About this Research Topic
Forest plantations play a vital role in timber production, environmental protection, and landscape construction. Potential impacts of plantations on the environment and biodiversity can be mitigated through appropriate planning and management measures. Technological innovations such as forest breeding, genetic modification, and management systems have driven the continuous improvement of man-made forest ecosystems. Phenotype refers to the external expression of interactions between a plant’s genotype and the environment. The phenotypes of trees are one of the basic research areas of forest genetics and breeding, plantation culture, and forest ecology. Such research provides important data and techniques for tree breeding and precision forestry.
Although conventional forest phenotype evaluation methods have high accuracy, detailed assessment is time-consuming and costly. In addition, achieving real-time and rapid measurement of instantaneously changing physiological phenotypes is challenging. Therefore, high-throughput, high-precision, non-destructive forest phenotype determination and analysis are necessary. With the development of sensor technology and high-performance computing technology, studies of forest phenotypes have made significant progress. The application of machine learning algorithms and various imaging sensors, such as visible RGB images, fluorescence imaging, near-infrared spectroscopy, multi-spectral imaging, hyperspectral imaging, thermal infrared imaging, and LiDAR, have provided new opportunities and challenges in obtaining phenotypic information of tree growth, morphology, individual organs, physiology, and biochemistry.
This Research Topic aims to understand the existing sensor and computing technologies applied in forest phenotyping and identify any future perspectives. We welcome original papers and review articles broadly contributing to forest phenotyping. Specific topics of interest include but are not limited to:
- High-throughput and accurate tree phenotypic traits prediction and classification in planted forest
- Applications of multi-source optical imagery to forest tree breeding, cultivation, and management.
- Methods in object detection, trait extraction, and data mining in tree phenomics.
- Use of advanced machine learning/ deep learning algorithms in forest tree phenomics
Although conventional forest phenotype evaluation methods have high accuracy, detailed assessment is time-consuming and costly. In addition, achieving real-time and rapid measurement of instantaneously changing physiological phenotypes is challenging. Therefore, high-throughput, high-precision, non-destructive forest phenotype determination and analysis are necessary. With the development of sensor technology and high-performance computing technology, studies of forest phenotypes have made significant progress. The application of machine learning algorithms and various imaging sensors, such as visible RGB images, fluorescence imaging, near-infrared spectroscopy, multi-spectral imaging, hyperspectral imaging, thermal infrared imaging, and LiDAR, have provided new opportunities and challenges in obtaining phenotypic information of tree growth, morphology, individual organs, physiology, and biochemistry.
This Research Topic aims to understand the existing sensor and computing technologies applied in forest phenotyping and identify any future perspectives. We welcome original papers and review articles broadly contributing to forest phenotyping. Specific topics of interest include but are not limited to:
- High-throughput and accurate tree phenotypic traits prediction and classification in planted forest
- Applications of multi-source optical imagery to forest tree breeding, cultivation, and management.
- Methods in object detection, trait extraction, and data mining in tree phenomics.
- Use of advanced machine learning/ deep learning algorithms in forest tree phenomics
Keywords: Phenomics, Multiple Optical Imaging, Machine Learning, High-throughput, Forest Growth
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
