Status, advancements and prospects of deep learning methods applied in forest studies
Ting Yun, Jian Li, Lingfei Ma, Ji Zhou, Ruisheng Wang, Markus P. Eichhorn, Huaiqing Zhang
Abstract
• Deliver a taxonomy of deep learning (DL) methods for various forest applications. • Review and analyze the merits & restrictions of DL technique in forest researches. • Summarize main forest datasets and discuss global distribution of related literature. • Enumerate future directions and challenges of DL technology in forest development. Deep learning, which has exhibited considerable potential and effectiveness in forest resource assessment, is vital for comprehending and managing forest resources and ecosystems. However, extensive assessment of forest resources is highly challenging due to the complex and varied nature of forest types sourced from diverse remote sensing platforms, which include images, point clouds, and fusion data. To facilitate further study, we systematically review the current status, applications and prospects of deep learning technologies for different types of forest remote sensing data. After considering more than two hundred forest-related papers published over the past decade, we introduce sensors and devices for forest data acquisition, classify deep learning methods based on their data processing methods and operational principles, and categorize diverse instances of these methods with various forest applications. Moreover, we summarize available datasets related primarily to forest data and examine the global geographic distribution of the relevant literature. Comprehensive insights into the advantages and limitations of each method are described, offering a forward-looking perspective on the trend of applying deep learning technology to forest research. In this paper, we aim to provide an overview of the current trends and challenges of deep learning techniques applied to forest research, creating a comprehensive picture for use as a reference by both academia and industry professionals.