Extreme-value forest fire prediction A study of the Loss Function in an Ordinality Scheme

• URL: http://arxiv.org/abs/2601.03327v2
• Date: Thu, 08 Jan 2026 16:01:17 GMT
• Title: Extreme-value forest fire prediction A study of the Loss Function in an Ordinality Scheme
• Authors: Nicolas Caron, Christophe Guyeux, Hassan Noura, Benjamin Aynes,
• Abstract summary: We introduce the first ordinal classification framework for forecasting wildfire severity levels directly aligned with operational decision-making in France.<n>Our study investigates the influence of loss-function design on the ability of neural models to predict rare yet critical high-severity fire occurrences.
• Score: 2.2049183478692593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wildfires are highly imbalanced natural hazards in both space and severity, making the prediction of extreme events particularly challenging. In this work, we introduce the first ordinal classification framework for forecasting wildfire severity levels directly aligned with operational decision-making in France. Our study investigates the influence of loss-function design on the ability of neural models to predict rare yet critical high-severity fire occurrences. We compare standard cross-entropy with several ordinal-aware objectives, including the proposed probabilistic TDeGPD loss derived from a truncated discrete exponentiated Generalized Pareto Distribution. Through extensive benchmarking over multiple architectures and real operational data, we show that ordinal supervision substantially improves model performance over conventional approaches. In particular, the Weighted Kappa Loss (WKLoss) achieves the best overall results, with more than +0.1 IoU (Intersection Over Union) gain on the most extreme severity classes while maintaining competitive calibration quality. However, performance remains limited for the rarest events due to their extremely low representation in the dataset. These findings highlight the importance of integrating both severity ordering, data imbalance considerations, and seasonality risk into wildfire forecasting systems. Future work will focus on incorporating seasonal dynamics and uncertainty information into training to further improve the reliability of extreme-event prediction.

Related papers

• EVEREST: An Evidential, Tail-Aware Transformer for Rare-Event Time-Series Forecasting [4.551615447454767]
  EVEREST is a transformer-based architecture for probabilistic rare-event forecasting.<n>It delivers calibrated predictions and tail-aware risk estimation.<n>It is applicable to high-stakes domains such as industrial monitoring, weather, and satellite diagnostics.
  arXiv  Detail & Related papers  (2026-01-26T23:15:20Z)
• Dynamic Attention (DynAttn): Interpretable High-Dimensional Spatio-Temporal Forecasting (with Application to Conflict Fatalities) [0.0]
  DynAttn is an interpretable dynamic-attention forecasting framework for high-dimensional count processes.<n>It produces multi-horizon forecasts of expected casualties and exceedance, while retaining transparent diagnostics.<n>Across forecast horizons from one to twelve months, DynAttn consistently achieves substantially higher predictive accuracy.
  arXiv  Detail & Related papers  (2025-12-24T21:47:35Z)
• Forests of Uncertaint(r)ees: Using tree-based ensembles to estimate probability distributions of future conflict [0.0]
  We develop a strategy to quantify uncertainty in conflict forecasting, shifting from traditional point predictions to full predictive distributions.<n>Models are able to consistently outperform a suite of benchmarks derived from conflict history in predictions up to one year in advance.<n>We emphasize the need to understand how a metric behaves for a given prediction problem, in our case characterized by extremely high zero-inflatedness.
  arXiv  Detail & Related papers  (2025-12-05T23:10:16Z)
• Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Network [0.13470973674919004]
  This study proposes an autoregressive conditional generative adversarial network (CGAN) for probabilistic wildfire spread prediction.<n>By formulating the prediction task as an autoregressive problem, the model learns sequential state transitions, ensuring long-term prediction stability.<n> Experimental results demonstrate that the proposed CGAN-based model outperforms conventional deep learning models in both overall predictive accuracy and boundary delineation of fire perimeters.
  arXiv  Detail & Related papers  (2025-11-26T03:32:54Z)
• xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion [65.63135031712153]
  We propose xTime, a novel framework for extreme event forecasting in time series.<n>xTime leverages knowledge distillation to transfer information from models trained on lower-rarity events.<n>We introduce a mixture of experts (MoE) mechanism that dynamically selects and fuses outputs from expert models across different rarity levels.
  arXiv  Detail & Related papers  (2025-10-23T15:24:45Z)
• SynCast: Synergizing Contradictions in Precipitation Nowcasting via Diffusion Sequential Preference Optimization [62.958457694151384]
  We introduce preference optimization into precipitation nowcasting for the first time, motivated by the success of reinforcement learning from human feedback in large language models.<n>In the first stage, the framework focuses on reducing FAR, training the model to effectively suppress false alarms.
  arXiv  Detail & Related papers  (2025-10-22T16:11:22Z)
• Deep learning framework for predicting stochastic take-off and die-out of early spreading [3.3147247892604708]
  Large-scale outbreaks pose significant threats to human society.<n>The question of whether an emerging outbreak will escalate into a major epidemic or naturally die out remains largely unaddressed.<n>Here, we introduce the first systematic framework for forecasting whether initial transmission events will amplify into major outbreaks.
  arXiv  Detail & Related papers  (2025-10-06T08:18:47Z)
• Accuracy Law for the Future of Deep Time Series Forecasting [65.46625911002202]
  Time series forecasting inherently faces a non-zero error lower bound due to its partially observable and uncertain nature.<n>This paper focuses on a fundamental question: how to estimate the performance upper bound of deep time series forecasting.<n>Based on rigorous statistical tests of over 2,800 newly trained deep forecasters, we discover a significant exponential relationship between the minimum forecasting error of deep models and the complexity of window-wise series patterns.
  arXiv  Detail & Related papers  (2025-10-03T05:18:47Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• Performative Time-Series Forecasting [64.03865043422597]
  We formalize performative time-series forecasting (PeTS) from a machine-learning perspective.<n>We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts.<n>We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-09T18:34:29Z)
• AA-Forecast: Anomaly-Aware Forecast for Extreme Events [25.89754218631525]
  Time series models often deal with extreme events and anomalies, both prevalent in real-world datasets. We propose an anomaly-aware forecast framework that leverages the previously seen effects of anomalies to improve its prediction accuracy. Specifically, the framework automatically extracts anomalies and incorporates them through an attention mechanism to increase its accuracy for future extreme events.
  arXiv  Detail & Related papers  (2022-08-21T17:51:46Z)
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [70.54920804222031]
  Most existing forecasting models disregard uncertainty quantification, resulting in mis-calibrated predictions. Recent works in deep neural models for uncertainty-aware time-series forecasting also have several limitations. We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP.
  arXiv  Detail & Related papers  (2021-06-07T18:31:47Z)

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.