Accurate forecasts of fine particulate matter (PM 2.5) from wildfire smoke are crucial to safeguarding cardiopulmonary public health. Existing forecasting systems are trained on sparse and inaccurate ground truths, and do not take sufficient advantage of important spatial inductive biases. In this work, we present a convolutional neural network which preserves sparsity invariance throughout, and leverages multitask learning to perform dense forecasts of PM 2.5values. We demonstrate that our model outperforms two existing smoke forecasting systems during the 2018 and 2019 wildfire season in British Columbia, Canada, predicting PM 2.5 at a grid resolution of 10 km, 24 hours in advance with high fidelity. Most interestingly, our model also generalizes to meaningful smoke dispersion patterns despite training with irregularly distributed ground truth PM 2.5 values available in only 0.5% of grid cells.

中文翻译：

---

使用稀疏不变卷积神经网络对野火烟雾颗粒物进行密集预测

准确预测来自野火烟雾的细颗粒物 (PM 2.5) 对于保护心肺公共卫生至关重要。现有的预测系统在稀疏和不准确的地面实况上进行训练，并且没有充分利用重要的空间归纳偏差。在这项工作中，我们提出了一个卷积神经网络，它始终保持稀疏不变性，并利用多任务学习来执行 PM 2.5 值的密集预测。我们证明，我们的模型在 2018 年和 2019 年加拿大不列颠哥伦比亚省的野火季节期间优于两个现有的烟雾预测系统，以高保真度提前 24 小时以 10 公里的网格分辨率预测 PM 2.5。最有趣的是，