U-Net with Hadamard Transform and DCT Latent Spaces for Next-day Wildfire Spread Prediction

TL;DR

The paper addresses next-day wildfire spread prediction using multimodal satellite data under resource constraints. It introduces a lightweight Transform Domain Fusion UNet (TD-FusionUNet) that learns transform-domain representations via HT and DCT latent spaces, embedded through HT-perceptron layers, soft-thresholding, and a dual-branch architecture. Custom preprocessing (random margin cropping and Gaussian mixture smoothing) enhances sparsity handling and generalization. Empirical results show strong accuracy with far fewer parameters (e.g., 370k) than ResNet18-based UNets, achieving F1 scores of 0.591 on WildfireSpreadTS and high performance on Google’s dataset, highlighting practical potential for real-time, edge-enabled wildfire forecasting.

Abstract

We developed a lightweight and computationally efficient tool for next-day wildfire spread prediction using multimodal satellite data as input. The deep learning model, which we call Transform Domain Fusion UNet (TD-FusionUNet), incorporates trainable Hadamard Transform and Discrete Cosine Transform layers that apply two-dimensional transforms, enabling the network to capture essential "frequency" components in orthogonalized latent spaces. Additionally, we introduce custom preprocessing techniques, including random margin cropping and a Gaussian mixture model, to enrich the representation of the sparse pre-fire masks and enhance the model's generalization capability. The TD-FusionUNet is evaluated on two datasets which are the Next-Day Wildfire Spread dataset released by Google Research in 2023, and WildfireSpreadTS dataset. Our proposed TD-FusionUNet achieves an F1 score of 0.591 with 370k parameters, outperforming the UNet baseline using ResNet18 as the encoder reported in the WildfireSpreadTS dataset while using substantially fewer parameters. These results show that the proposed latent space fusion model balances accuracy and efficiency under a lightweight setting, making it suitable for real time wildfire prediction applications in resource limited environments.

Figures (3)

• Figure 1: HT-Unet structure
• Figure 2: TD-FusionUNet structure
• Figure 3: Examples of inference results, where false positives (FP) are highlighted in yellow and false negatives (FN) are highlighted in blue.