arXiv subjects

Miguel Esparza

Publications and source records attributed to Miguel Esparza.

6 recordsLinked to original sources

arXiv2026

Modular Deep Learning Mechanisms for Auditable Next-Day Wildfire Spread Prediction

Next-day wildfire prediction requires models whose forecasts can be evaluated alongside the assumptions and historical evidence used in their computation. Although deep learning can learn spatial patterns from remote-sensing data, predictive performance alone does not establish physical fidelity or operational trustworthiness. This study investigates three modular augmentations for next-day active-fire prediction: wind- and slope-conditioned attention biases, physics-feature retrieval-augmented output correction, and fire conditioned dual-stream gating. The attention biases expose prescribed directional preferences, while the retrieval module selects historical tiles using a nine-dimensional environmental and fire-state descriptor and applies a learned correction to a frozen model's logits. The modules are evaluated across five backbones on the Next Day Wildfire Spread benchmark, using staged ablations, directional audits, retrieval perturbations, calibration measures, and computational comparisons. The three-seed mean F1 score and area under the precision--recall curve (AUC-PR) of a SwinUNETR model with all three augmentations are 0.4216 and 0.3673. Then, a mixed ensemble (two augmented architectures and one non-augmented architecture) model achieves 0.4292 and 0.3790. Benefits vary across architectures, and retrieval-related improvements in AUC-PR do not consistently translate into higher F1. The constructed wind bias aligns closely with input wind, but its alignment with observed next-day fire displacement is much weaker, distinguishing prior inspectability from predictive physical fidelity. The study contributes a framework for exposing and evaluating selected domain-informed components within wildfire prediction models. Together, the results presented show that predictive performance, operational trustworthiness, and computational practicality need not be competing objectives.

cs.LG↗

arXiv2026

Automated Wildfire Damage Assessment from Multi view Ground level Imagery Via Vision Language Models

The escalating intensity and frequency of wildfires demand innovative computational methods for rapid and accurate property damage assessment. Traditional methods are often time-consuming, while modern computer vision approaches typically require extensive labeled datasets, hindering immediate post-disaster deployment. This research introduces a novel, zero-shot framework leveraging pre-trained multimodal large language models (MLLMs) to classify damage from ground-level imagery. Using Generative Pre-trained Transformer 4o (GPT-4o) as the primary model with comparative validation against Qwen2.5-Vision-Language-32-Billion-Instruct (Qwen), the research evaluates two pipelines applied to the 2025 Eaton and Palisades fires in California. These pipelines include an end-to-end inference method (Pipeline A) and a decoupled workflow where visual cues drive text-based classification (Pipeline B). A primary contribution of this study is demonstrating the efficacy of MLLMs in synthesizing information from multiple perspectives. The findings show that while single-view assessments struggle to classify intermediate damage, a multi-view analysis yields dramatic improvements. To explore the impact of prompting methods, the research benchmarked a baseline zero-shot and heuristic approach against advance reasoning strategies (Structured-Chain-of-Thought and Self-Consistency). The results indicate that simple prompting methods achieve a comparable accuracy to the reasoning strategies.

cs.CV↗

arXiv2026

Recov-Vision: Linking Street View Imagery and Vision-Language Models for Post-Disaster Recovery

Building-level occupancy after disasters is vital for triage, inspections, utility re-energization, and equitable resource allocation. Overhead imagery provides rapid coverage but often misses facade and access cues that determine habitability, while street-view imagery captures those details but is sparse and difficult to align with parcels. We present FacadeTrack, a street-level, language-guided framework that links panoramic video to parcels, rectifies views to facades, and elicits interpretable attributes (for example, entry blockage, temporary coverings, localized debris) that drive two decision strategies: a transparent one-stage rule and a two-stage design that separates perception from conservative reasoning. Evaluated across two post-Hurricane Helene surveys, the two-stage approach achieves a precision of 0.927, a recall of 0.781, and an F-1 score of 0.848, compared with the one-stage baseline at a precision of 0.943, a recall of 0.728, and an F-1 score of 0.822. Beyond accuracy, intermediate attributes and spatial diagnostics reveal where and why residual errors occur, enabling targeted quality control. The pipeline provides auditable, scalable occupancy assessments suitable for integration into geospatial and emergency-management workflows.

cs.CV↗

arXiv2025

GraphFire-X: Physics-Informed Graph Attention Networks and Structural Gradient Boosting for Building-Scale Wildfire Preparedness at the Wildland-Urban Interface

As wildfires increasingly evolve into urban conflagrations, traditional risk models that treat structures as isolated assets fail to capture the non-linear contagion dynamics characteristic of the wildland urban interface (WUI). This research bridges the gap between mechanistic physics and data driven learning by establishing a novel dual specialist ensemble framework that disentangles vulnerability into two distinct vectors, environmental contagion and structural fragility. The architecture integrates two specialized predictive streams, an environmental specialist, implemented as a graph neural network (GNN) that operationalizes the community as a directed contagion graph weighted by physics informed convection, radiation, and ember probabilities, and enriched with high dimensional Google AlphaEarth Foundation embeddings, and a Structural Specialist, implemented via XGBoost to isolate granular asset level resilience. Applied to the 2025 Eaton Fire, the framework reveals a critical dichotomy in risk drivers. The GNN demonstrates that neighborhood scale environmental pressure overwhelmingly dominates intrinsic structural features in defining propagation pathways, while the XGBoost model identifies eaves as the primary micro scale ingress vector. By synthesizing these divergent signals through logistic stacking, the ensemble achieves robust classification and generates a diagnostic risk topology. This capability empowers decision makers to move beyond binary loss prediction and precisely target mitigation prioritizing vegetation management for high connectivity clusters and structural hardening for architecturally vulnerable nodes thereby operationalizing a proactive, data driven approach to community resilience.

cs.LG↗

arXiv2024

AI Meets Natural Hazard Risk: A Nationwide Vulnerability Assessment of Data Centers to Natural Hazards and Power Outages

Our society is on the verge of a revolution powered by Artificial Intelligence (AI) technologies. With increasing advancements in AI, there is a growing expansion in data centers (DCs) serving as critical infrastructure for this new wave of technologies. This technological wave is also on a collision course with exacerbating climate hazards which raises the need for evaluating the vulnerability of DCs to various hazards. Hence, the objective of this research is to conduct a nationwide vulnerability assessment of (DCs) in the United States of America (USA). DCs provide such support; however, if an unplanned disruption (like a natural hazard or power outage) occurs, the functionality of DCs are in jeopardy. Unplanned downtime in DCs cause severe economic and social repercussions. With the Local Indicator of Spatial Association (LISA) test, the research found that there are a large percentage of DCs that are in non-vulnerable areas of disruption; however, there is still a notable percentage in disruption prone areas. For example, earthquakes, hurricanes, and tornadoes have the most DCs in vulnerable areas. After identifying these vulnerabilities, the research identified areas within the USA that have minimal vulnerabilities to both the aforementioned natural hazards and power outages with the BI-LISA test. After doing a composite vulnerability score on the Cold-Spots from the BILISA analysis, the research found three counties with the low vulnerability scores. These are Koochiching, Minnesota (0.091), Schoolcraft, Michigan (0.095), and Houghton, Michigan (0.096).

cs.CY↗

arXiv2022

Examining Data Imbalance in Crowdsourced Reports for Improving Flash Flood Situational Awareness

The use of crowdsourced data has been finding practical use for enhancing situational awareness during disasters. While recent studies have shown promising results regarding the potential of crowdsourced data for flood mapping, little attention has been paid to data imbalances issues that could introduce biases. We examine biases present in crowdsourced reports to identify data imbalances with a goal of improving disaster situational awareness. Sample bias, spatial bias, and demographic bias are examined as we analyzed reported flooding from 3-1-1, Waze reports, and FEMA damage data collected in the aftermaths of Tropical Storm Imelda in 2019 and Hurricane Ida in 2021. Integrating other flooding related topics from 3-1-1 reports into the Global Moran's I and Local Indicator of Spatial Association (LISA) test revealed more communities that were impacted by floods. To examine spatial bias, we perform the LISA and BI-LISA tests on the three datasets at the census tract and census block group level. By looking at two geographical aggregations, we found that the larger spatial aggregations, census tracts, show less data imbalance in the results. Finally, one-way analysis of Variance (ANOVA) test performed on the clusters generated from the BI-LISA shows that data imbalance exists in areas where minority populations reside. Through a regression analysis, we found that 3-1-1 and Waze reports have data imbalance limitations in areas where minority populations reside. The findings of this study advance understanding of data imbalances and biases in crowdsourced datasets that are growingly used for disaster situational awareness.

cs.CY↗