si and Mg) elements and Fe. Our results show that (i) the loci of both in situ and accreted subgroups in chemical space match those of their field counterparts; (ii) GCs from different individual accreted subgroups occupy the same locus in chemical space. This could either mean that they share a similar origin or that they are associated with distinct satellites which underwent similar chemical enrichment histories; (iii) the chemical compositions of the GCs associated with the low orbital energy subgroup defined by Massari and collaborators is broadly consistent with an in situ origin. However, at the low-metallicity end, the distinction between accreted and in situ populations is blurred; (iv) regarding the status of GCs whose origin is ambiguous, we conclude the following: the position in Si–Fe plane suggests an in situ origin for Liller 1 and a likely accreted origin for NGC 5904 and NGC 6388. The case of NGC 288 is unclear, as its orbital properties suggest an accretion origin, its chemical composition suggests it may have formed in situ.

Horta, Danny↗

DOE OSTI2024

The Dark Energy Survey Supernova Program: Cosmological Analysis and Systematic Uncertainties

We present the full Hubble diagram of photometrically classified Type Ia supernovae (SNe Ia) from the Dark Energy Survey supernova program (DES-SN). DES-SN discovered more than 20,000 SN candidates and obtained spectroscopic redshifts of 7000 host galaxies. Based on the light-curve quality, we select 1635 photometrically identified SNe Ia with spectroscopic redshift 0.10 < z < 1.13, which is the largest sample of supernovae from any single survey and increases the number of known z > 0.5 supernovae by a factor of 5. In a companion paper, we present cosmological results of the DES-SN sample combined with 194 spectroscopically classified SNe Ia at low redshift as an anchor for cosmological fits. Here we present extensive modeling of this combined sample and validate the entire analysis pipeline used to derive distances. We show that the statistical and systematic uncertainties on cosmological parameters are ${\sigma }_{{{\rm{\Omega }}}_{M},\mathrm{stat}+\mathrm{sys}}^{{\rm{\Lambda }}\mathrm{CDM}}=$ 0.017 in a flat ΛCDM model, and $({\sigma }_{{{\rm{\Omega }}}_{M}},{\sigma }_{w}{)}_{\mathrm{stat}+\mathrm{sys}}^{w\mathrm{CDM}}$ = (0.082, 0.152) in a flat wCDM model. Combining the DES SN data with the highly complementary cosmic microwave background measurements by Planck Collaboration reduces by a factor of 4 uncertainties on cosmological parameters. In all cases, statistical uncertainties dominate over systematics. We show that uncertainties due to photometric classification make up less than 10% of the total systematic uncertainty budget. This result sets the stage for the next generation of SN cosmology surveys such as the Vera C. Rubin Observatory's Legacy Survey of Space and Time.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2026

Graph Identification of Proteins in Tomograms (GRIP-Tomo) 2.0: Topologically aware classification for proteins

Cryo-electron tomography (cryo-ET) enables structural characterization of biomolecules under near-native conditions. Existing approaches for interpreting the resulting three-dimensional volumes are computationally expensive and have difficulty interpreting density associated with small proteins/complexes. To explore alternate approaches for identifying proteins in cryo-ET data we pursued a Graph Network and topologically invariant approach. Here, we report on a fast algorithm that classifies particles by searching for nuances of evolutionarily conversed motifs and the geometrical characteristics of protein structure. GRIP-Tomo 2.0 is a machine-learning pipeline that extracts interpretable topological features of protein structures within noisy experimental backgrounds. Compared to version 1.0, the new pipeline includes three upgrades that significantly improve performance including synthetic tomogram generation simulating realistic noise, graph-based persistent feature extraction as protein fingerprints, and high-performance computing acceleration. GRIP-Tomo 2.0 achieves over 90% accuracy in classifying between proteins and noise using both real and synthetic datasets which represents a foundational step toward advancing cryo-ET workflows and empowering automated visual proteomics.

Li, Chengxuan↗

DOE OSTI2023

A Search for Extragalactic Fast Blue Optical Transients in ZTF and the Rate of AT2018cow-like Transients

We present a search for extragalactic fast blue optical transients (FBOTs) during Phase I of the Zwicky Transient Facility (ZTF). We identify 38 candidates with durations above half-maximum light 1 day < t 1/2 < 12 days, of which 28 have blue ( g – r ≲ –0.2 mag) colors at peak light. Of the 38 transients (28 FBOTs), 19 (13) can be spectroscopically classified as core-collapse supernovae (SNe): 11 (8) H- or He-rich (Type II/IIb/Ib) SNe, 6 (4) interacting (Type IIn/Ibn) SNe, and 2 (1) H&He-poor (Type Ic/Ic-BL) SNe. Two FBOTs (published previously) had predominantly featureless spectra and luminous radio emission: AT2018lug (The Koala) and AT2020xnd (The Camel). Seven (five) did not have a definitive classification: AT 2020bdh showed tentative broad H α in emission, and AT 2020bot showed unidentified broad features and was 10 kpc offset from the center of an early-type galaxy. Ten (eight) have no spectroscopic observations or redshift measurements. We present multiwavelength (radio, millimeter, and/or X-ray) observations for five FBOTs (three Type Ibn, one Type IIn/Ibn, one Type IIb). Additionally, we search radio-survey (VLA and ASKAP) data to set limits on the presence of radio emission for 24 of the transients. All X-ray and radio observations resulted in nondetections; we rule out AT2018cow-like X-ray and radio behavior for five FBOTs and more luminous emission (such as that seen in the Camel) for four additional FBOTs. We conclude that exotic transients similar to AT2018cow, the Koala, and the Camel represent a rare subset of FBOTs and use ZTF’s SN classification experiments to measure the rate to be at most 0.1% of the local core-collapse SN rate.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

Detecting Quantum Critical Points of Correlated Systems by Quantum Convolutional Neural Network Using Data from Variational Quantum Eigensolver

Machine learning has been applied to a wide variety of models, from classical statistical mechanics to quantum strongly correlated systems, for classifying phase transitions. The recently proposed quantum convolutional neural network (QCNN) provides a new framework for using quantum circuits instead of classical neural networks as the backbone of classification methods. We present the results from training the QCNN by the wavefunctions of the variational quantum eigensolver for the one-dimensional transverse field Ising model (TFIM). We demonstrate that the QCNN identifies wavefunctions corresponding to the paramagnetic and ferromagnetic phases of the TFIM with reasonable accuracy. The QCNN can be trained to predict the corresponding ‘phase’ of wavefunctions around the putative quantum critical point even though it is trained by wavefunctions far away. The paper provides a basis for exploiting the QCNN to identify the quantum critical point.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2023

Classification Analytics of Pu-239 and U-235 Source Signatures Using Gamma Spectral Regions

Machine learning detection methods using gamma signatures from spectral measurements of low-intensity Pu-239 and U-235 sources are studied. NaI detectors located at different distances fromthe source have been used to collect the training and independent testing data sets. The source is introduced via a shielded conduit into the facility where it is surrounded by 21 NaI detectors deployed over 6 x 6 meters area in the formation of two concentric circles and a spiral. The counts in gamma spectral regions associated with these two sources are estimated at 1 second intervals for each NaI detector, and are used as classifier features for detecting the source presence. Eight different classifiers with five basic properties — namely, smooth, non-smooth, statistical, structural, and hyper-parameter tuning — are trained and tested using the background and source measurements collected over multiple experimental runs. While the overall classifier performance improved as detectors closer to the source are used, some identically produced detectors under-performed but differently between two sources. Some classifiers achieved lower training error but their testing error based on independent measurements is higher for both sources. Overall, these results indicate significant over-fitting by these methods, and illustrate the complexity of training and selecting the machine learning methods to solve these detection problems.

Rao, Nageswara↗

DOE OSTI2026

Bayesian Optimization of Catalysis with In-Context Learning

Large language models (LLMs) can perform accurate classification with zero or few examples through in-context learning (ICL), allowing the model to observe query-relevant examples at inference time and eliminating the need for additional weight updates to generalize beyond its original training data. We extend this capability to regression with uncertainty estimation using frozen LLMs (e.g., GPT-4o, Gemini), enabling Bayesian optimization (BO) in natural language without explicit model training or feature engineering. We apply this to materials discovery by representing materials as synthesis and testing procedures for use in natural language prompts. This Bayesian, design-first approach prioritizes optimization toward target material properties before detailed characterization, in contrast to conventional experimental workflows that often emphasize characterization of suboptimal materials. On benchmarks like aqueous solubility and oxidative coupling of methane (OCM), BO-ICL matches or outperforms Gaussian processes. In live experiments on the reverse water–gas shift (RWGS) reaction, BO-ICL identifies multimetallic catalysts that approach equilibrium CO yield within 6 and 10 iterations from a pool of 3,700 and 360,000 candidates, respectively. Our method redefines materials representation and accelerates discovery, with broad applications across catalysis, materials science, and AI.

Calibration↗

DOE OSTI2026

Plutonium Retention by Crystalline Silicotitanate under Hyperalkaline Conditions Relevant to Tank-Side Cesium-Removal at the Hanford Site

Crystalline silicotitanate (CST) is used in Hanford’s Tank-Side Cesium-Removal (TSCR) process to selectively remove Cs-137 from highly caustic, nitrate-rich tank supernatants. Recent testing with actual waste samples suggests that CST can also retain measurable plutonium (Pu), which could affect radiological classification and disposal pathways for spent CST. To quantify this behavior, Pu partitioning to CST was studied under Hanford-relevant conditions using batch-contact experiments in a representative simulant (2 M NaNO3, 0.7 M NaOH). Isotherm data were measured and distribution ratios calculated, with Cs+ uptake used as benchmark. Under low-carbonate conditions, Pu was retained strongly by CST in systems initially contacted with either PuO2 nanoparticles (Pu(IV)) or aqueous Pu(VI), with distribution ratios of ~2,200–3,700 mL/g, generally exceeding those for Cs+ (~400–1,000 mL/g). Increasing carbonate concentration strongly reduced PuO2 nanoparticle retention; at [Na2CO3] = 1 M, distribution ratios decreased by up to one order of magnitude to roughly 100–300 mL/g. Electron microscopy suggests that Pu retention involves a combination of mechanisms such as PuO2 NP aggregation induced by CST leachate components, and association with CST bead surfaces.

Neumann, J.↗

DOE OSTI2021

Parameterization of arctic hydrometeor physics using new precipitation measurement technologies: Final Report

Predictions of precipitation are highly sensitive to the accuracy of parameterized growth and sedimentation processes, especially in remote regions such as the Arctic where observations are scarce. The goal of this study was to combine measurements of meteorological conditions and retrievals from passive and active remote sensors to provide refined parameterizations of precipitation properties and processes with a particular focus on the Arctic. To accomplish the project goals, new instrumentation was used from the Oliktok Point Mobile Facility and the Utqiagvik (Barrow) North Slope of Alaska ARM site focusing in particular on Multi-Angle Snowflake Camera (MASC) data. The MASC is the first device able to automatically photograph precipitation particles in free-fall from multiple angles while simultaneously measuring their fall speed. The MASC installed at the ARM Oliktok Point and Utqiagvik facilities was used to examine the nature of Arctic precipitation, taking particular advantage of the unique suite of precipitation, meteorological, and remote sensing instrumentation that is available at the high latitude sites. Combined with radiometer data we were able to explore the relationship between precipitation particle characteristics and the clouds where the snow is created. Ground-based wind measurements provided detailed data on turbulence. Further theoretical work explored the physical mechanisms controlling precipitation size distributions, the physics determining hydrometeor fallspeed, and the existence of general solutions to the Navier-Stokes equations for falling particles. Outreach work introduced hydrometeor classification to classrooms across the United States.

47 OTHER INSTRUMENTATION↗

DOE OSTI2023

Partitioning of Radionuclides in Various Streams of the Mo-99 Purification Process

The Universal Neutron Irradiator (UNI) was designed to irradiate a small volume of uranium solution and to achieve high fission power without creating a large radionuclide (RN) inventory. The UNI system is equipped with a fully enclosed off-gas system with online hydrogen gas monitoring to prevent the production of an explosive atmosphere, as well as storage cylinders for capturing fission gases. It also includes a catalytic recombiner in the target capsule (to immediately recombine radiolytic hydrogen and oxygen gas in the system) and access ports for sampling the target solution and capsule headspace. In UNI Phase I experiments, 50 mL of uranyl sulfate solution was irradiated at 0.3–0.5 W/mL fission power using a tantalum target assembly to produce photoneutrons via irradiation with an electron beam. The purposes of the Phase I experiments were to test the efficacy of adding 200 ppm Fe 2+ to the target solution to prevent uranyl peroxide precipitation under representative irradiation conditions, and to monitor iodine speciation in the irradiated uranyl sulfate solution. The focus of the UNI Phase II experiments was to use an irradiated uranyl sulfate solution containing a mixture of fission products and monitor their distribution in various streams during the primary recovery column (titania-based column) that separates Mo-99 from uranium. Irradiations were designed to create sufficient activity for tracking their distribution in various processing streams using a combination of gamma counting and inductively coupled plasma mass spectrometry (ICP-MS) analyses. Obtained data will be used to better understand the composition of waste streams, accumulation of RN on the titania column, and identify what RNs accumulate in the uranyl sulfate solution. Furthermore, this knowledge will allow us to determine waste classifications for various streams produced during the Mo-99 purification process and develop an appropriate waste clean-up strategy.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2024

Radio Frequency Spectrum Audit to Inventory Private Cellular Base Station Infrastructure

The ever-changing cellular communication landscape makes it difficult to identify, map, and localize cellular base stations. Localizing cellular base stations provides various advantages, including information security, cybersecurity, spectrum management, and interference detection. For example, the MITRE ATT&CK® (Adversarial Tactics, Techniques, and Common Knowledge architecture) [1] and Common Attack Pattern Enumeration and Classification [2] emphasize the importance of being able to minimize the cyber security threat presented by unregulated private cellular base stations (PCBS). The majority of published research looks at the malicious use of PCBSs and focuses on using data retrieved from user equipment (UE), data obtained from an application on the UE, or data shared between the UE and a mobile network to locate it. This innovative strategy, however, focuses on the passively discovered uniqueness of radio frequency (RF) transmissions from commercial cellular infrastructure received in a designated monitoring position (DMP).

42 ENGINEERING↗

DOE OSTI2022

Implementation Aspects of Smart Grids Cyber-Security Cross-Layered Framework for Critical Infrastructure Operation

Communication networks in power systems are a major part of the smart grid paradigm. It enables and facilitates the automation of power grid operation as well as self-healing in contingencies. Such dependencies on communication networks, though, create a roam for cyber-threats. An adversary can launch an attack on the communication network, which in turn reflects on power grid operation. Attacks could be in the form of false data injection into system measurements, flooding the communication channels with unnecessary data, or intercepting messages. Using machine learning-based processing on data gathered from communication networks and the power grid is a promising solution for detecting cyber threats. In this paper, a co-simulation of cyber-security for cross-layer strategy is presented. The advantage of such a framework is the augmentation of valuable data that enhances the detection as well as identification of anomalies in the operation of the power grid. The framework is implemented on the IEEE 118-bus system. The system is constructed in Mininet to simulate a communication network and obtain data for analysis. A distributed three controller software-defined networking (SDN) framework is proposed that utilizes the Open Network Operating System (ONOS) cluster. According to the findings of our suggested architecture, it outperforms a single SDN controller framework by a factor of more than ten times the throughput. This provides for a higher flow of data throughout the network while decreasing congestion caused by a single controller’s processing restrictions. Furthermore, our CECD-AS approach outperforms state-of-the-art physics and machine learning-based techniques in terms of attack classification. The performance of the framework is investigated under various types of communication attacks.

cross-layered↗

DOE OSTI2020

Modeling and Detection of Future Cyber-Enabled DSM Data Attacks

Demand-Side Management (DSM) is an essential tool to ensure power system reliability and stability. In future smart grids, certain portions of a customer’s load usage could be under the automatic control of a cyber-enabled DSM program, which selectively schedules loads as a function of electricity prices to improve power balance and grid stability. In this scenario, the security of DSM cyberinfrastructure will be critical as advanced metering infrastructure and communication systems are susceptible to cyber-attacks. Such attacks, in the form of false data injections, can manipulate customer load profiles and cause metering chaos and energy losses in the grid. The feedback mechanism between load management on the consumer side and dynamic price schemes employed by independent system operators can further exacerbate attacks. To study how this feedback mechanism may worsen attacks in future cyber-enabled DSM programs, we propose a novel mathematical framework for (i) modeling the nonlinear relationship between load management and real-time pricing, (ii) simulating residential load data and prices, (iii) creating cyber-attacks, and (iv) detecting said attacks. In this framework, we first develop time-series forecasts to model load demand and use them as inputs to an elasticity model for the price-demand relationship in the DSM loop. This work then investigates the behavior of such a feedback loop under intentional cyber-attacks. We simulate and examine load-price data under different DSM-participation levels with three types of random additive attacks: ramp, sudden, and point attacks. We conduct two investigations for the detection of DSM attacks. The first studies a supervised learning approach, with various classification models, and the second studies the performance of parametric and nonparametric change point detectors. Results conclude that higher amounts of DSM participation can exacerbate ramp and sudden attacks leading to better detection of such attacks, especially with supervised learning classifiers. We also find that nonparametric detection outperforms parametric for smaller user pools, and random point attacks are the hardest to detect with any method.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Alert Classification for the ALeRCE Broker System: The Light Curve Classifier

We present the first version of the Automatic Learning for the Rapid Classification of Events (ALeRCE) broker light curve classifier. ALeRCE is currently processing the Zwicky Transient Facility (ZTF) alert stream, in preparation for the Vera C. Rubin Observatory. The ALeRCE light curve classifier uses variability features computed from the ZTF alert stream and colors obtained from AllWISE and ZTF photometry. We apply a balanced random forest algorithm with a two-level scheme where the top level classifies each source as periodic, stochastic, or transient, and the bottom level further resolves each of these hierarchical classes among 15 total classes. This classifier corresponds to the first attempt to classify multiple classes of stochastic variables (including core- and host-dominated active galactic nuclei, blazars, young stellar objects, and cataclysmic variables) in addition to different classes of periodic and transient sources, using real data. We created a labeled set using various public catalogs (such as the Catalina Surveys and Gaia DR2 variable stars catalogs, and the Million Quasars catalog), and we classify all objects with ≥6 g-band or ≥6 r-band detections in ZTF (868,371 sources as of 2020 June 9), providing updated classifications for sources with new alerts every day. For the top level we obtain macro-averaged precision and recall scores of 0.96 and 0.99, respectively, and for the bottom level we obtain macro-averaged precision and recall scores of 0.57 and 0.76, respectively. Updated classifications from the light curve classifier can be found at the ALeRCE Explorer website (http://alerce.online).

47 OTHER INSTRUMENTATION↗