Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning, Random Forest”

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 379 records · Page 21

SU-C-BRA-04: Automated Segmentation of Head-And-Neck CT Images for Radiotherapy Treatment Planning Via Multi-Atlas Machine Learning (MAML)

Purpose: Accurate image segmentation is a crucial step during image guided radiation therapy. This work proposes multi-atlas machine learning (MAML) algorithm for automated segmentation of head-and-neck CT images. Methods: As the first step, the algorithm utilizes normalized mutual information as similarity metric, affine registration combined with multiresolution B-Spline registration, and then fuses together using the label fusion strategy via Plastimatch. As the second step, the following feature selection strategy is proposed to extract five feature components from reference or atlas images: intensity (I), distance map (D), box (B), center of gravity (C) and stable point (S). The box feature B is novel. It describes a relative position from each point to minimum inscribed rectangle of ROI. The center-of-gravity feature C is the 3D Euclidean distance from a sample point to the ROI center of gravity, and then S is the distance of the sample point to the landmarks. Then, we adopt random forest (RF) in Scikit-learn, a Python module integrating a wide range of state-of-the-art machine learning algorithms as classifier. Different feature and atlas strategies are used for different ROIs for improved performance, such as multi-atlas strategy with reference box for brainstem, and single-atlas strategy with reference landmark for optic chiasm. Results: The algorithm was validated on a set of 33 CT images with manual contours using a leave-one-out cross-validation strategy. Dice similarity coefficients between manual contours and automated contours were calculated: the proposed MAML method had an improvement from 0.79 to 0.83 for brainstem and 0.11 to 0.52 for optic chiasm with respect to multi-atlas segmentation method (MA). Conclusion: A MAML method has been proposed for automated segmentation of head-and-neck CT images with improved performance. It provides the comparable result in brainstem and the improved result in optic chiasm compared with MA. Xuhua Ren and Hao Gao were partially supported by the NSFC (#11405105), the 973 Program (#2015CB856000), and the Shanghai Pujiang Talent Program (#14PJ1404500).

60 APPLIED LIFE SCIENCES↗

Temporal regulation of cold transcriptional response in switchgrass

Switchgrass low-land ecotypes have significantly higher biomass but lower cold tolerance compared to up-land ecotypes. Understanding the molecular mechanisms underlying cold response, including the ones at transcriptional level, can contribute to improving tolerance of high-yield switchgrass under chilling and freezing environmental conditions. Here, by analyzing an existing switchgrass transcriptome dataset, the temporal cis- regulatory basis of switchgrass transcriptional response to cold is dissected computationally. We found that the number of cold-responsive genes and enriched Gene Ontology terms increased as duration of cold treatment increased from 30 min to 24 hours, suggesting an amplified response/cascading effect in cold-responsive gene expression. To identify genomic sequences likely important for regulating cold response, machine learning models predictive of cold response were established using k -mer sequences enriched in the genic and flanking regions of cold-responsive genes but not non-responsive genes. These k -mers, referred to as putative cis -regulatory elements (pCREs) are likely regulatory sequences of cold response in switchgrass. There are in total 655 pCREs where 54 are important in all cold treatment time points. Consistent with this, eight of 35 known cold-responsive CREs were similar to top-ranked pCREs in the models and only these eight were important for predicting temporal cold response. More importantly, most of the top-ranked pCREs were novel sequences in cold regulation. Our findings suggest additional sequence elements important for cold-responsive regulation previously not known that warrant further studies.

60 APPLIED LIFE SCIENCES↗

Predicting Elastic Constants of Refractory Complex Concentrated Alloys Using Machine Learning Approach

Refractory complex concentrated alloys (RCCAs) have drawn increasing attention recently owing to their balanced mechanical properties, including excellent creep resistance, ductility, and oxidation resistance. The mechanical and thermal properties of RCCAs are directly linked with the elastic constants. However, it is time consuming and expensive to obtain the elastic constants of RCCAs with conventional trial-and-error experiments. The elastic constants of RCCAs are predicted using a combination of density functional theory simulation data and machine learning (ML) algorithms in this study. The elastic constants of several RCCAs are predicted using the random forest regressor, gradient boosting regressor (GBR), and XGBoost regression models. Based on performance metrics R-squared, mean average error and root mean square error, the GBR model was found to be most promising in predicting the elastic constant of RCCAs among the three ML models. Additionally, GBR model accuracy was verified using the other four RHEAs dataset which was never seen by the GBR model, and reasonable agreements between ML prediction and available results were found. The present findings show that the GBR model can be used to predict the elastic constant of new RHEAs more accurately without performing any expensive computational and experimental work.

36 MATERIALS SCIENCE↗

Reducing Uncertainty in Offshore Wind Energy Yield Estimates via a Metocean Reference Site

The offshore wind industry is burgeoning in the coastal waters of the United States, specifically along the Atlantic. For wind energy to be successful, reliable observations and model simulations are needed for resource assessment and forecasting. While many of these activities have already begun, there is currently an absence of observations at hub-height in these waters, with the closest available hub-height measurements usually taken onshore. Deployment of floating lidars has occurred through various federally funded projects, but only encapsulates time periods of a couple of years at best. Private industry is also beginning to leverage floating lidars, but this data is often proprietary, and not shared with the general public. In this work, we make the case for a metocean reference site for long-term offshore wind energy. Specifically, we quantify the impact of having a metocean reference site compared to other methods of determining hub-height winds and energy production. We use an offshore floating lidar to directly measure the wind resource, and compare these measurements to predictions derived from other widely-available surface meteorological variables. These prediction methods (vertical extrapolation, machine learning, and NWP output) produce a variety of vertical wind speed profiles, of which produce different energy yield estimates for a reference offshore turbine (Figure 1). While some methods perform reasonably well against the lidar, the uncertainty in these energy yield estimates has financial implications, further illustrating the need for long-term measurements in coastal waters.

machine learning↗

Modeling the Impact of Baryons on Subhalo Populations with Machine Learning

Here, we identify subhalos in dark matter–only (DMO) zoom-in simulations that are likely to be disrupted due to baryonic effects by using a random forest classifier trained on two hydrodynamic simulations of Milky Way (MW)–mass host halos from the Latte suite of the Feedback in Realistic Environments (FIRE) project. We train our classifier using five properties of each disrupted and surviving subhalo: pericentric distance and scale factor at first pericentric passage after accretion and scale factor, virial mass, and maximum circular velocity at accretion. Our five-property classifier identifies disrupted subhalos in the FIRE simulations with an 85% out-of-bag classification score. We predict surviving subhalo populations in DMO simulations of the FIRE host halos, finding excellent agreement with the hydrodynamic results; in particular, our classifier outperforms DMO zoom-in simulations that include the gravitational potential of the central galactic disk in each hydrodynamic simulation, indicating that it captures both the dynamical effects of a central disk and additional baryonic physics. We also predict surviving subhalo populations for a suite of DMO zoom-in simulations of MW-mass host halos, finding that baryons impact each system consistently and that the predicted amount of subhalo disruption is larger than the host-to-host scatter among the subhalo populations. Although the small size and specific baryonic physics prescription of our training set limits the generality of our results, our work suggests that machine-learning classification algorithms trained on hydrodynamic zoom-in simulations can efficiently predict realistic subhalo populations.

79 ASTRONOMY AND ASTROPHYSICS↗

Using Machine Learning to Discern Eruption in Noisy Environments: A Case Study Using CO2-Driven Cold-Water Geyser in Chimayó, New Mexico

In this paper, we present an approach based on machine learning (ML) to distinguish eruption and precursory signals of Chimayó geyser (New Mexico, U.S.A.) under noisy environmental conditions. This geyser can be considered a natural analog of CO 2 intrusion into shallow water aquifers. By studying this geyser, we can understand upwelling of CO 2 -rich fluids from depth, which has relevance to leak monitoring in a CO 2 sequestration project. ML methods such as random forests (RFs) are known to be robust multiclass classifiers and perform well under unfavorable, noisy conditions. However, the extent of the RF method’s accuracy is poorly understood for this CO 2 -driven geysering application. The current study aims to quantify the performance of RF classifiers to discern the geyser state. Toward this goal, we first present the data collected from the seismometer that is installed near the Chimayó geyser. The seismic signals collected at this site contain different types of noises such as daily temperature variations, animal movement near the geyser, and human activity. First, we filter the signals from these noises by combining the Butterworth high-pass (BH) filter and an autoregressive (AR) method in a multilevel fashion. We show that by combining these filtering techniques in a hierarchical fashion leads to a reduction in noise in the seismic data without removing the precursors and eruption event signals. We then use RF on the filtered data to classify the state of geyser into three classes: remnant noise, precursor, and eruption states. RF classifier is constructed based on the comprehensive features extracted using the Tsfresh Python package. We show that the classification accuracy using RF on the filtered data is greater than 90%. We also evaluate the accuracy of other classical time-series methods such as dynamic time warping (DTW) on filtered data along with RF on partially filtered data in which we remove the daily trends. Classification accuracy shows that DTW performs poorly (44%) and RF on partially filtered data performs decently (87%). Denoising seismic signals from both daily trends and human activity enhances RF classifier performance by 7%. Finally, these aspects make the proposed ML framework attractive for event discrimination and signal enhancement under noisy conditions, with strong potential for application to monitor leaks in CO 2 sequestration.

58 GEOSCIENCES↗

Single Cell RNA-Seq and Machine Learning Reveal Novel Subpopulations in Low-Grade Inflammatory Monocytes With Unique Regulatory Circuits

Subclinical doses of LPS (SD-LPS) are known to cause low-grade inflammatory activation of monocytes, which could lead to inflammatory diseases including atherosclerosis and metabolic syndrome. Sodium 4-phenylbutyrate is a potential therapeutic compound which can reduce the inflammation caused by SD-LPS. To understand the gene regulatory networks of these processes, we have generated scRNA-seq data from mouse monocytes treated with these compounds and identified 11 novel cell clusters. We have developed a machine learning method to integrate scRNA-seq, ATAC-seq, and binding motifs to characterize gene regulatory networks underlying these cell clusters. Using guided regularized random forest and feature selection, our method achieved high performance and outperformed a traditional enrichment-based method in selecting candidate regulatory genes. Our method is particularly efficient in selecting a few candidate genes to explain observed expression pattern. In particular, among 531 candidate TFs, our method achieves an auROC of 0.961 with only 10 motifs. Finally, we found two novel subpopulations of monocyte cells in response to SD-LPS and we confirmed our analysis using independent flow cytometry experiments. Our results suggest that our new machine learning method can select candidate regulatory genes as potential targets for developing new therapeutics against low grade inflammation.

60 APPLIED LIFE SCIENCES↗

Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST

In this paper, we report on disruption prediction using a shallow machinelearning method known as Random Forests, trained on large databases containingonly plasma parameters that are available in real-time on Alcator C-Mod, DIII-D, and EAST. The database for each tokamak contains parameters sampled ~10 6 times throughout ~10 4 discharges (disruptive and non-disruptive) over the last 4years of operation. It is found that a number of parameters (e.g.P rad /P input ,l i ,n/n G ,B n=1 /B 0 ) exhibit changes in aggregate as a disruption is approached on one ormore of these tokamaks. However, for each machine, the most useful parameters,as well as the details of their precursor behaviors, are markedly different. When the prediction problem is framed using a binary classification scheme to discriminate between time slices "close to disruption" and "far from disruption," it is found that the prediction algorithms differ substantially in performance among the three machines ona time slice-by-time slice basis, but have similar disruption detection rates (~80-90%) on a shot-by-shot basis after appropriate optimisation. This could have important implications for disruption prediction and avoidance on ITER, for which developmentof a training database of disruptions may be infeasible. The algorithm's output is interpretable using a method that identifies the most strongly contributing inputsignals, which may have implications for avoiding disruptive scenarios. Lastly, to further support its real-time capability, successful applications in inter-shot and real-time environments on EAST and DIII-D are also discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Machine Learning Models for Mapping Groundwater Pollution Risk: Advancing Water Security and Sustainable Development Goals in Georgia, USA

The widespread use of pesticides, such as atrazine and malathion, in agricultural systems raises significant concerns regarding the contamination of groundwater, which serves as a critical resource for drinking water. This study applies machine learning techniques to predict the concentrations of atrazine and malathion in groundwater across Georgia, USA, using 2019 data. A Random Forest classifier was employed to integrate various environmental and demographic factors, including pesticide application rates, precipitation, lithology, and population density, to predict pesticide contamination in groundwater. The models demonstrated high training accuracies of 100% and moderate average testing accuracy of 55% for atrazine and 60% for malathion across five iterations. The low test accuracy of the model, ranging from 50% to 75%, is likely due to overfitting, which can be attributed to the small dataset size and the complex nature of pesticide-contamination patterns, making it challenging for the model to generalize to unseen data. Feature importance analysis revealed that average pesticide usage emerged as the most influential factor for atrazine, while aquifer lithology and precipitation played crucial roles in both models. These results provide valuable insights into the dynamics of pesticide contamination, highlighting areas at greater risk of contamination. The findings underscore the importance of integrating environmental, geological, and agricultural variables for more effective groundwater management and sustainable agricultural practices, contributing to the protection of water resources and public health.

54 ENVIRONMENTAL SCIENCES↗

Invasion in the Niger Delta: Remote Sensing of Mangrove Conversion to Invasive Nypa fruticans from 2015-2020

Invasive species are a leading threat to biodiversity worldwide. Nypa palm ( Nypa fruticans ) has emerged as the predominant invasive species in the Niger Delta region of Nigeria. While endemic mangroves have high rates of carbon sequestration, stabilize coastlines, and protect biodiversity, Nypa does not provide these services outside its native region of Southeast Asia. Oil exploration and urbanization in this region also exacerbates mangrove loss and Nypa spread. As Nypa is difficult to distinguish from endemic mangrove species in remotely sensed data, estimates of mangrove and ecosystem services losses in Nigeria are highly uncertain. Here, we analyze multisensor satellite data with machine learning to quantify the rapid expansion of Nypa from 2015-2020 in Nigeria. Using Landsat imagery and random forest classification, we quantify total potential Nypa extent in Nigeria in 2019. We then produced a Nypa extent map using iterative combinations of Sentinel-1 SAR, Sentinel-2 MSI, and ALOS PALSAR. Random forest classifications using SAR data from ALOS and Sentinel-1 were best suited for mapping Nypa extent with similar accuracies (78% and 75% respectively). Based on data availability and accuracy, we focused our change analysis on Sentinel-1 SAR. Our results show ~28,000 ha of mangroves were converted to Nypa in Nigeria by 2020 and covered a larger extent than endemic mangroves, compounding the effect of the existing degradation and deforestation in the region. We also compared forest height and complexity estimates from GEDI (Global Ecosystem Dynamics Investigation) LiDAR to further distinguish between endemic mangroves and Nypa in three dimensions. Nypa structural variability, measured by top-of-canopy height, vegetation cover, plant area index, and foliage height diversity, was lower than that of mangroves. At current rates of Nypa expansion, the entire area of study would be invaded by Nypa by 2028, with potentially detrimental consequences to the ecosystem services provided by mangroves.

GEE↗

Detecting Arsenic Contamination Using Satellite Imagery and Machine Learning

Arsenic, a potent carcinogen and neurotoxin, affects over 200 million people globally. Current detection methods are laborious, expensive, and unscalable, being difficult to implement in developing regions and during crises such as COVID-19. This study attempts to determine if a relationship exists between soil’s hyperspectral data and arsenic concentration using NASA’s Hyperion satellite. It is the first arsenic study to use satellite-based hyperspectral data and apply a classification approach. Four regression machine learning models are tested to determine this correlation in soil with bare land cover. Raw data are converted to reflectance, problematic atmospheric influences are removed, characteristic wavelengths are selected, and four noise reduction algorithms are tested. The combination of data augmentation, Genetic Algorithm, Second Derivative Transformation, and Random Forest regression (R 2 =0.840 and normalized root mean squared error (re-scaled to [0,1]) = 0.122) shows strong correlation, performing better than past models despite using noisier satellite data (versus lab-processed samples). Three binary classification machine learning models are then applied to identify high-risk shrub-covered regions in ten U.S. states, achieving strong accuracy (=0.693) and F1-score (=0.728). Overall, these results suggest that such a methodology is practical and can provide a sustainable alternative to arsenic contamination detection.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗

Modeling freight mode choice using machine learning classifiers: a comparative study using Commodity Flow Survey (CFS) data

This study explores the usefulness of machine learning classifiers for modeling freight mode choice. We investigate eight commonly used machine learning classifiers, namely Naïve Bayes, Support Vector Machine, Artificial Neural Network, K-Nearest Neighbors, Classification and Regression Tree, Random Forest, Boosting and Bagging, along with the classical Multinomial Logit model. US 2012 Commodity Flow Survey data are used as the primary data source; we augment it with spatial attributes from secondary data sources. The performance of the classifiers is compared based on prediction accuracy results. The current research also examines the role of sample size and training-testing data split ratios on the predictive ability of the various approaches. In addition, the importance of variables is estimated to determine how the variables influence freight mode choice. The results show that the tree-based ensemble classifiers perform the best. Specifically, Random Forest produces the most accurate predictions, closely followed by Boosting and Bagging. With regard to variable importance, shipment characteristics, such as shipment distance, industry classification of the shipper and shipment size, are the most significant factors for freight mode choice decisions.

42 ENGINEERING↗

Monitoring covariance in multivariate time series: Comparing machine learning and statistical approaches

Abstract In complex systems with multiple variables monitored at high‐frequency, variables are not only temporally autocorrelated, but they may also be nonlinearly related or exhibit nonstationarity as the inputs or operation changes. One approach to handling such variables is to detrend them prior to monitoring and then apply control charts that assume independence and stationarity to the residuals. Monitoring controlled systems is even more challenging because the control strategy seeks to maintain variables at prespecified mean levels, and to compensate, correlations among variables may change, making monitoring the covariance essential. In this paper, a vector autoregressive model (VAR) is compared with a multivariate random forest (MRF) and a neural network (NN) for detrending multivariate time series prior to monitoring the covariance of the residuals using a multivariate exponentially weighted moving average (MEWMA) control chart. Machine learning models have an advantage when the data's structure is unknown or may change. We design a novel simulation study with nonlinear, nonstationary, and autocorrelated data to compare the different detrending models and subsequent covariance monitoring. The machine learning models have superior performance for nonlinear and strongly autocorrelated data and similar performance for linear data. An illustration with data from a reverse osmosis process is given.

Weix, Derek↗

Characterization and prediction of the electromechanical wear of contact tips during wire arc additive manufacturing of 316L stainless steel

Here, this study seeks to better understand the degradation of the contact tip with respect to WAAM for a 316L wire electrode as well as explore methods of monitoring the contact tip state from process data. The contact tip, a consumable component, positions the wire and serves as the electrical contact surface between the wire electrode and the welding power supply. The wear of the contact tip was characterized in terms of material loss and material contamination for a set of tips worn to discrete levels as measured by the amount of wire fed or arc time. Geometrical characterization found a 49% increase in the bore exit area at 180 meters of wire fed. Machine learning models were developed to predict the relative bore exit area of the contact tip from arc-based process data and a random forest classifier exhibited favorable performance with a cross-validated f1-score of 0.84. The regression architecture implemented a multi-layer perceptron with the ability to predict the relative exit area with an $R^2$ score of 0.75. Key features used in the prediction include the standard deviation of the voltage and the time between shorts.

Contact tip wear↗

Machine learning prediction of incidence of Alzheimer’s disease using large-scale administrative health data

Nationwide population-based cohort provides a new opportunity to build an automated risk prediction model based on individuals’ history of health and healthcare beyond existing risk prediction models. We tested the possibility of machine learning models to predict future incidence of Alzheimer’s disease (AD) using large-scale administrative health data. From the Korean National Health Insurance Service database between 2002 and 2010, we obtained de-identified health data in elders above 65 years (N = 40,736) containing 4,894 unique clinical features including ICD-10 codes, medication codes, laboratory values, history of personal and family illness and socio-demographics. To define incident AD we considered two operational definitions: “definite AD” with diagnostic codes and dementia medication (n = 614) and “probable AD” with only diagnosis (n = 2026). We trained and validated random forest, support vector machine and logistic regression to predict incident AD in 1, 2, 3, and 4 subsequent years. For predicting future incidence of AD in balanced samples (bootstrapping), the machine learning models showed reasonable performance in 1-year prediction with AUC of 0.775 and 0.759, based on “definite AD” and “probable AD” outcomes, respectively; in 2-year, 0.730 and 0.693; in 3-year, 0.677 and 0.644; in 4-year, 0.725 and 0.683. The results were similar when the entire (unbalanced) samples were used. Important clinical features selected in logistic regression included hemoglobin level, age and urine protein level. This study may shed a light on the utility of the data-driven machine learning model based on large-scale administrative health data in AD risk prediction, which may enable better selection of individuals at risk for AD in clinical trials or early detection in clinical settings.

97 MATHEMATICS AND COMPUTING↗

Semi-supervised machine-learning classification of materials synthesis procedures

Digitizing large collections of scientific literature can enable new informatics approaches for scientific analysis and meta-analysis. However, most content in the scientific literature is locked-up in written natural language, which is difficult to parse into databases using explicitly hard-coded classification rules. In this work, we demonstrate a semi-supervised machine-learning method to classify inorganic materials synthesis procedures from written natural language. Without any human input, latent Dirichlet allocation can cluster keywords into topics corresponding to specific experimental materials synthesis steps, such as “grinding” and “heating”, “dissolving” and “centrifuging”, etc. Guided by a modest amount of annotation, a random forest classifier can then associate these steps with different categories of materials synthesis, such as solid-state or hydrothermal synthesis. Finally, we show that a Markov chain representation of the order of experimental steps accurately reconstructs a flowchart of possible synthesis procedures. Our machine-learning approach enables a scalable approach to unlock the large amount of inorganic materials synthesis information from the literature and to process it into a standardized, machine-readable database.

36 MATERIALS SCIENCE↗

A bi-level data-driven framework for fault-detection and diagnosis of HVAC systems

Long-term operation of heating, ventilation, and air conditioning (HVAC) systems will eventually lead to a range of HVAC system failures, resulting in excessive energy consumption and maintenance costs. Here, to avoid HVAC malfunctioning, fault detection diagnostic (FDD) is utilized as a common practice. Machine learning methods have lately received considerable interest for FDD analysis of HVAC systems due to their high detection accuracy. Meanwhile, HVAC malfunctions are regarded as rare occurrences, hence normal operating data samples are much more accessible than data samples in faulty and malfunctioning conditions. The dominating frequency of normal operation in HVAC datasets has also led to heavily biased classification algorithms within the literature. Moreover, the focus of previous literature has been on increasing the accuracy of the models which leads to a high number of false positives (misleading alarms) in the system. In order to enhance the performance of diagnostic procedures and fill the mentioned gaps, this study proposes a novel data-driven framework. A bi-level machine learning framework is developed for diagnosing faults in air handling units (AHUs) and rooftop units (RTUs) based on principal component analysis (PCA), time series anomaly detection, and random forest (RF). It is shown that PCA can reduce the dataset dimension with one principal component accounting for 95% of data variance. Also, the random forest could classify the faults with 89% precision for single-zone AHU, 85% precision for RTU, and 79% for multi-zone AHU. By proposing this framework, three persistent challenges are addressed: (I) minimizing false positives; (II) accounting for data imbalance; and (III) normal condition monitoring of equipment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Machine- z : Rapid machine-learned redshift indicator for Swift gamma-ray bursts

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here, we introduce ‘machine-z’, a redshift prediction algorithm and a ‘high-z’ classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time, our high-z classifier can achieve 80 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve ~100 per cent recall. As a result, the most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

79 ASTRONOMY AND ASTROPHYSICS↗