Authorship：Lead author   Language：Japanese   Publishing type：Research paper (bulletin of university, research institution)  

DOI： 10.19019/jiyu.8.1_17

Language：Japanese   Publishing type：Research paper (scientific journal)  

Language：English   Publishing type：Research paper (scientific journal)   Publisher：MDPI AG  

Identifying tree species from the air has long been desired for forest management. Recently, combination of UAV RGB image and deep learning has shown high performance for tree identification in limited conditions. In this study, we evaluated the practicality and robustness of the tree identification system using UAVs and deep learning. We sampled training and test data from three sites in temperate forests in Japan. The objective tree species ranged across 56 species, including dead trees and gaps. When we evaluated the model performance on the dataset obtained from the same time and same tree crowns as the training dataset, it yielded a Kappa score of 0.97, and 0.72, respectively, for the performance on the dataset obtained from the same time but with different tree crowns. When we evaluated the dataset obtained from different times and sites from the training dataset, which is the same condition as the practical one, the Kappa scores decreased to 0.47. Though coniferous trees and representative species of stands showed a certain stable performance regarding identification, some misclassifications occurred between: (1) trees that belong to phylogenetically close species, (2) tree species with similar leaf shapes, and (3) tree species that prefer the same environment. Furthermore, tree types such as coniferous and broadleaved or evergreen and deciduous do not always guarantee common features between the different trees belonging to the tree type. Our findings promote the practicalization of identification systems using UAV RGB images and deep learning.

DOI： 10.3390/rs14071710

Web of Science

Authorship：Lead author,　Corresponding author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：PeerJ  

In plants, negative reproductive interaction among closely related species (<italic>i.e.</italic>, reproductive interference) is known to hamper the coexistence of congeneric species while facilitation can increase species persistence. Since reproductive interference in plants may occur through interspecific pollination, the effective range of reproductive interference may reflects the spatial range of interspecific pollination. Therefore, we hypothesized that the coexistence of congeners on a small spatial scale would be less likely to occur by chance but that such coexistence would be likely to occur on a scale larger than interspecific pollination frequently occur. In the present study, we tested this hypothesis using spatially explicit woody plant survey data. Contrary to our prediction, congeneric tree species often coexisted at the finest spatial scale and significant exclusive distribution was not detected. Our results suggest that cooccurrence of congeneric tree species is not structured by reproductive interference, and they indicate the need for further research to explore the factors that mitigate the effects of reproductive interference.

DOI： 10.7717/peerj.12150

Other Link： https://peerj.com/articles/12150.xml

Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media LLC  

<title>Abstract</title><sec>
<title>Background</title>
Classifying and mapping vegetation are crucial tasks in environmental science and natural resource management. However, these tasks are difficult because conventional methods such as field surveys are highly labor-intensive. Identification of target objects from visual data using computer techniques is one of the most promising techniques to reduce the costs and labor for vegetation mapping. Although deep learning and convolutional neural networks (CNNs) have become a new solution for image recognition and classification recently, in general, detection of ambiguous objects such as vegetation is still difficult. In this study, we investigated the effectiveness of adopting the chopped picture method, a recently described protocol for CNNs, and evaluated the efficiency of CNN for plant community detection from Google Earth images.


</sec><sec>
<title>Results</title>
We selected bamboo forests as the target and obtained Google Earth images from three regions in Japan. By applying CNN, the best trained model correctly detected over 90% of the targets. Our results showed that the identification accuracy of CNN is higher than that of conventional machine learning methods.


</sec><sec>
<title>Conclusions</title>
Our results demonstrated that CNN and the chopped picture method are potentially powerful tools for high-accuracy automated detection and mapping of vegetation.


</sec>

DOI： 10.1186/s12898-020-00331-5

Other Link： http://link.springer.com/article/10.1186/s12898-020-00331-5/fulltext.html

Total pages：339p, 図版ivp   Language：Japanese

CiNii Books

Language：English Book type：Scholarly book

DOI： https://doi.org/10.1016/bs.aecr.2020.01.004

Authorship：Lead author,　Corresponding author   Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

J-GLOBAL