- Apply for Authority
- P-ISSN2765-2203
- E-ISSN2765-2211
- KCI Candidate
Abstract
The analysis of seven islands in Gogunsan archipelago, Korea with insect fauna and vascular plant flora was carried out based on a field survey conducted in May, July, and September. As a result, a total of 2,817 insect individuals including 264 species and 315 taxa of vascular plant were recorded. Bangchukdo the largest island among the seven islands showed the largest number both insect species and plant taxa. The similarity analysis suggested that the nearness of each island strongly affected the insect fauna and vascular plant flora on each island. In addition, there was significant correlation between the areas of each island and the numbers of insect species (Spearman’s correlation coefficient=0.857, P-value=0.014). In the future, the results of this study can be used as data related to island ecology and conservation.
Abstract
Farming practices that balance environmental friendliness with biodiversity are increasingly valuable. Wild plants on farmlands compete for nutrients with crops and create a crucial microhabitat and resources for animals such as natural enemies. Investigating farmlands and their surrounding plants with limited human and material resources has become an essential aspect of evaluating the agricultural ecosystem services. This study investigated plants in six agricultural long-term ecological research sites in Taiwan from 2017 to 2020 to determine the ideal season for investigation. Cluster analysis was performed to group habitats with similar plant composition, and the species–area curves of the clusters in each season were created. The results indicated that the agricultural ecosystem could be divided into farmlands, banks, orchards, and tea gardens. The habitats were divided into farmland, bank, Chia-Yi orchard, Gu-Keng orchard, and tea garden clusters. Ground plant cover can be investigated all year with at least 18 quadrats. However, if human and material resources are limited, 10 quadrats should be the minimum for farmlands in autumn and for the other microhabitats in spring. The minimum number of quadrats is 10 for banks, 17 for orchards, and 9 for tea gardens.
Abstract
Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep- learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.