Interpretable Models Capture the Complex Relationship Between Climate Indices and Fire Season Intensity in Maritime Southeast Asia
Explore the source record for details and available documents.
William S. Daniels↗
SEARCH · Search NASA
Results for “interpretable models”
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.
SLAR image interpretation keys for geographic analysis
A means for side-looking airborne radar (SLAR) imagery to become a more widely used data source in geoscience and agriculture is suggested by providing interpretation keys as an easily implemented interpretation model. Interpretation problems faced by the researcher wishing to employ SLAR are specifically described, and the use of various types of image interpretation keys to overcome these problems is suggested. With examples drawn from agriculture and vegetation mapping, direct and associate dichotomous image interpretation keys are discussed and methods of constructing keys are outlined. Initial testing of the keys, key-based automated decision rules, and the role of the keys in an information system for agriculture are developed.
Coiner, J. C.↗
Integrating adaptive learning with post hoc model explanation and symbolic regression to build interpretable surrogate models
Abstract We develop a materials informatics workflow to build an interpretable surrogate model for micromagnetic simulations. Our goal is to predict the energy barrier of a moving isolated skyrmion in rare-earth-free $$\hbox {Mn}_4$$ Mn 4 N. Our approach integrates adaptive learning with post hoc model explanation and symbolic regression methods. We discuss an unexplored acquisition function (information condensing active learning) within the adaptive learning loop and compare it with the known standard deviation function for efficient navigation of the search space. Model-agnostic post hoc explanation techniques then uncover trends learned by the trained model, which we then leverage to constrain the expressions used for symbolic regression. Graphical abstract
Biswas, Ankita↗
Mn-53 and Al-26 evidence for solar cosmic ray constancy - An improved model for interpretation
A general, numerical method for calculating activities of solar cosmic ray produced radionuclides at any point within an irregularly shaped lunar rock of known surface contour and lunar surface orientation is described. This method is then used to predict the activities of Mn-53 andAl-26 as a function of postion within lunar rock 68815 for various assumed values of solar cosmic ray flux (J), rigidity (R sub 0), and rock erosion rate (ER). The predicted activities agree with the measured activities of Kohl et al. (1978) when values of R sub 0 = 100 MV, J = 70 p/sq cm-sec (4 pi, E greater than 10 MeV), ER not greater than 1 mm/m.y. and a total exposure time of 2 m.y. are assumed. These values are in agreement with those found for rocks exposed for not less than 10 m.y. and provide no evidence for variation of the average solar cosmic ray parameters between the last 2 and 10 m.y. intervals. When interpreted with the improved model the activity vs. depth profiles for three faces of 68815 show no evidence of SCR anisotropy or differential erosion.
Russ, G. P., III↗
Guiding center model to interpret neutral particle analyzer results
The theoretical model is discussed, which accounts for drift and cyclotron components of ion motion in a partially ionized plasma. Density and velocity distributions are systematically precribed. The flux into the neutral particle analyzer (NPA) from this plasma is determined by summing over all charge exchange neutrals in phase space which are directed into apertures. Especially detailed data, obtained by sweeping the line of sight of the apertures across the plasma of the NASA Lewis HIP-1 burnout device, are presented. Selection of randomized cyclotron velocity distributions about mean azimuthal drift yield energy distributions which compared well with experiment. Use of data obtained with a bending magnet on the NPA showed that separation between energy distribution curves of various mass species correlate well with a drift divided by mean cyclotron energy parameter of the theory. Use of the guiding center model in conjunction with NPA scans across the plasma aid in estimates of ion density and E field variation with plasma radius.
Englert, G. W.↗
The Barnes-Evans color-surface brightness relation: A preliminary theoretical interpretation
Model atmosphere calculations are used to assess whether an empirically derived relation between V-R and surface brightness is independent of a variety of stellar paramters, including surface gravity. This relationship is used in a variety of applications, including the determination of the distances of Cepheid variables using a method based on the Beade-Wesselink method. It is concluded that the use of a main sequence relation between V-R color and surface brightness in determining radii of giant stars is subject to systematic errors that are smaller than 10% in the determination of a radius or distance for temperature cooler than 12,000 K. The error in white dwarf radii determined from a main sequence color surface brightness relation is roughly 10%.
Shipman, H. L.↗
Model for interpreting Doppler broadened optical line emission measurements on axially symmetric plasma
A plasma model, previously developed to interpret neutral-particle analyzer measurements on E x B heating devices, is adapted to analyze Doppler broadened charge-exchange-neutral lines measured by an optical monochromator. Comparison of theoretical with experimental results indicates that azimuthal drift as well as cyclotron motion are quite influential in determining line shapes and widths, and thus important in temperature determination, even when the monochromator line of sight is intersecting the plasma axis of symmetry. At this central sighting position, however, results are quite insensitive to radial ion density distribution when time lag between the charge-exchange-excitation events and emission is neglected. Line shapes and widths obtained by sighting across chords of plasma at various distances from the plasma axis of symmetry indicate a strong dependence on time lag.
Englert, G. W.↗
Learning Physically Interpretable Atmospheric Models From Data With WSINDy
The multiscale and turbulent nature of Earth's atmosphere has historically rendered accurate weather modeling a hard problem. Recently, there has been an explosion of interest surrounding data-driven approaches to weather modeling, which in many cases show improved forecasting accuracy and computational efficiency when compared to traditional methods. However, many of the current data-driven approaches employ highly parameterized neural networks, often resulting in uninterpretable models and limited gains in scientific understanding. In this work, we address the interpretability problem by explicitly discovering partial differential equations governing atmospheric phenomena, identifying symbolic mathematical models with direct physical interpretations. The purpose of this paper is to demonstrate that, in particular, the weak-form sparse identification of nonlinear dynamics (WSINDy) algorithm can learn effective atmospheric models from both simulated and assimilated data. Our approach adapts the standard WSINDy algorithm to work with high-dimensional fluid data of arbitrary spatial dimension.
58 GEOSCIENCES↗
Guiding center model to interpret neutral particle analyzer results
An attempt is made to model the essential features of ion motion in a plasma. A guiding center model is hypothesized for a plasma heating device whose radial electric fields and axial magnetic fields are crossed. The guiding center model is shown to give results which agree with experimental data from four different plasma heating devices and are helpful for the interpretation of neutral particle analyzer results.
Englert, G. W.↗
Investigation to develop a multistage forest sampling inventory system using ERTS-1 imagery
The author has identified the following significant results. The annotation system produced a RMSE of about 200 m ground distance in the MSS data system with the control data used. All the analytical MSS interpretation models tried were highly significant. However, the gains in forest sampling efficiency that can be achieved by using the models vary from zero to over 50 percent depending on the area to which they are applied and the sampling method used. Among the sampling methods tried, regression sampling yielded substantial and the most consistent gains. The single most significant variable in the interpretation model was the difference between bands 5 and 7. The contrast variable, computed by the Hadamard transform was significant but did not contribute much to the interpretation model. Forest areas containing very large timber volumes because of large tree sizes were not separable from areas of similar crown cover but containing smaller trees using ERTS image interpretation only. All correlations between space derived timber volume predictions and estimates obtained from aerial and ground sampling were relatively low but significant and stable. There was a much stronger relationship between variables derived from MSS and U2 data than between U2 and ground data.
Langley, P. G.↗
Understanding the Impact of Unobservable Variables on the Performance of Predictive Models: The Need for Feature Space Partitioning and Fusion
When developing predictive models over a dataset, the model is globally optimized across the entire feature space to learn a decision boundary. However, when unobservable variables—which cannot be measured or estimated—interact with the observable variables, this can negatively impact the optimization applied to the decision boundary since the data samples introduced by unobservable variables may have little to no association with the applied global optimization. This, consequently, penalizes the entire decision boundary and model performance. This paper examines some of the detrimental effects of unobservable variables, particularly their role in creating new modes in the distribution of observable variables and reducing the separability of class distributions. Such challenges result in skewed or warped decision boundaries and decreased accuracy of model predictions, particularly for interpretable models like logistic regression and decision trees. Through two illustrative case examples, we highlight the need to address the challenges imposed by unobservable variables. We propose a strategy to mitigate these challenges by creating local regions within the feature space through partitioning. This enables the optimization of local models within the regions to overcome the impact of unobservability in different feature space localities. Research into a more sophisticated partitioning strategy and where the partition should be relative to the sample of interest is left as future work. Through the analysis of the impact of unobservability and the development of a partitioning method, we demonstrate the clear need for a partitioning strategy that integrates knowledge from multiple local models to estimate risk factors using information fusion. Thus, we establish the foundation and motivation for using partitioning and information fusion to overcome the effects of unobservability in predictive models. Formal fusion methods, such as Dempster-Shafer theory, can better leverage the information from local regions to improve the performance of interpretable predictive models in the presence of unobservable variables.
Time Series Data↗
Interpretable Machine Learning for Characterizing Electric Vehicle Charging Behavior: Insights from Real-World Data
As electric vehicle (EV) adoption rises globally, concerns about the impact on aging electrical grids grow, particularly regarding the charging behavior of EV drivers. This study analyzes real-world driving and charging data from Ford battery electric vehicles (BEVs) collected between 2018 and 2019 to develop interpretable models that characterize charging behavior and quantify influencing factors. Prior research has relied on assumptions regarding driver behavior, often overlooking actual charging patterns. By employing generalized linear mixed models (GLMMs), this work offers insights into how various elements, such as next trip distance and state of charge (SOC), influence charging decisions. The dataset comprises over three million park-trip pairs from 1,997 vehicles, revealing that features related to driving behavior significantly dictate charging behavior, while infrastructure and regional factors have lesser impacts. The findings suggest that existing simulation models may oversimplify EV charging behavior assumptions. This work utilizes real-world EV driving and charging data to train interpretable models that describe charging behavior and quantify the factors most associated with how drivers use charging infrastructure. This research underscores the need for interpretable, data-driven methodologies to inform future EV infrastructure planning and grid management.
29 - ENERGY PLANNING, POLICY AND ECONOMY↗
A semiempirical model for interpreting microwave emission from semiarid land surfaces as seen from space
A radiative-transfer model for simulating microwave brightness temperatures over land surfaces is described. The model takes into account sensor viewing conditions (spacecraft altitude, viewing angle, frequency, and polarization) and atmospheric parameters over a soil surface characterized by its moisture, roughness, and temperature and covered with a layer of vegetation characterized by its temperature, water content, single scattering albedo, structure, and percent coverage. In order to reduce the influence of atmospheric and surface temperature effects, the brightness temperatures are expressed as polarization ratios that depend primarily on the soil moisture and roughness, canopy water content, and percentage of cover. The sensitivity of the polarization ratio to these parameters is investigated. Simulation of the temporal evolution of the microwave signal over semiarid areas in the African Sahel is presented and compared to actual satellite data from the SMMR instrument on Nimbus-7.
Kerr, Yann H.↗
Dust Model Sensitivity to Dust Source Mask, Sandblasting Efficiency, Air Density, and Land Use: Implications for Model Improvement
This study compares dust storm simulations using two commonly adopted methods for representing four important dust emission parameters. Compared to a dynamic dust source mask based on land use and vegetation cover, a static mask based solely on land use overestimates dust concentration and optical depth by a factor of 2, besides generating spurious emissions. The results reinforce that seasonal variations in vegetation cover can significantly affect dust emissions. For sandblasting efficiency, a clay-dependent semiempirical expression produces 10 times more dust than a physics-based expression. Simulations using model-predicted versus a fixed constant for air density differ by only 8%. However, this difference could range between 12 and 22% for annual simulations over global dust source regions. Simulations with updated versus old land use data, using the same dust source mask, differ twofold, indicating the significant impact of land use change on regional dust emission in central Arizona. The differences in the pairs of these simulations are generally larger than the uncertainty due to meteorology. The simulations align better with observation when using the dynamic dust source mask, the physics-based sandblasting efficiency, and the up-to-date land use data. Given the high sensitivity of dust to surface conditions, the results discussed have implications for improving the dust cycle in weather and climate models and for interpreting model intercomparisons.
Dust-emission source↗
Modeling and interpretation of the optical and HST UV spectrum of SN 1993J
We present spherically symmetric, non-local thermodynamic equilibrium (non-LTE), expanding model atmosphere synthetic spectra of SN 1993J and compare them to the ultraviolet and optical spectra obtained simultaneously on 1993 April 15 by the Hubble Space Telescope (HST) and at Lick Observatory. We are able to fit the optical and HST near-UV spectra with a variety of compositions, but find that our best fits are obtained with an enhanced helium abundance (Y = 0.8) and significant nonthermal ionization due to gamma rays produced by the decay of Ni-56. We find the effects of X-rays produced by thermal bremsstrahlung in the circumstellar material to have little effect on the spectrum. Our current models are unable to fit the HST far-UV region, predicting too little flux and strong, unseen Fe II features.
Baron, E.↗
ERTS data user investigation to develop a multistage forest sampling inventory system
The author has identified the following significant results. A unique digital timber volume estimation system was developed for use with the MSS CCT tapes. The system was tested on a 64-square mile area in Northern California's Trinity Alps. The outcome of a systematic experiment, in which several possible combinations of bands 5 and 7 and a contrast measure were tried, showed that an estimated gain in precision of 50% can be obtained in a multistage sampling design. The difference between bands 5 and 7 proved to be of special importance for the estimation of biomass in the form of timber volume. In addition, an interpretation model for high flight U2 photographs was developed. A maximum multiple correlation coefficient of 0.74 was obtained for the regression model, explaining 55% of the variation in timber volume as estimated from aerial photos and ground measurments. An interpretation model for MSS color composites is in the testing stage.
Langley, P. G.↗
A Model-based Interpretation of Low-frequency Changes in the Carbon Cycle during the Last 120,000 years and its Implications for the Reconstruction of Atmospheric (delta) 14-C
A main caveat in the interpretation of observed changes in atmospheric (Delta)C-l4 during the last 50,000 years is the unknown variability of the carbon cycle, which together with changes in the C-14 production rates determines the C-14 dynamics. A plausible scenario explaining glacial/interglacial dynamics seen in atmospheric CO2 and (delta)C-13 was proposed recently (Kohler et al., 2005a). A similar approach that expands its interpretation to the C-14 cycle is an important step toward a deeper understanding of (Delta)C-14 variability. This approach is based on an ocean/atmosphere/biosphere box model of the global carbon cycle (BICYCLE) to reproduce low-frequency changes in atmospheric CO2 as seen in Antarctic ice cores. The model is forced forward in time by various paleoclimatic records derived from ice and sediment cores. The simulation results of our proposed scenario match a compiled CO2 record from various ice cores during the last 120,000 years with high accuracy (r(sup 2) = 0.89). We analyze scenarios with different C-14 production rates, which are either constant or based on Be-10 measured in Greenland ice cores or the recent high-resolution geomagnetic field reconstruction GLOPIS-75 and compare them with the available (Delta)C-14 data covering the last 50,000 years. Our results suggest that during the last glacial cycle in general less than 110%0o f the increased atmospheric (Delta)C-14 is based on variations in the carbon cycle, while the largest part (5/6) of the variations has to be explained by other factors. Glacial atmospheric (Delta)C-14 larger than 700% cannot not be explained within our framework, neither through carbon cycle-based changes nor through variable C-14 production. Superimposed on these general trends might lie positive anomalies in atmospheric (Delta)C-14 of approx. 50% caused by millennial-scale variability of the northern deep water production during Heinrich events and Dansgaard/Oeschger climate fluctuations. According to our model, the dominant processes that increase glacial (Delta)C-14 are a reduced glacial ocean circulation (+ approx.40%0), a restricted glacial gas exchange between the atmosphere and the surface ocean through sea ice coverage (+ approx. 20%), and the enrichment of dissolved inorganic carbon with C-14 in the surface waters through isotopic fractionation during higher glacial marine export production caused by iron fertilization (+ approx.10%).
Koehler, Peter↗
A statistical model for interpreting computerized dynamic posturography data
Computerized dynamic posturography (CDP) is widely used for assessment of altered balance control. CDP trials are quantified using the equilibrium score (ES), which ranges from zero to 100, as a decreasing function of peak sway angle. The problem of how best to model and analyze ESs from a controlled study is considered. The ES often exhibits a skewed distribution in repeated trials, which can lead to incorrect inference when applying standard regression or analysis of variance models. Furthermore, CDP trials are terminated when a patient loses balance. In these situations, the ES is not observable, but is assigned the lowest possible score--zero. As a result, the response variable has a mixed discrete-continuous distribution, further compromising inference obtained by standard statistical methods. Here, we develop alternative methodology for analyzing ESs under a stochastic model extending the ES to a continuous latent random variable that always exists, but is unobserved in the event of a fall. Loss of balance occurs conditionally, with probability depending on the realized latent ES. After fitting the model by a form of quasi-maximum-likelihood, one may perform statistical inference to assess the effects of explanatory variables. An example is provided, using data from the NIH/NIA Baltimore Longitudinal Study on Aging.
NASA Discipline Neuroscience↗