Stanford University School of Medicine, Stanford, CA, 94305, USA; The Harker School, San Jose, CA, 95129, USA.
Stanford University School of Medicine, Stanford, CA, 94305, USA.
J Environ Manage. 2023 Sep 1;341:117908. doi: 10.1016/j.jenvman.2023.117908. Epub 2023 May 12.
Wildfires are increasingly impacting the environment and human health. Among the top 20 California wildfires, those in 2020-2021 burned more acres than the last century combined. Lack of an adequate early warning system impacts the health and safety of vulnerable populations disproportionately and widens the inequality gap. In this project, a multi-modal wildfire prediction and early warning system has been developed based on a novel spatio-temporal machine learning architecture. A comprehensive wildfire database with over 37 million data points was created, including the historical wildfires, environmental and meteorological sensor data from the Environmental Protection Agency, and geological data. The data was augmented into 2.53 km × 2.53 km square grids to overcome the sensor network coverage limitations. Leading and trailing indicators for the wildfires are proposed, classified, and tested. The leading indicators are correlated to the risks of wildfire conception, whereas the trailing indicators are correlated to the byproducts of the wildfires. Additionally, geological data was incorporated to provide additional information for better assessment on wildfire risks and propagation. Next, a novel U-Convolutional Long Short-Term Memory (ULSTM) neural network was developed to extract key spatial and temporal features of the dataset, specifically to address the spatial nature of the location of the wildfire and time-progression temporal nature of the wildfire evolution. Through iterative improvements and optimization, the final ULSTM network architecture, trained with data from 2012 to 2017, achieved >97% accuracy for predicting wildfires in 2018, as compared to ∼76% using traditional Convolutional Neural Network (CNN) techniques. The final model was applied to conduct a retrospective study for the 2018-2022 wildfire seasons, and successfully predicted 85.7% of wildfires >300 K acres in size. This technique could enable fire departments to anticipate and prevent wildfires before they strike and provide early warnings for at-risk individuals for better preparation, thereby saving lives, protecting the environment, and avoiding economic damages.
野火越来越多地影响着环境和人类健康。在加利福尼亚州的前 20 次大火中，2020-2021 年发生的火灾燃烧的面积比上个世纪的总和还要多。缺乏足够的早期预警系统会不成比例地影响弱势群体的健康和安全，并扩大不平等差距。在这个项目中，基于一种新颖的时空机器学习架构，开发了一种多模态野火预测和早期预警系统。创建了一个拥有超过 3700 万个数据点的综合野火数据库，其中包括历史野火、环境保护署的环境和气象传感器数据以及地质数据。将数据扩充到 2.53km×2.53km 的正方形网格中，以克服传感器网络覆盖范围的限制。提出、分类和测试了野火的领先和滞后指标。领先指标与野火概念的风险相关，而滞后指标与野火的副产品相关。此外，还纳入了地质数据，以为更好地评估野火风险和传播提供额外信息。接下来，开发了一种新颖的 U 型卷积长短期记忆 (ULSTM) 神经网络，以提取数据集的关键空间和时间特征，特别是解决野火位置的空间性质和野火演化的时间渐进性质。通过反复改进和优化，最终的 ULSTM 网络架构，使用 2012 年至 2017 年的数据进行训练，在预测 2018 年的野火时达到了＞97%的准确率，而使用传统的卷积神经网络 (CNN) 技术则约为 76%。最终模型应用于进行 2018-2022 年野火季节的回顾性研究，并成功预测了＞300K 英亩的 85.7%的野火。该技术可以使消防部门在野火发生之前预测和预防野火，并为高危个人提供早期预警，以便更好地做好准备，从而拯救生命、保护环境和避免经济损失。
