, "Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles," J. Appl. Remote Sens. 11(4), 042621 (2017), doi: 10.1117/1.JRS.11.042621. Abstract. Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.
The goal of this study was to establish an efficient protocol for the large-scale propagation of Mertensia maritima (L.) Gray, and evaluate the carotenoid, fatty acid, and tocopherol contents in the leaves of in vitro regenerated shoots. Surface-disinfected node and shoot tip explants were placed on semisolid Murashige and Skoog (MS) medium with 0–16 µM N6-benzyladenine (BA), kinetin, (KN), and thidiazuron (TDZ) alone, or in combination with, 1 or 2 µM α-naphthaleneacetic acid (NAA). Of the three different cytokinins employed, TDZ elicited the best results for axillary shoot proliferation. A maximum frequency of shoot initiation above 84%, with a mean of 8.9 and 4.8 shoots per node and shoot tip, respectively, was achieved on the culture medium supplemented with 4 µM TDZ. A combination of TDZ + NAA significantly increased the percentage of multiple shoot formation and number of shoots per explant. The best shoot induction response occurred on MS medium with 4 µM TDZ and 1 µM NAA. On this medium, the node (93.8%) and shoot tip (95.9%) explants produced an average of 17.7 and 8.6 shoots, respectively. The highest root induction frequency (97.4%) and number of roots per shoot (25.4), as well as the greatest root length (4.2 cm), were obtained on half-strength MS medium supplemented with 4 µM indole-3-butyric acid (IBA). The presence of six carotenoids and α-tocopherol in the leaf tissues of M. maritima was confirmed by HPLC. Gas chromatography-mass spectrometry analysis confirmed the presence of 10 fatty acids, including γ-linolenic acid and stearidonic acid in the leaf tissues of M. maritima. All-E-lutein (18.49 μg g−1 fresh weight, FW), α-tocopherol (3.82 μg g−1 FW) and α-linolenic acid (30.37%) were found to be the significant compounds in M. maritima. For the first time, a successful protocol has been established for the mass propagation of M. maritima with promising prospects for harnessing its bioactive reserves.
The genus Ajuga L., belonging to Lamiaceae family, is widespread. The demand for Ajuga species has risen sharply because of their medicinal, ornamental, and pharmacological properties. These wide-ranging plants are being rapidly depleted due to over-collection for ornamental and medicinal purposes, as well as by habitat destruction and deforestation. Ajuga boninsimae, A. bracteosa, A. ciliate, A. genevensis, A. incisa, A. makinoi, A. multiflora, A. pyramidalis, A. shikotanensis, A. reptans, and A. vestita are categorized and protected as endangered plants. In vitro plant culture has therefore emerged for the conservation and mass clonal propagation of rare plants. This mini-review covers the current in vitro scenario in the propagation of Ajuga species. Adventitious or axillary shoots are initiated on the leaf, petiole and internodes, as well as roots, nodes, and shoot tip explants. Shoot induction is predominantly dependent on plant growth regulators added to the culture medium. Full- or half-strength Murashige and Skoog medium with or without auxin is used for in vitro rooting. Rooted shoots need to be acclimatized in the greenhouse with an estimated 82-100% survival rate.
The influence of 2,4-dichlorophenoxyacetic acid (2,4-D), benzyladenine (BA), and thidiazuron (TDZ) on direct rhizome induction and shoot formation from rhizome explants of was explored. Rhizome segments obtained from in vitro seed cultures of were placed on Murashige and Skoog (MS) medium incorporated with 5, 10, 20, or 40 µM 2,4-D and 1, 2, 4, or 8 µM BA or TDZ alone or in combination with 20 µM 2,4-D. The explants developed only rhizomes on MS medium with or without 2,4-D. The highest percent of rhizome formation (100%) was obtained on MS medium incorporated with 20 μM of 2,4-D. The morphology and number of rhizomes varied with the level of 2,4-D in the medium. Direct adventitious shoot formation was achieved on medium incorporated with BA or TDZ. The adventitious shoots produced per explant significantly increased with the supplementation of 2,4-D to cytokinin-containing medium. The highest mean of 21.8 ± 1.8 shoot buds per rhizome segment was obtained in medium fortified with 20 μM 2,4-D and 2 μM TDZ. The greatest percent of root induction (100%) and the mean of 5.3 ± 1.1 roots per shoot were achieved on ½ MS medium incorporated with 2 μM of α-naphthaleneacetic acid. About 97% of the in vitro-produced plantlets acclimatized in the greenhouse. An efficient in vitro propagation protocol was thus developed for using rhizome explants.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.