arXiv subjects

Adam Watts

Publications and source records attributed to Adam Watts.

13 recordsLinked to original sources

arXiv2026

ShearFuse-UNet: Hadamard, DCT, and Shearlet Transform Fusion for Next-Day Wildfire Spread Prediction

We propose ShearFuse-UNet, a lightweight and computationally efficient deep learning model for next-day wildfire spread prediction from multi-modal satellite data. The model integrates three complementary transform-domain branches inside each encoder block of a U-Net backbone: a 2D Fast Walsh-Hadamard Transform (WHT) branch, a 2D Discrete Cosine Transform (DCT) branch, and a cone-adapted digital Shearlet residual branch. The WHT and DCT branches establish orthogonal latent spaces with learnable spectral scaling and fixed soft-thresholding, while the Shearlet branch provides anisotropic, multi-directional feature decomposition that explicitly encodes the elongated edge structures characteristic of fire fronts. A learned SpectralFusion gate adaptively combines the WHT and DCT responses, and the Shearlet reconstruction is added as a residual. This three-branch design bears a loose structural analogy to transformer self-attention: the WHT and DCT branches provide complementary spectral representations that are adaptively fused, while the Shearlet branch contributes directional content through a residual pathway. Unlike self-attention, the proposed design relies on fixed mathematical transforms rather than learned projection operators, reducing parameter count and computational cost. Evaluated on the WildfireSpreadTS dataset, ShearFuse-UNet achieves an F1 score of 0.596 with only 267k parameters, outperforming a ResNet18-based U-Net (14M parameters, F1 = 0.589) and demonstrating a highly favorable accuracy-efficiency trade-off. Results on the Google Next-Day Wildfire Spread dataset further validate these findings across a different benchmark.

cs.CV↗

arXiv2026

Inverse Reconstruction of Shock Time Series from Shock Response Spectrum Curves using Machine Learning

The shock response spectrum (SRS) is widely used to characterize the response of single-degree-of-freedom (SDOF) systems to transient accelerations. Because the mapping from acceleration time history to SRS is nonlinear and many-to-one, reconstructing time-domain signals from a target spectrum is inherently ill-posed. Conventional approaches address this problem through iterative optimization, typically representing signals as sums of exponentially decayed sinusoids, but these methods are computationally expensive and constrained by predefined basis functions. We propose a conditional variational autoencoder (CVAE) that learns a data-driven inverse mapping from SRS to acceleration time series. Once trained, the model generates signals consistent with prescribed target spectra without requiring iterative optimization. Experiments demonstrate improved spectral fidelity relative to classical techniques, strong generalization to unseen spectra, and inference speeds three to six orders of magnitude faster. These results establish deep generative modeling as a scalable and efficient approach for inverse SRS reconstruction.

cs.LG↗

arXiv2026

U-Net with Hadamard Transform and DCT Latent Spaces for Next-day Wildfire Spread Prediction

We developed a lightweight and computationally efficient tool for next-day wildfire spread prediction using multimodal satellite data as input. The deep learning model, which we call Transform Domain Fusion UNet (TD-FusionUNet), incorporates trainable Hadamard Transform and Discrete Cosine Transform layers that apply two-dimensional transforms, enabling the network to capture essential "frequency" components in orthogonalized latent spaces. Additionally, we introduce custom preprocessing techniques, including random margin cropping and a Gaussian mixture model, to enrich the representation of the sparse pre-fire masks and enhance the model's generalization capability. The TD-FusionUNet is evaluated on two datasets which are the Next-Day Wildfire Spread dataset released by Google Research in 2023, and WildfireSpreadTS dataset. Our proposed TD-FusionUNet achieves an F1 score of 0.591 with 370k parameters, outperforming the UNet baseline using ResNet18 as the encoder reported in the WildfireSpreadTS dataset while using substantially fewer parameters. These results show that the proposed latent space fusion model balances accuracy and efficiency under a lightweight setting, making it suitable for real time wildfire prediction applications in resource limited environments.

cs.CV↗

arXiv2026

The impact of ram pressure on the radio spectral index and magnetic field of NGC 4522: A high-resolution VLA continuum study

We present high-resolution Very Large Array (VLA) continuum observations at S-band ($3$ GHz, $560$ pc scale) and X-band ($10$ GHz, $200$ pc scale) of the ram-pressure-stripped Virgo galaxy NGC 4522, to investigate the characteristics of its radio continuum, spectral index, and magnetic field under the influence of the intracluster medium (ICM). The total radio continuum shows an asymmetry that extends northwest, mirroring the HI gas distribution, but showing distinct features in the extraplanar regions. The spectral index steepens systematically from $\alpha\sim-0.6$ in the main disk to $\alpha\sim-1.1$ in the outer disk. We find that the spectral index behavior of the outer disk is mainly due to an ICM shock that can re-accelerate electrons and a significant reduction of thermal emission. Intriguingly, extraplanar clouds exhibit exceptionally flat spectral indices ($\alpha\sim-0.2$ to $0$), resulting from a combination of significantly enhanced thermal emission and pronounced spectral aging of the non-thermal component. Although some of these regions correlate with H$\alpha$, others do not. We propose that the mixing between the ICM and interstellar medium (ISM) is an alternative mechanism that enhances thermal emission independently of star formation. Polarized continuum emissions are highly asymmetric, preferentially distributed along the ICM wind side, and the polarization fraction increases radially outward from the galactic midplane, indicating that the polarized emission is strongly influenced by the ICM wind. Our results show how and where the ICM substantially affects the ISM, and also demonstrate that high-frequency observations are crucial for analyzing the radio continuum of ram pressure stripping galaxies.

astro-ph.GA↗

arXiv2025

Concepts Rookie Book

This book begins with the basic accelerator knowledge required to understand the latter chapters. This is followed by topics from Fermilab accelerator specifics to general accelerator physics concepts. These chapters are accompanied by descriptions of the instrumentation and utilities required to operate a high-energy physics laboratory. Last, we discuss the role of operators in safety at the lab.

physics.acc-ph↗

arXiv2024

Sub-Meter Remote Sensing of Soil Moisture Using Portable L-band Microwave Radiometer

Spaceborne microwave passive soil moisture products are known for their accuracy but are often limited by coarse spatial resolutions. This limits their ability to capture finer soil moisture gradients and hinders their applications. The Portable L band radiometer (PoLRa) offers soil moisture measurements from submeter to tens of meters depending on the altitude of measurement. Given that the assessments of soil moisture derived from this sensor are notably lacking, this study aims to evaluate the performance of submeter soil moisture retrieved from PoLRa mounted on poles at four different locations in central Illinois, USA. The evaluation focuses on the consistency of PoLRa measured brightness temperatures from different directions relative to the same area, and the accuracy of PoLRa derived soil moisture. As PoLRa shares many aspects of the L band radiometer onboard the NASA Soil Moisture Active Passive (SMAP) mission, two SMAP operational algorithms and the conventional dual channel algorithm were applied to calculate soil moisture from the measured brightness temperatures. The vertically polarized brightness temperatures from the PoLRa are typically more stable than their horizontally polarized counterparts. In each test period, the standard deviations of observed dual polarization brightness temperatures are generally less than 5 K. By comparing PoLRa based soil moisture retrievals against the moisture values obtained by handheld time domain reflectometry, the unbiased root mean square error and the Pearson correlation coefficient are mostly below 0.04 and above 0.75, confirming the high accuracy of PoLRa derived soil moisture retrievals and the feasibility of utilizing SMAP algorithms for PoLRa data. These findings highlight the significant potential of ground or drone based PoLRa measurements as a standalone reference for future spaceborne L band sensors.

eess.SP↗

arXiv2024

Joint Soil and Above-Ground Biomass Characterization Using Radars

Soil moisture sensing through biomass or vegetation canopy has challenged researchers, even those who use SAR sensors with penetration capabilities. This is mainly due to the imposed extra time and phase offsets on Radio Frequency (RF) signals as they travel through the canopy. These offsets depend on the vegetation canopy moisture and height, both of which are typically unknown in agricultural and forest fields. In this paper, we leverage the mobility of an unmanned aerial system (UAS) to collect spatially-diverse radar measurements, enabling the joint estimation of soil moisture, above-ground biomass moisture, and biomass height, all without assuming any calibration steps. We leverage the changes in time-of-flight (ToF) and angle-of-arrival (AoA) measurements of reflected radar signals as the UAS flies above a reflector buried under the soil. We demonstrate the effectiveness of our algorithm by simulating its performance under realistic measurement noises as well as conducting lab experiments with different types of above-ground biomass. Our simulation results conclude that our algorithm is capable of estimating volumetric soil moisture to less than 1% median absolute error (MAE), vegetation height to 11.1cm MAE, and vegetation relative permittivity to 0.32 MAE. Our experimental results demonstrate the effectiveness of the proposed method in practical scenarios for varying biomass moistures and heights.

eess.SP↗

arXiv2024

Confidence Intervals on Multivariate Normal Quantiles for Environmental Specification Development in Multi-axis Shock and Vibration Testing

This article describes two Monte Carlo methods for calculating confidence intervals on cumulative density function (CDF) based multivariate normal quantiles that allows for controlling the tail regions of a multivariate distribution where one is most concerned about extreme responses. The CDF based multivariate normal quantiles associated with bivariate distributions are represented as contours and for trivariate distributions represented as iso-surfaces. We first provide a novel methodology for an inverse problem, characterizing the uncertainty on the $\tau^{\mathrm{th}}$ multivariate quantile probability, when using concurrent univariate quantile probabilities. The uncertainty on the $\tau^{\mathrm{th}}$ multivariate quantile probability demonstrates inadequacy in univariate methods which neglect correlation between multiple variates. Limitations of traditional multivariate normal tolerance regions and simultaneous univariate tolerance methods are discussed thereby necessitating the need for confidence intervals on CDF based multivariate normal quantiles. Two Monte Carlo methods are discussed; the first calculates the CDF over a tessellated domain followed by taking a bootstrap confidence interval over the tessellated CDF. The CDF based multivariate quantiles are then estimated from the CDF confidence intervals. For the second method, only the point associated with highest probability density along the CDF based quantile is calculated, which greatly improves the computational speed compared to the first method. Monte Carlo simulation studies are used to assess the performance of the various methods. Finally, real data analysis is performed to illustrate a workflow for CDF based multivariate normal quantiles in the domain of mechanical shock and vibration to specify a minimum conservative test level for environmental specification.

stat.ME↗

arXiv2024

Dual-Frequency Radar Wave-Inversion for Sub-Surface Material Characterization

Moisture estimation of sub-surface soil and the overlaying biomass layer is pivotal in precision agriculture and wildfire risk assessment. However, the characterization of layered material is nontrivial due to the radar penetration-resolution tradeoff. Here, a waveform inversion-based method was proposed for predicting the dielectric permittivity (as a moisture proxy) of the bottom soil layer and the top biomass layer from radar signals. Specifically, the use of a combination of a higher and a lower frequency radar compared to a single frequency in predicting the permittivity of both the soil and the overlaying layer was investigated in this study. The results show that each layer was best characterized via one of the frequencies. However, for the simultaneous prediction of both layers permittivity, the most consistent results were achieved by inversion of data from a combination of both frequencies, showing better correlation with in situ permittivity and reduced prediction errors.

eess.SP↗

arXiv2024

FUELVISION: A Multimodal Data Fusion and Multimodel Ensemble Algorithm for Wildfire Fuels Mapping

Accurate assessment of fuel conditions is a prerequisite for fire ignition and behavior prediction, and risk management. The method proposed herein leverages diverse data sources including Landsat-8 optical imagery, Sentinel-1 (C-band) Synthetic Aperture Radar (SAR) imagery, PALSAR (L-band) SAR imagery, and terrain features to capture comprehensive information about fuel types and distributions. An ensemble model was trained to predict landscape-scale fuels such as the 'Scott and Burgan 40' using the as-received Forest Inventory and Analysis (FIA) field survey plot data obtained from the USDA Forest Service. However, this basic approach yielded relatively poor results due to the inadequate amount of training data. Pseudo-labeled and fully synthetic datasets were developed using generative AI approaches to address the limitations of ground truth data availability. These synthetic datasets were used for augmenting the FIA data from California to enhance the robustness and coverage of model training. The use of an ensemble of methods including deep learning neural networks, decision trees, and gradient boosting offered a fuel mapping accuracy of nearly 80\%. Through extensive experimentation and evaluation, the effectiveness of the proposed approach was validated for regions of the 2021 Dixie and Caldor fires. Comparative analyses against high-resolution data from the National Agriculture Imagery Program (NAIP) and timber harvest maps affirmed the robustness and reliability of the proposed approach, which is capable of near-real-time fuel mapping.

eess.IV↗

arXiv2024

A comprehensive survey of research towards AI-enabled unmanned aerial systems in pre-, active-, and post-wildfire management

Wildfires have emerged as one of the most destructive natural disasters worldwide, causing catastrophic losses in both human lives and forest wildlife. Recently, the use of Artificial Intelligence (AI) in wildfires, propelled by the integration of Unmanned Aerial Vehicles (UAVs) and deep learning models, has created an unprecedented momentum to implement and develop more effective wildfire management. Although some of the existing survey papers have explored various learning-based approaches, a comprehensive review emphasizing the application of AI-enabled UAV systems and their subsequent impact on multi-stage wildfire management is notably lacking. This survey aims to bridge these gaps by offering a systematic review of the recent state-of-the-art technologies, highlighting the advancements of UAV systems and AI models from pre-fire, through the active-fire stage, to post-fire management. To this aim, we provide an extensive analysis of the existing remote sensing systems with a particular focus on the UAV advancements, device specifications, and sensor technologies relevant to wildfire management. We also examine the pre-fire and post-fire management approaches, including fuel monitoring, prevention strategies, as well as evacuation planning, damage assessment, and operation strategies. Additionally, we review and summarize a wide range of computer vision techniques in active-fire management, with an emphasis on Machine Learning (ML), Reinforcement Learning (RL), and Deep Learning (DL) algorithms for wildfire classification, segmentation, detection, and monitoring tasks. Ultimately, we underscore the substantial advancement in wildfire modeling through the integration of cutting-edge AI techniques and UAV-based data, providing novel insights and enhanced predictive capabilities to understand dynamic wildfire behavior.

cs.LG↗

arXiv2023

Bayesian inversion of GPR waveforms for sub-surface material characterization: an uncertainty-aware retrieval of soil moisture and overlaying biomass properties

Accurate estimation of sub-surface properties such as moisture content and depth of soil and vegetation layers is crucial for applications spanning sub-surface condition monitoring, precision agriculture, and effective wildfire risk assessment. Soil in nature is often covered by overlaying vegetation and surface organic material, making its characterization challenging. In addition, the estimation of the properties of the overlaying layer is crucial for applications like wildfire risk assessment. This study thus proposes a Bayesian model-updating-based approach for ground penetrating radar (GPR) waveform inversion to predict moisture contents and depths of soil and overlaying material layer. Due to its high correlation with moisture contents, the dielectric permittivity of both layers were predicted with the proposed method, along with other parameters, including depth and electrical conductivity of layers. The proposed Bayesian model updating approach yields probabilistic estimates of these parameters that can provide information about the confidence and uncertainty related to the estimates. The methodology was evaluated for a diverse range of experimental data collected through laboratory and field investigations. Laboratory investigations included variations in soil moisture values, depth of the overlaying surface layer, and coarseness of its material. The field investigation included measurement of field soil moisture for sixteen days. The results demonstrated predictions consistent with time-domain reflectometry (TDR) measurements and conventional gravimetric tests. The depth of the surface layer could also be predicted with reasonable accuracy. The proposed method provides a promising approach for uncertainty-aware sub-surface parameter estimation that can enable decision-making for risk assessment across a wide range of applications.

eess.SP↗

arXiv2022

VERTICO IV: Environmental Effects on the Gas Distribution and Star Formation Efficiency of Virgo Cluster Spirals

We measure the molecular-to-atomic gas ratio, $R_{\rm mol}$, and the star formation rate (SFR) per unit molecular gas mass, SFE$_{\rm mol}$, in 38 nearby galaxies selected from the Virgo Environment Traced in CO (VERTICO) survey. We determine their scale-lengths for the molecular and stellar components and find a roughly 3:5 ratio between them compared to $\sim$1:1 in field galaxies, indicating that the CO emission is more centrally concentrated than the stars. We compute $R_{\rm mol}$ as a function of different physical quantities. While the spatially-resolved $R_{\rm mol}$ on average decreases with increasing radius, we find that the mean molecular-to-atomic gas ratio within the stellar effective radius $R_{\rm e}$, $R_{\rm mol}(r<R_{\rm e})$, shows a systematic increase with the level of H$_{\rm I}$, truncation and/or asymmetry (H$_{\rm I}$ perturbation). Analysis of the molecular- and the atomic-to-stellar mass ratios within $R_{\rm e}$, $R^{\rm mol}_{\star}(r<R_{\rm e})$ and $R^{\rm atom}_{\star}(r<R_{\rm e})$, shows that VERTICO galaxies have increasingly lower $R^{\rm atom}_{\star}(r<R_{\rm e})$ for larger levels of H$_{\rm I}$perturbation (compared to field galaxies matched in stellar mass), but no significant change in $R^{\rm mol}_{\star}(r<R_{\rm e})$. We also measure a clear systematic decrease of the SFE$_{\rm mol}$ within $R_{\rm e}$, SFE$_{\rm mol}(r<R_{\rm e})$, with increasingly perturbed H$_{\rm I}$. Therefore, compared to galaxies from the field, VERTICO galaxies are more compact in CO emission in relation to their stellar distribution, but increasingly perturbed atomic gas increases their $R_{\rm mol}$ and decreases the efficiency with which their molecular gas forms stars. (abridged)

astro-ph.GA↗