Predicting Next-Day Wildfire Spread with Time Series and Attention

• URL: http://arxiv.org/abs/2502.12003v1
• Date: Mon, 17 Feb 2025 16:41:46 GMT
• Title: Predicting Next-Day Wildfire Spread with Time Series and Attention
• Authors: Saad Lahrichi, Jesse Johnson, Jordan Malof,
• Abstract summary: We investigate a transformer-based model, termed the SwinUnet, for next-day wildfire prediction. We benchmark Swin-based models against several current state-of-the-art models on WildfireSpreadTS. We find that, with the proper modifications, SwinUnet achieves state-of-the-art accuracy on next-day prediction for both the single-day and multi-day scenarios.
• Score: 1.6385815610837162
• License:
• Abstract: Recent research has demonstrated the potential of deep neural networks (DNNs) to accurately predict next-day wildfire spread, based upon the current extent of a fire and geospatial rasters of influential environmental covariates e.g., vegetation, topography, climate, and weather. In this work, we investigate a recent transformer-based model, termed the SwinUnet, for next-day wildfire prediction. We benchmark Swin-based models against several current state-of-the-art models on WildfireSpreadTS (WFTS), a large public benchmark dataset of historical wildfire events. We consider two next-day fire prediction scenarios: when the model is given input of (i) a single previous day of data, or (ii) five previous days of data. We find that, with the proper modifications, SwinUnet achieves state-of-the-art accuracy on next-day prediction for both the single-day and multi-day scenarios. SwinUnet's success depends heavily upon utilizing pre-trained weights from ImageNet. Consistent with prior work, we also found that models with multi-day-input always outperformed models with single-day input.

Related papers

• A generative model for surrogates of spatial-temporal wildfire nowcasting [13.551652250858144]
  A generative model is proposed using a three-dimensional Vector-Quantized Variational Autoencoders. The model is tested in the ecoregion of a recent massive wildfire event in California, known as the Chimney fire. Numerical results show that the model succeed in generating coherent and structured fire scenarios.
  arXiv  Detail & Related papers  (2023-08-05T06:54:18Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• Wildfire Forecasting with Satellite Images and Deep Generative Model [0.0]
  We use a series of wildfire images as a video to anticipate how the fire would behave in the future. We introduce a novel temporal model whose dynamics are driven in a latent space. Results will be compared towards various benchmarking models.
  arXiv  Detail & Related papers  (2022-08-19T15:52:43Z)
• CEP3: Community Event Prediction with Neural Point Process on Graph [59.434777403325604]
  We propose a novel model combining Graph Neural Networks and Marked Temporal Point Process (MTPP) Our experiments demonstrate the superior performance of our model in terms of both model accuracy and training efficiency.
  arXiv  Detail & Related papers  (2022-05-21T15:30:25Z)
• Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data [5.814925201882753]
  Next Day Wildfire Spread' is a curated data set of historical wildfires aggregating nearly a decade of remote-sensing data across the United States. We implement a convolutional autoencoder that takes advantage of the spatial information of this data to predict wildfire spread. This data set can be used as a benchmark for developing wildfire propagation models based on remote sensing data for a lead time of one day.
  arXiv  Detail & Related papers  (2021-12-04T23:28:44Z)
• Learning Wildfire Model from Incomplete State Observations [0.0]
  We create a dynamic model for future wildfire predictions of five locations within the western United States through a deep neural network. The proposed model has distinct features that address the characteristic need in prediction evaluations, including dynamic online estimation and time-series modeling.
  arXiv  Detail & Related papers  (2021-11-28T03:21:46Z)
• Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report [70.7321040534471]
  Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. There is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting.
  arXiv  Detail & Related papers  (2021-09-01T09:52:31Z)
• Improving Event Duration Prediction via Time-aware Pre-training [90.74988936678723]
  We introduce two effective models for duration prediction. One model predicts the range/unit where the duration value falls in (R-pred); and the other predicts the exact duration value E-pred. Our best model -- E-pred, substantially outperforms previous work, and captures duration information more accurately than R-pred.
  arXiv  Detail & Related papers  (2020-11-05T01:52:11Z)
• Modeling Wildfire Perimeter Evolution using Deep Neural Networks [0.0]
  We propose a wildfire spreadingmodel that predicts the evolution of the wildfire perimeter in 24 hour periods. The model is able to learn wildfirespreading dynamics from real historic data sets from wildfires in the Western Sierra Nevada Mountains in Cal-ifornia.
  arXiv  Detail & Related papers  (2020-09-08T20:06:01Z)
• Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
  We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
  arXiv  Detail & Related papers  (2020-03-10T09:15:42Z)
• A Multi-Channel Neural Graphical Event Model with Negative Evidence [76.51278722190607]
  Event datasets are sequences of events of various types occurring irregularly over the time-line. We propose a non-parametric deep neural network approach in order to estimate the underlying intensity functions.
  arXiv  Detail & Related papers  (2020-02-21T23:10:50Z)

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.