Search NASA⌕ Search

SEARCH · Search NASA

Results for “random variable”

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 955 records · Page 53

Heuristic Computational Model for Predicting Lignin Solubility in Tailored Organic Solvents

Lignin is a random heteropolymer that has been extensively studied as a renewable source of aromatic precursors for high-value chemicals, biofuels, and bioplastics. A key challenge in lignin valorization is the structural and compositional heterogeneity of lignin feedstocks. Solvent-based approaches are commonly used to fractionate lignin to reduce this heterogeneity, but solvent selection can be challenging due to variability in lignin composition. In this work, we developed computational methods to predict good and poor organic solvents as a function of lignin composition. We analyzed 28 different linear pentamer structures, 18 from known libraries and 10 hypothetical polymers, and calculated their activity coefficients in 50 different organic solvents by using the conductor-like screening model for realistic solvents. We used these data to train a regression model that enabled the extensive investigation of the impact of solvent and monolignol compositions on predicted lignin solubility. The exhaustive exploration of solubility trends using model predictions revealed sets of solvents, identified using Kamlet–Taft parameters, that are predicted to promote lignin dissolution regardless of lignin composition. We further identified solvents expected to selectively isolate lignin fractions enriched in certain subunits. Furthermore, these results establish heuristic guidelines for solvent selection that can be used to tailor fractionation processes for lignin feedstocks of distinct composition or to design new processes that isolate fractions with higher proportions of selected subunits.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Three‐Phase CO 2 Flow in a Basalt Fracture Network

Abstract Geologic CO 2 sequestration in basalt reservoirs is predicated on permanent CO 2 isolation via rapid mineralization reactions. This process is supported by a substantial body of evidence, including laboratory experiments documenting rapid mineralization rates, regional storage estimates indicating large, accessible storage reservoirs, and two successful pilot‐scale studies. Nevertheless, there remains significant uncertainty in the behavior of CO 2 flow within basalt fracture networks, particularly in the context estimating physical trapping potential in early time and as CO 2 undergoes phase change. In this study, a Monte Carlo numerical model is designed to simulate a supercritical CO 2 plume infiltrating a low‐permeability flood basalt entablature. The fracture network model is based on outcrop‐scale LiDAR mapping of Columbia River Basalt, and CO 2 flow is simulated within fifty equally probable realizations of the fracture network. The spatial distribution of fracture permeability for each realization is randomly drawn from a basalt aperture distribution, and ensemble results are analyzed with e‐type estimates to compute mean and standard deviation of fluid pressure and CO 2 saturation. Results of this model after 10 years of simulation suggest that (1) CO 2 flow converges on a single dominant flow path, (2) CO 2 accumulates at fracture intersections, and (3) variability in permeability can account for a 1.6 m depth interval within which free CO 2 may change phase from supercritical fluid to subcritical liquid or gas. In the context of CO 2 sequestration in basalt, these results suggest that physical CO 2 trapping may be substantially enhanced as carbonate minerals precipitate within the basalt fracture network.

Gierzynski, Alec O.↗

SU-E-T-573: The Robustness of a Combined Margin Recipe for Uncertainties During Radiotherapy

Purpose: To investigate the variability of a safety margin recipe that combines CTV and PTV margins quadratically, with several tumor, treatment, and user related factors. Methods: Margin recipes were calculated by monte-carlo simulations in 5 steps. 1. A spherical tumor with or without isotropic microscopic was irradiated with a 5 field dose plan2. PTV: Geometric uncertainties were introduced using systematic (Sgeo) and random (sgeo) standard deviations. CTV: Microscopic disease distribution was modelled by semi-gaussian (Smicro) with varying number of islets (Ni)3. For a specific uncertainty set (Sgeo, sgeo, Smicro(Ni)), margins were varied until pre-defined decrease in TCP or dose coverage was fulfilled. 4. First, margin recipes were calculated for each of the three uncertainties separately. CTV and PTV recipes were then combined quadratically to yield a final recipe M(Sgeo, sgeo, Smicro(Ni)).5. The final M was verified by simultaneous simulations of the uncertainties.Now, M has been calculated for various changing parameters like margin criteria, penumbra steepness, islet radio-sensitivity, dose conformity, and number of fractions. We subsequently investigated A: whether the combined recipe still holds in all these situations, and B: what the margin variation was in all these cases. Results: We found that the accuracy of the combined margin recipes remains on average within 1mm for all situations, confirming the correctness of the quadratic addition. Depending on the specific parameter, margin factors could change such that margins change over 50%. Especially margin recipes based on TCP-criteria are more sensitive to more parameters than those based on purely geometric Dmin-criteria. Interestingly, measures taken to minimize treatment field sizes (by e.g. optimizing dose conformity) are counteracted by the requirement of larger margins to get the same tumor coverage. Conclusion: Margin recipes combining geometric and microscopic uncertainties quadratically are accurate under varying circumstances. However margins can change up to 50% for different situations.

60 APPLIED LIFE SCIENCES↗

Microbial Communities Influence Soil Dissolved Organic Carbon Concentration by Altering Metabolite Composition

Rapid microbial growth in the early phase of plant litter decomposition is viewed as an important component of soil organic matter (SOM) formation. However, the microbial taxa and chemical substrates that correlate with carbon storage are not well resolved. The complexity of microbial communities and diverse substrate chemistries that occur in natural soils make it difficult to identify links between community membership and decomposition processes in the soil environment. To identify potential relationships between microbes, soil organic matter, and their impact on carbon storage, we used sand microcosms to control for external environmental factors such as changes in temperature and moisture as well as the variability in available carbon that exist in soil cores. Using Fourier transform ion cyclotron resonance mass spectrometry (FTICR-MS) on microcosm samples from early phase litter decomposition, we found that protein- and tannin-like compounds exhibited the strongest correlation to dissolved organic carbon (DOC) concentration. Proteins correlated positively with DOC concentration, while tannins correlated negatively with DOC. Through random forest, neural network, and indicator species analyses, we identified 42 bacterial and 9 fungal taxa associated with DOC concentration. The majority of bacterial taxa (26 out of 42 taxa) belonged to the phylum Proteobacteria while all fungal taxa belonged to the phylum Ascomycota. Additionally, we identified significant connections between microorganisms and protein-like compounds and found that most taxa (12/14) correlated negatively with proteins indicating that microbial consumption of proteins is likely a significant driver of DOC concentration. This research links DOC concentration with microbial production and/or decomposition of specific metabolites to improve our understanding of microbial metabolism and carbon persistence.

59 BASIC BIOLOGICAL SCIENCES↗

Automated characterization of perceptual quality of clinical chest radiographs: Validation and calibration to observer preference

Purpose: The authors previously proposed an image-based technique [Y. Lin et al. Med. Phys. 39, 7019–7031 (2012)] to assess the perceptual quality of clinical chest radiographs. In this study, an observer study was designed and conducted to validate the output of the program against rankings by expert radiologists and to establish the ranges of the output values that reflect the acceptable image appearance so the program output can be used for image quality optimization and tracking. Methods: Using an IRB-approved protocol, 2500 clinical chest radiographs (PA/AP) were collected from our clinical operation. The images were processed through our perceptual quality assessment program to measure their appearance in terms of ten metrics of perceptual image quality: lung gray level, lung detail, lung noise, rib–lung contrast, rib sharpness, mediastinum detail, mediastinum noise, mediastinum alignment, subdiaphragm–lung contrast, and subdiaphragm area. From the results, for each targeted appearance attribute/metric, 18 images were selected such that the images presented a relatively constant appearance with respect to all metrics except the targeted one. The images were then incorporated into a graphical user interface, which displayed them into three panels of six in a random order. Using a DICOM calibrated diagnostic display workstation and under low ambient lighting conditions, each of five participating attending chest radiologists was tasked to spatially order the images based only on the targeted appearance attribute regardless of the other qualities. Once ordered, the observer also indicated the range of image appearances that he/she considered clinically acceptable. The observer data were analyzed in terms of the correlations between the observer and algorithmic rankings and interobserver variability. An observer-averaged acceptable image appearance was also statistically derived for each quality attribute based on the collected individual acceptable ranges. Results: The observer study indicated that, for each image quality attribute, the averaged observer ranking strongly correlated with the algorithmic ranking (linear correlation coefficient R > 0.92), with highest correlation (R = 1) for lung gray level and the lowest (R = 0.92) for mediastinum noise. There was a strong concordance between the observers in terms of their rankings (i.e., Kendall’s tau agreement > 0.84). The observers also generally indicated similar tolerance and preference levels in terms of acceptable ranges, as 85% of the values were close to the overall tolerance or preference levels and the differences were smaller than 0.15. Conclusions: The observer study indicates that the previously proposed technique provides a robust reflection of the perceptual image quality in clinical images. The results established the range of algorithmic outputs for each metric that can be used to quantitatively assess and qualify the appearance quality of clinical chest radiographs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Uncertainty quantification for systems of conservation laws

Uncertainty quantification through stochastic spectral methods has been recently applied to several kinds of non-linear stochastic PDEs. In this paper, we introduce a formalism based on kinetic theory to tackle uncertain hyperbolic systems of conservation laws with Polynomial Chaos (PC) methods. The idea is to introduce a new variable, the entropic variable, in bijection with our vector of unknowns, which we develop on the polynomial basis: by performing a Galerkin projection, we obtain a deterministic system of conservation laws. We state several properties of this deterministic system in the case of a general uncertain system of conservation laws. We then apply the method to the case of the inviscid Burgers' equation with random initial conditions and we present some preliminary results for the Euler system. We systematically compare results from our new approach to results from the stochastic Galerkin method. In the vicinity of discontinuities, the new method bounds the oscillations due to Gibbs phenomenon to a certain range through the entropy of the system without the use of any adaptative random space discretizations. It is found to be more precise than the stochastic Galerkin method for smooth cases but above all for discontinuous cases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Environmental stress mediates groundwater microbial community assembly

Community assembly describes how different ecological processes shape microbial community composition and structure. How environmental factors impact community assembly remains elusive. Here we sampled microbial communities and >200 biogeochemical variables in groundwater at the Oak Ridge Field Research Center, a former nuclear waste disposal site, and developed a theoretical framework to conceptualize the relationships between community assembly processes and environmental stresses. We found that stochastic assembly processes were critical (>60% on average) in shaping community structure, but their relative importance decreased as stress increased. Dispersal limitation and ‘drift’ related to random birth and death had negative correlations with stresses, whereas the selection processes leading to dissimilar communities increased with stresses, primarily related to pH, cobalt and molybdenum. Assembly mechanisms also varied greatly among different phylogenetic groups. As a result, our findings highlight the importance of microbial dispersal limitation and environmental heterogeneity in ecosystem restoration and management.

54 ENVIRONMENTAL SCIENCES↗

Machine learning and process-based modeling of spatiotemporal changes in active layer thickness across Alaska

Permafrost degradation poses a growing threat to infrastructure stability and ecosystem resilience in the rapidly warming Arctic. We investigated the spatiotemporal dynamics of active layer thickness (ALT) across Alaska by integrating field observations, environmental datasets, a physically based Stefan model, and machine learning (ML) techniques. Using weather projections from the Coupled Model Intercomparison Project Phase 6 under two Shared Socioeconomic Pathways (SSP 2-4.5 and SSP 5-8.5), we assessed ALT sensitivity to projected future weather conditions. The random forest (RF) model outperformed the Stefan approach in predicting ALT on the training dataset (R² = 0.84 vs. 0.53) but demonstrated lower generalizability on the test dataset (R² = 0.24 vs. 0.54). The root mean square error (RMSE) for the RF model for training and testing ranged from 14 to 22 cm, compared to 17 and 18 cm for the Stefan model. Variable importance analysis revealed that mean annual temperature and slope angle were the strongest predictors of ALT, accounting for 19% and 18% of the variance, respectively, followed by sediment transport index (14%) and stream power index (11%). Comparative analysis of baseline ALT predictions showed the Stefan model tended to project a thicker active layer (mean ± SD: 65 ± 16 cm), compared to the RF model (mean ± SD: 59 ± 8.8) cm). Both models indicated a latitudinal gradient in ALT, with shallower depths at higher latitudes. Projected ALT increases by 2100 were estimated at 3.3 ± 2.2 cm under SSP 2-4.5 and 5.9 ± 4.0 cm under SSP 5-8.5 for the ML model, whereas the Stefan model projected substantially larger increases of 13 ± 2.6 cm (SSP 2-4.5) and 28 ± 4.4 cm (SSP5-8.5). Spatial analysis showed the greatest ALT increases in northern Alaska, with relatively smaller changes in southern regions. These findings highlight the complex, multifactorial nature of ALT dynamics and the value of hybrid modeling approaches. As rising temperatures accelerate permafrost thaw, changes in ALT can disrupt ecosystems, damage infrastructures, and enhance the release of stored soil carbon, highlighting the urgent need for improved predictive capabilities to inform adaptation strategies in the Arctic.

Climate sciences↗

Protein subcellular location pattern classification in cellular images using latent discriminative models

Motivation: Knowledge of the subcellular location of a protein is crucial for understanding its functions. The subcellular pattern of a protein is typically represented as the set of cellular components in which it is located, and an important task is to determine this set from microscope images. In this article, we address this classification problem using confocal immunofluorescence images from the Human Protein Atlas (HPA) project. The HPA contains images of cells stained for many proteins; each is also stained for three reference components, but there are many other components that are invisible. Given one such cell, the task is to classify the pattern type of the stained protein. We first randomly select local image regions within the cells, and then extract various carefully designed features from these regions. This region-based approach enables us to explicitly study the relationship between proteins and different cell components, as well as the interactions between these components. To achieve these two goals, we propose two discriminative models that extend logistic regression with structured latent variables. The first model allows the same protein pattern class to be expressed differently according to the underlying components in different regions. The second model further captures the spatial dependencies between the components within the same cell so that we can better infer these components. To learn these models, we propose a fast approximate algorithm for inference, and then use gradient-based methods to maximize the data likelihood. Results: In the experiments, we show that the proposed models help improve the classification accuracies on synthetic data and real cellular images. The best overall accuracy we report in this article for classifying 942 proteins into 13 classes of patterns is about 84.6%, which to our knowledge is the best so far. In addition, the dependencies learned are consistent with prior knowledge of cell organization.

59 BASIC BIOLOGICAL SCIENCES↗

Dimension-adaptive machine learning-based quantum state reconstruction

Here, we introduce an approach for performing quantum state reconstruction on systems of n qubits using a machine learning-based reconstruction system trained exclusively on m qubits, where m ≥ n. This approach removes the necessity of exactly matching the dimensionality of a system under consideration with the dimension of a model used for training. We demonstrate our technique by performing quantum state reconstruction on randomly sampled systems of one, two, and three qubits using machine learning-based methods trained exclusively on systems containing at least one additional qubit. The reconstruction time required for machine learning-based methods scales significantly more favorably than the training time; hence this technique can offer an overall saving of resources by leveraging a single neural network for dimension-variable state reconstruction, obviating the need to train dedicated machine learning systems for each Hilbert space.

42 ENGINEERING↗

Comparison of ANN (MLP), ANFIS, SVM, and RF models for the online classification of heating value of burning municipal solid waste in circulating fluidized bed incinerators

Highlights: • A rapid, cost-effective, and comparative methodology was proposed to evaluate the HVs of burning MSW online. • Models ranked in descending order of performance are ANFIS, RF, SVM, MLP. • A well trained model is capable of characterizing the variation trend of HVs accurately. - Abstract: The heating values, particularly lower heating values of burning municipal solid waste are critically important parameters in operating circulating fluidized bed incineration systems. However, the heating values change widely and frequently, while there is no reliable real-time instrument to measure heating values in the process of incinerating municipal solid waste. A rapid, cost-effective, and comparative methodology was proposed to evaluate the heating values of burning MSW online based on prior knowledge, expert experience, and data-mining techniques. First, selecting the input variables of the model by analyzing the operational mechanism of circulating fluidized bed incinerators, and the corresponding heating value was classified into one of nine fuzzy expressions according to expert advice. Development of prediction models by employing four different nonlinear models was undertaken, including a multilayer perceptron neural network, a support vector machine, an adaptive neuro-fuzzy inference system, and a random forest; a series of optimization schemes were implemented simultaneously in order to improve the performance of each model. Finally, a comprehensive comparison study was carried out to evaluate the performance of the models. Results indicate that the adaptive neuro-fuzzy inference system model outperforms the other three models, with the random forest model performing second-best, and the multilayer perceptron model performing at the worst level. A model with sufficient accuracy would contribute adequately to the control of circulating fluidized bed incinerator operation and provide reliable heating value signals for an automatic combustion control system.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

A novel random forest approach to revealing interactions and controls on chlorophyll concentration and bacterial communities during coastal phytoplankton blooms

Abstract Increasing occurrence of harmful algal blooms across the land–water interface poses significant risks to coastal ecosystem structure and human health. Defining significant drivers and their interactive impacts on blooms allows for more effective analysis and identification of specific conditions supporting phytoplankton growth. A novel iterative Random Forests (iRF) machine-learning model was developed and applied to two example cases along the California coast to identify key stable interactions: (1) phytoplankton abundance in response to various drivers due to coastal conditions and land-sea nutrient fluxes, (2) microbial community structure during algal blooms. In Example 1, watershed derived nutrients were identified as the least significant interacting variable associated with Monterey Bay phytoplankton abundance. In Example 2, through iRF analysis of field-based 16S OTU bacterial community and algae datasets, we independently found stable interactions of prokaryote abundance patterns associated with phytoplankton abundance that have been previously identified in laboratory-based studies. Our study represents the first iRF application to marine algal blooms that helps to identify ocean, microbial, and terrestrial conditions that are considered dominant causal factors on bloom dynamics.

59 BASIC BIOLOGICAL SCIENCES↗

Fixed-rate compressed floating-point arrays

ZFP is a library for lossy compression of single- and double-precision floating-point data. One of the unique features of ZFP is its support for fixed-rate compression, which enables random read and write access at the granularity of small blocks of values. Using a C++ interface, this allows declaring compressed arrays (1D, 2D, and 3D arrays are supported) that through operator overloading can be treated just like conventional, uncompressed arrays, but which allow the user to specify the exact number of bits to allocate to the array. ZFP also has variable-rate fixed-precision and fixed-accuracy modes, which allow the user to specify a tolerance on the relative or absolute error.

ECP↗

Toward Improving the Generation Quality of Autoregressive Slot VAEs

Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (“slots”) from images, unconditional generation of scenes from slots has received less attention. This is primarily because learning the multiobject relations necessary to imagine coherent scenes is difficult. We hypothesize that most existing slot-based models have a limited ability to learn object correlations. We propose two improvements that strengthen object correlation learning. The first is to condition the slots on a global, scene-level variable that captures higher-order correlations between slots. Second, we address the fundamental lack of a canonical order for objects in images by proposing to learn a consistent order to use for the autoregressive generation of scene objects. Specifically, we train an autoregressive slot prior to sequentially generate scene objects following a learned order. Ordered slot inference entails first estimating a randomly ordered set of slots using existing approaches for extracting slots from images, then aligning those slots to ordered slots generated autoregressively with the slot prior. Our experiments across three multiobject environments demonstrate clear gains in unconditional scene generation quality. Detailed ablation studies are also provided that validate the two proposed improvements.

MATHEMATICS AND COMPUTING↗

AutoFocus: AI-driven alignment of nanofocusing X-ray mirror systems

We describe the application of an AI-driven system to autonomously align complex x-ray-focusing mirror systems, including mirrors systems with variable focus spot sizes. The system has been developed and studied on a digital twin of nanofocusing X-ray beamlines, built using advanced optical simulation tools calibrated with wavefront sensing data collected at the beamline. We experimentally demonstrated that the system is reliably capable of positioning a focused beam on the sample, both by simulating the variation of a beamline with random perturbations due to typical changes in the light source and optical elements over time, and by conducting similar tests on an actual focusing mirror system.

47 OTHER INSTRUMENTATION↗

Predicting initial trans-membrane pressure across cycles in the ultrafiltration process using random forest

With growing freshwater scarcity, direct potable reuse (DPR) systems that reclaim wastewater for drinking are becoming increasingly important for sustainable water supply. Reliable operation requires minimizing downtime in ultrafiltration (UF) units, where membrane fouling leads to elevated trans-membrane pressure (TMP). This study develops data-driven regression models based on random forest (RF) and autoregressive (AR) approaches to forecast the initial TMP at the start of each UF filtration cycle in a pilot-scale DPR system. The RF model consistently outperforms baseline methods, including historical mean, last observation carried forward, and AR models, across multiple forecast horizons, achieving the lowest root mean square error. To evaluate how different classes of process variables contribute to TMP dynamics over time, we examine the feature importance of independent input variables across multiple forecast horizons. This analysis provides insight into the temporal relevance of operational and sensor-derived features, guiding control and monitoring strategies. Additionally, the impact of hyperparameter tuning on TMP prediction performance is assessed for both direct and recursive RF modelling approaches. The proposed RF framework establishes a robust foundation for predictive monitoring and real-time optimization of UF operations, supporting sustainable and reliable water reuse.

direct potable reuse↗

Test Plan to Assess Fire Effects on the Function of an Engineered Surface Barrier

Wildfire is a frequent perturbation in shrub steppe ecosystems, altering the flora, fauna, atmosphere, and soil of these systems. Research on the fire effects has focused mostly on natural ecosystems with essentially no attention on engineered systems like surface barriers. The scope of the project is to use a simulated wildfire to induce changes in an engineered surface barrier and document the effects on barrier performance. The main objective is to quantify the effects of burning and the resulting post-fire conditions on alterations in soil physical properties; hydrologic response, particularly the water balance; geochemical properties; and biological properties. A secondary objective is to use the lessons learned to maximize fire protection in the design of long-term monitoring systems based on electronic sensors. A simulated wildfire will be initiated, controlled and monitored at the 200-BP-1 barrier in collaboration with the Hanford Fire Department during the fall of 2008. The north half of the barrier will be divided into nine 12 x 12 m plots, each of which will be randomly assigned a fuel load of 2 kg m-2 or 4 kg m-2. Each plot will be ignited around the perimeter and flames allowed to carry to the centre. Any remaining unburned vegetation will be manually burned off using a drip torch. Progress of the fire and its effects will be monitored using point measurements of thermal, hydrologic, and biotic variables. Three measures of fire intensity will be used to characterize fire behavior: (1) flame height, (2) the maximum temperature at three vertical profile levels, and (3) total duration of elevated temperature at these levels. Pre-burn plant information, including species diversity, plant height, and canopy diameter will be measured on shrubs from the plots to be burned and from control plots at the McGee ranch. General assessments of shrub survival, recovery, and recruitment will be made after the fire. Near-surface soil samples will be collected pre- and post-burn to determine changes in the gravel content of the surface layer so as to quantify inflationary or deflationary responses to fire and to reveal the ability of the surface to resist post-fire erosive stresses. Measures of bulk density, water repellency, water retention, and hydraulic conductivity will be used to characterize changes in infiltration rates and water storage capacity following the fire. Samples will also be analyzed to quantify geochemical changes including changes in soil pH, cation exchange capacity, specific surface area, and the concentration of macro nutrients (e.g. N, P, K) and other elements such as Na, Mg, Ca, that are critical to the post-fire recovery revegetation. Soil CO2 emissions will be measured monthly for one year following the burn to document post-fire stimulation of carbon turnover and soil biogenic emissions. Surface and subsurface temperature measurements at and near monitoring installations will be used to document fire effects on electronic equipment. The results of this study will be used to bridge the gaps in knowledge on the effects of fire on engineered ecosystems (e.g. surface barriers), particularly the hydrologic and biotic characteristics that govern the water and energy balance. These results will also support the development of practical fire management techniques for barriers that are compatible with wildfire suppression strategies. Furthermore, lessons learned will be use to develop installation strategies needed to protect electronic monitoring equipment from the intense heat of fire and the potential damaging effects of smoke and fire extinguishing agents. Such information is needed to better understand long-term barrier performance under extreme conditions, especially if site maintenance and operational funding is lost for activities such as barrier revegetation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Deep Learning Estimation of Daily Ground–Level NO 2 Concentrations from Remote Sensing Data

The limited number of nitrogen dioxide (NO 2 ) surface measurements calls for the development of highly accurate approaches to estimating surface NO 2 concentrations. In this study, we leverage a new satellite instrument, the TROPOspheric Monitoring Instrument (TROPOMI), along with other predictor variables, to estimate daily surface NO 2 concentrations over Texas in 2019. We use the deep convolutional neural network (Deep-CNN), an advanced deep learning algorithm, to obtain estimates and achieve a correlation coefficient (R) of 0.91, an index of agreement (IOA) of 0.95, and a mean absolute bias (MAB) of 1.75 ppb in surface NO 2 estimation. Additionally, we leverage a novel approach, SHapley Additive exPlanations (SHAP), to describe how Deep-CNN understands each predictor variable. The SHAP results show that the Deep-CNN model has an advanced understanding of the dataset, revealing that TROPOMI closely captures levels of NO 2 . In addition, we show the superiority of our Deep-CNN model at estimating surface NO 2 over other well-known machine learning and regression models in the field, including the support vector machines (SVM), random forest (RF), and multiple linear regression (MLR). Although SVM and RF show strong capabilities at estimating surface NO 2 concentrations, their accuracy is inferior to that of the Deep-CNN model, ranking second and third in model accuracy in this study. The MLR, however, shows a poor ability at NO 2 estimation and ranks last among all models. Furthermore, testing the impact of sample size on model performance, we also show that, compared to other models, Deep-CNN needs more samples to trigger its strength at surface NO 2 estimation.

54 ENVIRONMENTAL SCIENCES↗