Pine wood nematode disease area identification based on multi-temporal multi-source remote sensing images and BIT model

Abstract

Pine wood nematode (PWN) disease is a severe contagious disease in forests which endangers the health of forests, as it can rapidly kill trees. The detection of regions impacted by this disease plays a crucial role in forest management, remediation efforts and ensuring the overall ecological security of forests. With the advancements in remote sensing technology, remote sensing images offer distinct advantages such as extensive coverage, timely data acquisition and high spatial resolution, making them highly suitable for accurately and efficiently identifying PWN disease areas. This article introduces a deep learning approach for the identification of PWN disease areas using multi-temporal and multi-source remote sensing images. Specifically, a specialized model called the bitemporal image transformer (BIT) model is developed and trained using multi-temporal Beijing-2 and Beijing-3 images acquired at different stages of PWN disease. BIT is a twin network for semantic segmentation with transformer structure and its backbone utilizes the Resnet structure. The input bitemporal image can be represented by several semantic tokens and encoded using a transformer encoder. The contextual information learned from the tokens is subsequently applied back to the pixel space. Finally, transformer decoder is utilized to refine the original features. To evaluate the model’s generalization ability, the best-trained model for different regions affected by pine nematode disease is identified using a transfer learning mechanism. The experimental results demonstrate a significant enhancement in classification accuracy using the proposed method, with a noteworthy 15.23% improvement in F1-score, 9.34% in accuracy, 11.7% in precision, 12.88% in recall, compared to traditional methods. Moreover, the model exhibits impressive generalization ability across various forest regions. In summary, this research introduces a promising approach that utilizes remote sensing images and deep learning techniques as a powerful tool for precisely identifying and managing areas affected by PWN disease.