FLNet: Flood-Induced Agriculture Damage Assessment using Super Resolution of Satellite Images

TL;DR

This paper presents FLNet, a deep learning architecture that enhances satellite image resolution via super-resolution to improve flood damage assessment of crops, enabling faster and more accurate post-disaster evaluations.

Contribution

Introduces FLNet, a novel super-resolution based deep learning model that significantly improves damage classification accuracy using satellite imagery.

Findings

F1-score for 'Full Damage' increased from 0.83 to 0.89

Super-resolution improved damage detection accuracy

Cost-effective, scalable damage assessment method

Abstract

Distributing government relief efforts after a flood is challenging. In India, the crops are widely affected by floods; therefore, making rapid and accurate crop damage assessment is crucial for effective post-disaster agricultural management. Traditional manual surveys are slow and biased, while current satellite-based methods face challenges like cloud cover and low spatial resolution. Therefore, to bridge this gap, this paper introduced FLNet, a novel deep learning based architecture that used super-resolution to enhance the 10 m spatial resolution of Sentinel-2 satellite images into 3 m resolution before classifying damage. We tested our model on the Bihar Flood Impacted Croplands Dataset (BFCD-22), and the results showed an improved critical "Full Damage" F1-score from 0.83 to 0.89, nearly matching the 0.89 score of commercial high-resolution imagery. This work presented a cost-effective and scalable solution, paving the way for a nationwide shift from manual to automated, high-fidelity damage assessment.