Search NASA⌕ Search

SEARCH · Search NASA

Results for “Featurization”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS1985

Spectroscopy of the 3 micron emission features

High-spectral-resolution observations of the 3.3 and 3.4 microns features in the three planetary nebulae NGC 7027, IC 418, and BD +30 deg 3639, in the H II region S106, and in the 'red rectangle' HD 44179 are presented. The profile of the unidentified 3.3 microns emission feature is similar in all five sources. The unidentified feature previously referred to as the 3.4 microns feature actually consists of two components, a low-level emission from 3.35 to 3.60 microns and a narrow emission peak at 3.40 microns. The strength of the latter feature relative to that of the 3.3 microns feature varies by a a factor of three from source to source. The origin and properties of these features may be explained by further development of the small-grain models of Sellgren (1984) and Leger and Puget (1984).

Geballe, T. R.↗
NASA NTRS1988

Spectral feature design in high dimensional multispectral data

The High resolution Imaging Spectrometer (HIRIS) is designed to acquire images simultaneously in 192 spectral bands in the 0.4 to 2.5 micrometers wavelength region. It will make possible the collection of essentially continuous reflectance spectra at a spectral resolution sufficient to extract significantly enhanced amounts of information from return signals as compared to existing systems. The advantages of such high dimensional data come at a cost of increased system and data complexity. For example, since the finer the spectral resolution, the higher the data rate, it becomes impractical to design the sensor to be operated continuously. It is essential to find new ways to preprocess the data which reduce the data rate while at the same time maintaining the information content of the high dimensional signal produced. Four spectral feature design techniques are developed from the Weighted Karhunen-Loeve Transforms: (1) non-overlapping band feature selection algorithm; (2) overlapping band feature selection algorithm; (3) Walsh function approach; and (4) infinite clipped optimal function approach. The infinite clipped optimal function approach is chosen since the features are easiest to find and their classification performance is the best. After the preprocessed data has been received at the ground station, canonical analysis is further used to find the best set of features under the criterion that maximal class separability is achieved. Both 100 dimensional vegetation data and 200 dimensional soil data were used to test the spectral feature design system. It was shown that the infinite clipped versions of the first 16 optimal features had excellent classification performance. The overall probability of correct classification is over 90 percent while providing for a reduced downlink data rate by a factor of 10.

Chen, Chih-Chien Thomas↗
NASA NTRS1989

Cloud field classification based on textural features

An essential component in global climate research is accurate cloud cover and type determination. Of the two approaches to texture-based classification (statistical and textural), only the former is effective in the classification of natural scenes such as land, ocean, and atmosphere. In the statistical approach that was adopted, parameters characterizing the stochastic properties of the spatial distribution of grey levels in an image are estimated and then used as features for cloud classification. Two types of textural measures were used. One is based on the distribution of the grey level difference vector (GLDV), and the other on a set of textural features derived from the MaxMin cooccurrence matrix (MMCM). The GLDV method looks at the difference D of grey levels at pixels separated by a horizontal distance d and computes several statistics based on this distribution. These are then used as features in subsequent classification. The MaxMin tectural features on the other hand are based on the MMCM, a matrix whose (I,J)th entry give the relative frequency of occurrences of the grey level pair (I,J) that are consecutive and thresholded local extremes separated by a given pixel distance d. Textural measures are then computed based on this matrix in much the same manner as is done in texture computation using the grey level cooccurrence matrix. The database consists of 37 cloud field scenes from LANDSAT imagery using a near IR visible channel. The classification algorithm used is the well known Stepwise Discriminant Analysis. The overall accuracy was estimated by the percentage or correct classifications in each case. It turns out that both types of classifiers, at their best combination of features, and at any given spatial resolution give approximately the same classification accuracy. A neural network based classifier with a feed forward architecture and a back propagation training algorithm is used to increase the classification accuracy, using these two classes of features. Preliminary results based on the GLDV textural features alone look promising.

Sengupta, Sailes Kumar↗
NASA NTRS1989

Spatial variations of the 3 micron emission features within nebulae

The 3 micron spectra is presented for the Orion bar region and the Red Rectangle. In both objects spectra were obtained at more than one location, corresponding to different distances from the excitation source. The well known 3.3 and 3.4 micron emission bands are seen in both objects as well as the recently discovered features at 3.46, 3.51, and 3.57 microns in the Orion bar spectra. The spectra show that the relative strengths of the 3 micron emission features vary within the Orion bar. As distance from the exciting star increases, the 3.4 and 3.51 micron features increase, and the 3.46 micron feature decreases in strength, relative to the strong 3.3 micron feature. These are two possible interpretations which are postulated, each of which involves the breaking of bonds by UV radiation, which removes the modes responsible for the 3.4 micron emission near the star. The two possible bond ruptures are the CH bond in small polycyclic aromatic hydrocarbons (PAHs), or the bond to an aliphatic subgroup. It has to be pointed out that neither interpretation appears entirely satisfactory. The vibrational overtone interpretation cannot explain the presence or behavior of the 3.46 micron feature, whereas the laboratory spectra of aliphatic sidegroups contain many more features in the 3 micron region than are observed in the astronomical sources.

Moorhouse, Alan↗
NASA NTRS1991

IRAS low-resolution spectral observations of the 10 and 18 micron silicate emission feature

The IRAS LRS Atlas contains 8-23 micron spectra of 1816 stars with silicate emission features. In order to study the shapes of the silicate dust features, the 117 stars whose emission features appear to be optically thin and which have the best signal-to-noise ratio at the longest wavelengths were analyzed. Simple spherical dust shell models were calculated in both the optically thin and the slightly optical thick approximations. From the comparison of the predicted spectra of the dust and stellar continuum, the emissivity function Kappa(lambda) was derived. In the different stars, the shape of the 10-micron feature is either narrow or broad and it is peaked either at about 9.7 microns or at 10 microns. Either particle size effects (particles above 0.75 microns in radius) or optical depth effects (central optical depth about 1) could broaden the 10-micron feature. Chemical composition differences no doubt are also important, particularly as regards the position of the peak of the 10-micron feature. The stars with the peak at 10 microns are more closely confined to the Galactic plane than the stars with the peak at 9.7 microns. The shape of the 18-micron feature is essentially the same in all stars, and can be used to extend the interstellar extinction curve past 13 to 22 microns.

Simpson, Janet P.↗
NASA NTRS1993

Feature extraction and classification algorithms for high dimensional data

Feature extraction and classification algorithms for high dimensional data are investigated. Developments with regard to sensors for Earth observation are moving in the direction of providing much higher dimensional multispectral imagery than is now possible. In analyzing such high dimensional data, processing time becomes an important factor. With large increases in dimensionality and the number of classes, processing time will increase significantly. To address this problem, a multistage classification scheme is proposed which reduces the processing time substantially by eliminating unlikely classes from further consideration at each stage. Several truncation criteria are developed and the relationship between thresholds and the error caused by the truncation is investigated. Next an approach to feature extraction for classification is proposed based directly on the decision boundaries. It is shown that all the features needed for classification can be extracted from decision boundaries. A characteristic of the proposed method arises by noting that only a portion of the decision boundary is effective in discriminating between classes, and the concept of the effective decision boundary is introduced. The proposed feature extraction algorithm has several desirable properties: it predicts the minimum number of features necessary to achieve the same classification accuracy as in the original space for a given pattern recognition problem; and it finds the necessary feature vectors. The proposed algorithm does not deteriorate under the circumstances of equal means or equal covariances as some previous algorithms do. In addition, the decision boundary feature extraction algorithm can be used both for parametric and non-parametric classifiers. Finally, some problems encountered in analyzing high dimensional data are studied and possible solutions are proposed. First, the increased importance of the second order statistics in analyzing high dimensional data is recognized. By investigating the characteristics of high dimensional data, the reason why the second order statistics must be taken into account in high dimensional data is suggested. Recognizing the importance of the second order statistics, there is a need to represent the second order statistics. A method to visualize statistics using a color code is proposed. By representing statistics using color coding, one can easily extract and compare the first and the second statistics.

Lee, Chulhee↗
NASA NTRS2002

Discovery of Cyclotron Resonance Features in the Soft Gamma Repeater SGR 1806-20

We report evidence for cyclotron resonance features from the Soft Gamma Repeater SCR 1806-20 in outburst, detected with the Rossi X-ray Timing Explorer in the spectrum of a long, complex precursor that preceded a strong burst. The features consist of a narrow 5.0 keV absorption line with modulation near its second and third harmonics (at 11.2 keV and 17.5 keV respectively). The line features are transient and are detected in the harder part of the precursor. The 5.0 keV feature is strong, with an equivalent width of approx. 500 eV, and a narrow width of < 0.4 keV. Interpreting the features as electron cyclotron lines in the context of accretion models leads to a large mass-radius ratio (M/R > 0.3 Solar Mass/km) that is inconsistent with neutron stars, or requires a low (5 - 7) x 10(exp 11) G magnetic field that is unlikely for SGRs. The line widths are also narrow compared to those of electron cyclotron resonances observed so far in X-ray pulsars. In the magnetar picture, the features are plausibly explained as ion cyclotron resonances in an ultra-strong magnetic field, which have recently been predicted from magnetar candidates. In this view, the 5.0 keV feature is consistent with a proton cyclotron fundamental whose energy and width are close to model predictions. The line energy would correspond to a surface magnetic field of 1.0 x 10(exp 15) G for SGR 1806-20, in good agreement with that inferred from the spin-down measure in the source.

Ibrahim, A. I.↗
NASA NTRS2002

Discovery of Cyclotron Resonance Features in the Soft Gamma Repeater SGR 1806-20

We report evidence of cyclotron resonance features from the Soft Gamma Repeater SGR 1806-20 in outburst, detected with the Rossi X-ray Timing Explorer in the spectrum of a long, complex precursor that preceded a strong burst. The features consist of a narrow 5.0 keV absorption line with modulation near its second and third harmonics (at 11.2 keV and 17.5 keV respectively). The line features are transient and are detected in the harder part of the precursor. The 5.0 keV feature is strong, with an equivalent width of approx. 500 eV and a narrow width of less than 0.4 keV. Interpreting the features as electron cyclotron lines in the context of accretion models leads to a large mass-radius ratio (M/R greater than 0.3 solar mass/km) that is inconsistent with neutron stars or that requires a low (5-7) x 10(exp 11) G magnetic field that is unlikely for SGRs. The line widths are also narrow compared with those of electron cyclotron resonances observed so far in X-ray pulsars. In the magnetar picture, the features are plausibly explained as ion cyclotron resonances in an ultra-strong magnetic field that have recently been predicted from magnetar candidates. In this view, the 5.0 keV feature is consistent with a proton cyclotron fundamental whose energy and width are close to model predictions. The line energy would correspond to a surface magnetic field of 1.0 x 10(exp 15) G for SGR 1806-20, in good agreement with that inferred from the spin-down measure in the source.

Ibrahim, Alaa I.↗
NASA NTRS2004

Three Years of TRMM Precipitation Features: Radar, Radiometric, and Lightning Characteristics - Part 1

During its first three years, the Tropical Rainfall Measuring Mission (TRMM) satellite observed nearly six million precipitation features. The population of precipitation features is sorted by lightning flash rate, minimum brightness temperature, maximum radar reflectivity, areal extent, and volumetric rainfall. For each of these characteristics, essentially describing the convective intensity or the size of the features, the population is broken into categories consisting of the top 0.001%, top 0.01%, top 0.1%, top 1%, top 2.4%, and remaining 97.6%. The set of 'weakest / smallest' features comprises 97.6% of the population because that fraction does not have detected lightning, with a minimum detectable flash rate 0.7 fl/min. The greatest observed flash rate is 1351 fl/min; the lowest brightness temperatures are 42 K (85-GHz) and 69 K (37- GHz). The largest precipitation feature covers 335,000 sq km and the greatest rainfall from an individual precipitation feature exceeds 2 x 10(exp 12) kg of water. There is considerable overlap between the greatest storms according to different measures of convective intensity. The largest storms are mostly independent of the most intense storms. The set of storms producing the most rainfall is a convolution of the largest and the most intense storms. This analysis is a composite of the global tropics and subtropics. Significant variability is known to exist between locations, seasons, and meteorological regimes. Such variability will be examined in Part II. In Part I, only a crude land / Ocean separation is made. The known differences in bulk lightning flash rates over land and Ocean result from at least two differences in the precipitation feature population: the frequency of occurrence of intense storms, and the magnitude of those intense storms that do occur. Even when restricted to storms with the same brightness temperature, same size, or same radar reflectivity aloft, the storms over water are considerably less likely to produce lightning than are comparable storms over land.

Cecil, Daniel J.↗
NASA NTRS2005

Three Years of TRMM Precipitation Features: Radar, Radiometric, and Lightning Characteristics - Part 1

During its first three years, the Tropical Rainfall Measuring Mission (TRMM) satellite observed nearly six million precipitation features. The population of precipitation features is sorted by lightning flash rate, minimum brightness temperature, maximum radar reflectivity. areal extent, and volumetric rainfall. For each of these characteristics, essentially describing the convective intensity or the size of the features, the population is broken into categories consisting of the top 0.001%, top 0.01%, top 0.1%, top 1%, top 2.4%. and remaining 97.6%. The set of weakest/smallest features composes 97.6% of the population because that fraction does not have detected lightning, with a minimum detectable flash rate of 0.7 flashes (fl) per minute. The greatest observed flash rate is 1351 fl per minute; the lowest brightness temperatures are 42 K (85 GHz) and 69 K (37 GHz). The largest precipitation feature covers 335 000 square kilometers and the greatest rainfall from an individual precipitation feature exceeds 2 x 10 kg per hour of water. There is considerable overlap between the greatest storms according to different measures of convective intensity. The largest storms are mostly independent of the most intense storms. The set of storms producing the most rainfall is a convolution of the largest and the most intense storms. This analysis is a composite of the global Tropics and subtropics. Significant variability is known to exist between locations. seasons, and meteorological regimes. Such variability will be examined in Part II. In Part I, only a crude land-ocean separation is made. The known differences in bulk lightning flash rates over land and ocean result from at least two differences in the precipitation feature population: the frequency of occurrence of intense storms and the magnitude of those intense storms that do occur. Even when restricted to storms with the same brightness temperature, same size, or same radar reflectivity aloft, the storms over water are considerably less likely to produce lightning than are comparable storms over land.

Cecil, Daniel J.↗
NASA NTRS2007

Morphological Feature Extraction for Automatic Registration of Multispectral Images

The task of image registration can be divided into two major components, i.e., the extraction of control points or features from images, and the search among the extracted features for the matching pairs that represent the same feature in the images to be matched. Manual extraction of control features can be subjective and extremely time consuming, and often results in few usable points. On the other hand, automated feature extraction allows using invariant target features such as edges, corners, and line intersections as relevant landmarks for registration purposes. In this paper, we present an extension of a recently developed morphological approach for automatic extraction of landmark chips and corresponding windows in a fully unsupervised manner for the registration of multispectral images. Once a set of chip-window pairs is obtained, a (hierarchical) robust feature matching procedure, based on a multiresolution overcomplete wavelet decomposition scheme, is used for registration purposes. The proposed method is validated on a pair of remotely sensed scenes acquired by the Advanced Land Imager (ALI) multispectral instrument and the Hyperion hyperspectral instrument aboard NASA's Earth Observing-1 satellite.

Plaza, Antonio↗
NASA NTRS2017

The Detection of 6.9 µm Emission Features in the Infrared Spectra of IRAS 04296+3429, IRAS 05341+0852, IRAS 22272+5435: Evidence for the Presence of Hn-PAHs in Post AGB Stars

Polycyclic aromatic hydrocarbons (PAHs) are generally believed to be ubiquitous in space and responsible for numerous telltale interstellar infrared emission bands. In Sandford et al., (2013), we suggested that polycyclic aromatic hydrocarbons with excess hydrogenation at their periphery (Hn-PAHs) may be an important subclass of these molecules in some astrophysical environments. These molecules are candidates to explain objects with anomalously large 3.4 μm features, which are presumed to be associated with the aliphatic C—H stretching vibrations of the excess hydrogen. In that work, we suggest that for Hn-PAHs to be a viable candidate as the source for this 3.4 μm feature, we must also expect to observe methylene scissoring modes at 6.9 μm. In this work, we continue to develop the Hn-PAH hypothesis with a focus on the 6.9 μm feature. We also present some new observations of three post-asymptotic giant branch (post- AGB) objects with abnormally large 3.4 μm features, IRAS 04296+3429, IRAS 05341+0852, IRAS 22272+5435, in addition to one post-AGB object with normal PAH emissions, IRAS 20000+3239. These observations were made using the FORCAST instrument in grism mode on the Stratospheric Observatory for Infrared Astronomy (SOFIA) aircraft (Adams et al. 2010) and demonstrate the presence of a 6.9 μm feature for the three objects with abnormally large 3.4 μm features and no detectable 6.9 μm feature for the normal PAH emitter. These results are consistent with the hypothesis that Hn-PAHs are a possible source of these infrared emission bands.

ISM↗
NASA NTRS2025

Large Impact Features on Ganymede and Callisto as Revealed By Geological Mapping and Morphometry

The icy Galilean satellites are host to a broad range of impact feature morphologies. Hypotheses seeking to explain the diversity of these impact features consider the effects of impact melt, the physical state of the subsurface at the time of impact, and the impactor characteristics. As part of a larger effort to assess the role of these factors in the formation and evolution of these impact features, we have performed topographic and geological mapping of 19 large impact features on Ganymede and Callisto. These are divided into two main morphological groups: craters (subdivided into pit, dome, and anomalous dome craters), and penepalimpsests/palimpsests. The transitions from pit, dome, to anomalous dome craters appear to be size-dependent up to diameters of ∼170 km. The morphologies of pit and dome craters appear to be independent of their age or geologic context. The impacts that formed them only affected a cold, rigid ice layer, with the development of pits and raised annuli on their floors possibly stemming from the evolution of a pocket of impact melt. The subdued rims and floors of anomalous dome craters indicate the increasing effect of a weak, warm ice layer on impact feature morphology with increasing size, but their prominent annuli and pits indicate that mobilization of impact melt is also a factor. The very low topographic relief of older penepalimpsests and palimpsests indicates that their impacts penetrated the ice shell to mobilize very large volumes of pre-existing liquid from a subsurface layer, with little contribution to the final feature morphology from impact melt. Penepalimpsests are distinguished from palimpsests by the higher frequency of concentric ridges within their interiors, indicating a generally more robust state of the subsurface that could better support the rotation and uplift of solid material during impact, even if a crater-like depression could not be supported. A few impact features seem to be transitional between anomalous dome craters and penepalimpsests, and the overlap of anomalous dome craters, penepalimpsests, and palimpsests in terms of diameter as well as age indicates that impactor size and subsurface properties over time are major factors in determining which of these morphologies emerges.

Oliver L White↗
DOE OSTI2020

eFESTA: Ensemble Feature Exploration with Surface Density Estimates

We propose surface density estimate (SDE) to model the spatial distribution of surface features-isosurfaces, ridge surfaces, and streamsurfaces-in 3D ensemble simulation data. The inputs of SDE computation are surface features represented as polygon meshes, and no field datasets are required (e.g., scalar fields or vector fields). The SDE is defined as the kernel density estimate of the infinite set of points on the input surfaces and is approximated by accumulating the surface densities of triangular patches. We also propose an algorithm to guide the selection of a proper kernel bandwidth for SDE computation. An ensemble Feature Exploration method based on Surface densiTy EstimAtes (eFESTA) is then proposed to extract and visualize the major trends of ensemble surface features. For an ensemble of surface features, each surface is first transformed into a density field based on its contribution to the SDE, and the resulting density fields are organized into a hierarchical representation based on the pairwise distances between them. The hierarchical representation is then used to guide visual exploration of the density fields as well as the underlying surface features. We demonstrate the application of our method using isosurface in ensemble scalar fields, Lagrangian coherent structures in uncertain unsteady flows, and streamsurfaces in ensemble fluid flows.

Computational modeling↗
DOE OSTI2022

Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation

With the proliferation of LiDAR sensors and 3-D vision cameras, 3-D point cloud analysis has attracted significant attention in recent years. In this article, we propose a novel 3-D point cloud learning network, referred to as dynamic point feature aggregation network (DPFA-Net), by selectively performing the neighborhood feature aggregation (FA) with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3-D point clouds. As the core module of the DPFA-Net, we propose an FA layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of semantic segmentation, we exploit the background–foreground (BF) information and present two novel approaches, namely, two-stage BF-Net and BF regularization. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score of 89.22% for semantic segmentation on the Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset and provides consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3-D object classification. Furthermore, our model achieves 93.1% accuracy on the ModelNet40 dataset and provides a mean shape intersection-over-union (IoU) value of 85.5% for part segmentation on the ShapeNet-Part dataset. It is a also computationally more efficient compared to other methods.

3-D↗
DOE OSTI2022

Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia

Feature selection plays a crucial role in the development of machine learning algorithms. Understanding the impact of the features on a model, and their physiological relevance can improve the performance. This is particularly helpful in the healthcare domain wherein disease states need to be identified with relatively small quantities of data. Autonomic Dysreflexia (AD) is one such example, wherein mismanagement of this neurological condition could lead to severe consequences for individuals with spinal cord injuries. We explore different methods of feature selection needed to improve the performance of a machine learning model in the detection of the onset of AD. We present different techniques used as well as the ideal metrics using a dataset of thirty-six features extracted from electrocardiograms, skin nerve activity, blood pressure and temperature. The best performing algorithm was a 5-layer neural network with five relevant features, which resulted in 93.4% accuracy in the detection of AD. The techniques in this paper can be applied to a myriad of healthcare datasets allowing forays into deeper exploration and improved machine learning model development. Through critical feature selection, it is possible to design better machine learning algorithms for detection of niche disease states using smaller datasets.

electrocardiography↗
DOE OSTI2021

Deep convolutional autoencoders as generic feature extractors in seismological applications

The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms), and phase picking. These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with subsequent application layers (either a fully connected layer, or a convolutional layer plus a fully connected layer) to make the decision. By comparing the performance of these newly designed models against the baseline models trained from scratch, we conclude that the autoencoder feature extractor approach may only outperform the baseline under certain conditions, such as when the target problems require features that are similar to the autoencoder encoded features, when a relatively small amount of training data is available, and when certain model structures and training strategies are utilized. The model structure that works best in all these tests is an overcomplete autoencoder with a convolutional layer and a fully connected layer to make the estimation.

58 GEOSCIENCES↗
DOE OSTI2022

A systematic method for selecting molecular descriptors as features when training models for predicting physiochemical properties

Machine learning has proven to be a powerful tool for accelerating biofuel development. Although numerous models are available to predict a range of properties using chemical descriptors, there is a trade-off between interpretability and performance. Neural networks provide predictive models with high accuracy at the expense of some interpretability, while simpler models such as linear regression often lack in accuracy. In addition to model architecture, feature selection is also critical for developing interpretable and accurate predictive models. We present a method for systematically selecting molecular descriptor features and developing interpretable machine learning models without sacrificing accuracy. Our method simplifies the process of selecting features by reducing feature multicollinearity and enables discoveries of new relationships between global properties and molecular descriptors. To demonstrate our approach, we developed models for predicting melting point, boiling point, flash point, yield sooting index, and net heat of combustion with the help of the Tree-based Pipeline Optimization Tool (TPOT). For training, we used publicly available experimental data for up to 8351 molecules. Our models accurately predict various molecular properties for organic molecules (mean absolute percent error (MAPE) ranges from 3.3% to 10.5%) and provide a set of features that are well-correlated to the property. This method enables researchers to explore sets of features that significantly contribute to the prediction of the property, offering new scientific insights. To help accelerate early stage biofuel research and development, we also integrated the data and models into a open-source, interactive web tool.

09 BIOMASS FUELS↗