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

TL;DR

This paper introduces TD-FusionUNet, a lightweight deep learning model that uses Hadamard and DCT transforms in latent spaces to improve next-day wildfire spread prediction from satellite data, balancing accuracy and efficiency.

Contribution

The paper presents a novel fusion model incorporating trainable frequency transforms and custom preprocessing, achieving high accuracy with fewer parameters for wildfire prediction.

Findings

Achieved an F1 score of 0.591 on wildfire datasets.

Outperformed baseline UNet with ResNet18 encoder.

Maintained high accuracy with significantly fewer parameters.

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.