基于集成模拟的可解释斑块深度学习野火蔓延预测
Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations
浏览论文内容
中文总结 AI 辅助
本研究比较四种深度学习架构作为野火模拟器的代理，发现U-Net等卷积模型依赖火线距离，Swin-Unet更重视燃料地形，且模型可迁移至新区域。
中文摘要 AI 辅助
野火蔓延传统上使用基于物理的模拟器进行预测，这些模拟器具有物理可解释性，但其成本随每个额外集成成员的加入而增加。我们探究深度学习代理模型能否以该成本的一小部分重现这些模拟，并在西班牙加泰罗尼亚Rectoret地区2米分辨率的10,584次火灾蔓延模拟上训练它们。比较了四种架构：基于斑块的U-Net、迁移学习的ResNet-50、受风驱动平流方程约束的物理信息网络以及Swin-Unet Transformer。在地形和植被变量中，只有地表燃料负荷以任何强度预测燃烧概率（r = 0.27），将其纳入可将预测误差降低21%。其余变量相关性较弱且高度重复。接下来，使用显著性、遮挡和旋转的实验展示了模型的学习情况。卷积模型主要依赖距当前火线的距离，而Swin-Unet则更重视燃料和地形，这一发现也在一个无关的野火数据集中被注意到。当未经重新训练应用于第二个区域Pedriza时，所有三个卷积模型仍能预测火灾蔓延，但准确性以微小但系统性的幅度下降。
英文摘要
Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble member. We ask how well deep learning surrogates can reproduce these simulations at a fraction of this cost, training them on 10,584 fire spread simulations at 2m resolution for the Rectoret region in Catalonia, Spain. Four architectures are compared: a patch-based U-Net, a transfer-learned ResNet-50, a physics-informed network constrained by the wind-driven advection equation and a Swin-Unet transformer. Among the terrain and vegetation variables, only surface fuel load predicts burn probability with any strength (r = 0.27) and including it lowers prediction error by 21%. The remaining variables correlate weakly and are highly duplicative. Next, an experiment with saliency, occlusion and rotation demonstrates the models' learning. Convolutional models rely primarily on distance from the current fire front, while Swin-Unet assigns more weight to fuel and terrain, a finding also noted in an unrelated wildfire dataset. When applied without retraining to the second region, Pedriza, all three convolutional models still predict fire spread, losing accuracy by a small but systematic margin.
发表机构
- Poznan Supercomputing and Networking Center（波兹南超级计算与网络中心）
- MeteoGrid（MeteoGrid公司）
- Technical University of Czestochowa（琴斯特霍瓦技术大学）
机构由 AI 辅助整理，请以论文原文为准。
