Yanjie Li
Cong Xu
Weiqi Yan- 1State Key Laboratory of Tree Genetics and Breeding, Research Institute of Subtropical Forestry, Chinese Academy of Forestry, Hangzhou, Zhejiang, China
- 2Key Laboratory of Tree Breeding of Zhejiang Province, Research Institute of Subtropical Forestry, Chinese Academy of Forestry, Hangzhou, Zhejiang, China
- 3School of Forestry, University of Canterbury, Christchurch, New Zealand
- 4School of Computer and Mathematical Sciences, Auckland University of Technology (AUT), Auckland, New Zealand
Editorial on the Research Topic
Forest phenomics: how does developing sensor technology improve the growth of forest plantations?
The burgeoning field of forest phenomics is on the verge of significant transformation, spurred by swift advancements in sensor technologies and machine learning algorithms. Sensor technology has substantially evolved, affecting both the agriculture and forestry sectors. Despite two decades of notable progress, numerous challenges and untapped opportunities persist in sensor-based plant phenomics (Tao et al., 2022). The emergence of high-throughput, high-precision, non-destructive methods signifies advancements in this field. These methods allow for real-time and swift measurement of dynamically changing physiological phenotypes.
Isabel et al. (2020) argue that forest phenomics is evolving to tackle complex issues such as ecological genetics and climate adaptation. The fusion of sensor technology with advanced computational models heralds promising prospects for next-generation forestry applications (Song et al., 2022). For instance, the employment of machine learning and deep learning algorithms has been pivotal in high-throughput and precise prediction and classification of tree phenotypic traits in planted forests. This, in turn, facilitates a better understanding and management of ecological genetics and climate adaptation challenges in forestry. Pappas et al. (2022) suggest that future applications may encompass integrating real-time environmental data for adaptive forest management, with a focus on forest health. The digitalization of forests facilitated by sensor technology is a step in this direction, offering real-time data, monitoring, and forest inventory crucial for adaptive management practices (Coops et al., 2023). A crucial bottleneck, highlighted by Harfouche et al. (2019), is the need for effective frameworks to translate the wealth of data into actionable insights. Given the nascent stage of industrial applications for these technologies, there is a need for more focused research and technology transfer strategies, a point emphasized by Guo et al. (2021). The diverse applications of remote sensing technology in forest ecology and management showcase the potential of these technologies to convert data into actionable insights, ranging from monitoring land-cover changes to estimating forests' biophysical and biochemical properties (Mohan et al., 2021).
Against this backdrop, the focal Research Topic, “Forest phenomics: how does developing sensor technology improve the growth of forest plantations?” serves as the foundation for this forthcoming transformation in forestry. It seamlessly integrates state-of-the-art sensor technologies with machine learning to decipher the complex dynamics of forest ecosystems. This editorial summarizes key findings from four cornerstone articles featured in this Research Topic. Collectively, they elucidate the significant influence of these technologies on sustainable forest management and plantation understanding.
Liu et al. used machine learning along with hyperspectral imagery for the non-invasive examination of tree symbiotic fungi. They revealed deep CNN architecture demonstrates high accuracy, hinting at the potential of non-destructive, real-time fungal interaction analyses that could substantially deepen our comprehension of both forest ecology and broader biodiversity. Long et al. focus on analyzing the nutrient content of Pinus elliottii × P. caribaea canopy needles. The integration of Visible-Near Infrared (Vis-NIR) hyperspectral imaging with ensemble learning methods overcomes the limitations of traditional chemical analysis techniques, which are often destructive. This advancement enables more accurate nutrient analysis that surpasses traditional methods. Such improved accuracy is essential for optimizing seedling cultivation, thereby improving both yield and quality. Wang et al. investigate chlorophyll content prediction in needles of Picea koraiensis Nakai, emphasizing the advantages of non-linear modeling over traditional linear approaches. This study not only reinforces the discourse on technological innovation in forest phenomics but also suggests that rapid, non-invasive characterization could become fundamental to sustainable forestry. Finally, Yang et al. extend the discussion to include the forest-based food industry. Their work emphasizing the potential utility of sensor technology in both quality assurance and genetic selection. The proposed model, which uses hyperspectral imaging to predict chestnut characteristics (i.e., soluble sugar content), serves as a pragmatic example. It provides a non-destructive assessment method that is essential for both the food industry and consumers.
This Research Topic marks the onset of a new era. The integration of sensor technology and machine learning amplifies our capacity for data-driven decision-making. This pivotal advancement is essential for sustainable and informed management of forest ecosystems. The tangible benefits underscored in the articles discussed herein exhibit both the immense potential and the impending transformation in the field of forestry. These advancements not only enrich our understanding of forest ecosystems, but also pave the way for innovative solutions to pressing global challenges such as climate change, biodiversity loss, and food security.
Author contributions
YL: Writing—original draft, Writing—review & editing. CX: Writing—review & editing. WY: Writing—review & editing.
Funding
The author(s) declare financial support was received for the research, authorship, and/or publication of this article. Financial support for this work was obtained from the cooperation projects between the People's Government of Zhejiang Province and the Chinese Academy of Forestry, No. 2023SY10 and the Zhejiang Science and Technology Major Program on Agricultural New Variety Breeding (2021C02070-7-3).
Acknowledgments
We greatly thank all authors and reviewers for their contributions to this Research Topic as well as the support of the editorial office.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. This had no impact on the peer review process and the final decision.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
Coops, N. C., Tompalski, P., Goodbody, T. R., Achim, A., and Mulverhill, C. (2023). Framework for near real-time forest inventory using multi source remote sensing data. Forestry 96, 1–19. doi: 10.1093/forestry/cpac015
Guo, W., Carroll, M. E., Singh, A., Swetnam, T. L., Merchant, N., Sarkar, S., et al. (2021). UAS-based plant phenotyping for research and breeding applications. Plant Phenom. 2021, 9840192. doi: 10.34133/2021/9840192
Harfouche, A. L., Jacobson, D. A., Kainer, D., Romero, J. C., Harfouche, A. H., Mugnozza, G. S., et al. (2019). Accelerating climate resilient plant breeding by applying next-generation artificial intelligence. Trends Biotechnol. 37, 1217–1235. doi: 10.1016/j.tibtech.2019.05.007
Isabel, N., Holliday, J. A., and Aitken, S. N. (2020). Forest genomics: advancing climate adaptation, forest health, productivity, and conservation. Evol. Appl. 13, 3–10. doi: 10.1111/eva.12902
Mohan, M., Richardson, G., Gopan, G., Aghai, M. M., Bajaj, S., Galgamuwa, G. P., et al. (2021). UAV-supported forest regeneration: current trends, challenges and implications. Remote Sens. 13, 2596. doi: 10.3390/rs13132596
Pappas, C., Bélanger, N., Bergeron, Y., Blarquez, O., Chen, H. Y. H., Comeau, P. G., et al. (2022). “Smartforests Canada: a network of monitoring plots for forest management under environmental change,” in Climate-Smart Forestry in Mountain Regions, eds R. Tognetti, M. Smith, and P. Panzacchi (Cham: Springer International Publishing), 521–543.
Song, Z., Tomasetto, F., Niu, X., Yan, W. Q., Jiang, J., and Li, Y. (2022). Enabling breeding selection for biomass in slash pine using UAV-based imaging. Plant Phenom. 2022, 9783785. doi: 10.34133/2022/9783785
Keywords: forest management, high-precision, high-throughput, forest phenomics, sensor-based plant phenomics
Citation: Li Y, Xu C and Yan W (2023) Editorial: Forest phenomics: how does developing sensor technology improve the growth of forest plantations? Front. For. Glob. Change 6:1327850. doi: 10.3389/ffgc.2023.1327850
Received: 25 October 2023; Accepted: 23 November 2023;
Published: 04 December 2023.
Edited and reviewed by: Lauren Bennett, The University of Melbourne, Australia
Copyright © 2023 Li, Xu and Yan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Cong Xu, Y29uZy54dSYjeDAwMDQwO2NhbnRlcmJ1cnkuYWMubno=