Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction

• URL: http://arxiv.org/abs/2605.03148v2
• Date: Wed, 06 May 2026 08:45:15 GMT
• Title: Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction
• Abstract summary: Most deep learning models lack principled uncertainty quantification (UQ)<n>For boundary-sensitive cases like wildfire spread, evaluating models with global metrics alone is often insufficient.<n>Fire-Centered Evaluation Region (FCER) framework is introduced as a spatially conditioned protocol to characterize UQ within critical fire zones.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification (UQ). Further, for boundary-sensitive cases like wildfire spread, evaluating models with global metrics alone is often insufficient. To shift the focus of UQ evaluation toward a more operationally relevant approach, the Fire-Centered Evaluation Region (FCER) framework is introduced as a spatially conditioned protocol to characterize UQ within critical fire zones. Using FCER, an Ensemble is compared against an distilled single-pass student model on the WildfireSpreadTS dataset. The student model demonstrates comparable calibration and complementary uncertainty ranking in boundary-relevant regimes. Code is available at https://github.com/jonasvilhofunk/WildfireUQ-FCER

Related papers

• Revisiting TD Target Aggregation under Uncertainty in Q-Learning [2.4908682918195804]
  Deep Q-Networks (DQNs) learn value functions through bootstrapped temporal-difference updates, where future returns are approximated using a greedy aggregation over next-state values.<n>We propose textbfSuccessor Rollout textbfAggregation textbfDeep textbfQ-Network (SADQ), a simple rollout to Q-learning that regularizes how the TD target is formed.
  arXiv  Detail & Related papers  (2026-08-04T03:31:24Z)
• On the QUEST for Uncertainty Quantification via Highest Density Regions [5.1459761018260854]
  Uncertainty quantification (UQ) is essential for reliable decision-making in safety-critical applications in machine learning.<n>We propose an alternative framework, in which uncertainty is characterised by the volume of the most probable subset of a distribution's support.<n>QUEST (Quantifying Uncertainty via highest dEnSiTy regions) is a novel approach to UQ based on the concentration of Lebesgue measure at a distribution's peak(s)
  arXiv  Detail & Related papers  (2026-06-17T20:13:45Z)
• Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Models [0.0]
  We present the first application of conformal risk control (CRC) to wildfire spread prediction.<n>Standard thresholds capture only 7-72% of true fire spread, but CRC eliminates this failure uniformly.<n>Both models with CRC achieve approximately 95% fire coverage while flagging only approximately 15% of total pixels, making them 4.2x more efficient than LightGBM.
  arXiv  Detail & Related papers  (2026-03-20T21:05:13Z)
• Target Concept Tuning Improves Extreme Weather Forecasting [51.43578341469291]
  Deep learning models for meteorological forecasting often fail in rare but high-impact events such as typhoons.<n>Existing fine-tuning methods face a trade-off between overlooking these extreme events and overfitting them at the expense of overall performance.<n>We propose TaCT, an interpretable concept-gated fine-tuning framework that solves the aforementioned issue by selective model improvement.
  arXiv  Detail & Related papers  (2026-03-17T15:34:05Z)
• Adaptive Monitoring of Stochastic Fire Front Processes via Information-seeking Predictive Control [7.775545390766459]
  We consider the problem of adaptively monitoring a wildfire front using a mobile agent (e.g., a drone)<n>This is a challenging problem, as the nature of wildfire evolution requires the seamless integration of sensing, estimation, and control.<n>We formulate the fire front monitoring task as an optimal control problem that integrates sensing, estimation, and control.
  arXiv  Detail & Related papers  (2026-01-16T12:21:27Z)
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment [92.70019102733453]
  Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence.<n>We propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions.
  arXiv  Detail & Related papers  (2025-10-28T16:09:59Z)
• Uncertainty Quantification for Regression using Proper Scoring Rules [76.24649098854219]
  We introduce a unified UQ framework for regression based on proper scoring rules, such as CRPS, logarithmic, squared error, and quadratic scores.<n>We derive closed-form expressions for the uncertainty measures under practical parametric assumptions and show how to estimate them using ensembles of models.<n>Our broad evaluation on synthetic and real-world regression datasets provides guidance for selecting reliable UQ measures.
  arXiv  Detail & Related papers  (2025-09-30T17:52:12Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• RICA2: Rubric-Informed, Calibrated Assessment of Actions [8.641411594566714]
  We present RICA2 - a deep probabilistic model that score rubric and accounts for prediction uncertainty for action quality assessment (AQA) We demonstrate that our method establishes new state of the art on public benchmarks, including FineDiving, MTL-AQA, and JIGSAWS, with superior performance in score prediction and uncertainty calibration.
  arXiv  Detail & Related papers  (2024-08-04T20:35:33Z)
• Has the Deep Neural Network learned the Stochastic Process? An Evaluation Viewpoint [17.897121328003617]
  This paper presents the first systematic study of evaluating Deep Neural Networks (DNNs)<n>We show that traditional evaluation methods assess a DNN's ability to replicate the observed ground truth but fail to measure the underlying process.<n>We propose a new evaluation criterion called Fidelity toGT Process (F2SP)
  arXiv  Detail & Related papers  (2024-02-23T07:54:20Z)
• Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification [59.81904428056924]
  We introduce SMASH: a Score MAtching estimator for learning markedPs with uncertainty quantification. Specifically, our framework adopts a normalization-free objective by estimating the pseudolikelihood of markedPs through score-matching. The superior performance of our proposed framework is demonstrated through extensive experiments in both event prediction and uncertainty quantification.
  arXiv  Detail & Related papers  (2023-10-25T02:37:51Z)
• Prescribed Fire Modeling using Knowledge-Guided Machine Learning for Land Management [2.158876211806538]
  This paper introduces a novel machine learning (ML) framework that enables rapid emulation of prescribed fires. By incorporating domain knowledge, the proposed method helps reduce physical inconsistencies in fuel density estimates in data-scarce scenarios. We also overcome the problem of biased estimation of fire spread metrics by incorporating a hierarchical modeling structure.
  arXiv  Detail & Related papers  (2023-10-02T19:38:04Z)
• Numerically assisted determination of local models in network scenarios [55.2480439325792]
  We develop a numerical tool for finding explicit local models that reproduce a given statistical behaviour. We provide conjectures for the critical visibilities of the Greenberger-Horne-Zeilinger (GHZ) and W distributions. The developed codes and documentation are publicly available at281.com/mariofilho/localmodels.
  arXiv  Detail & Related papers  (2023-03-17T13:24:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.