• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.66 no.2
• /
• pp.105-111
• /
• 2021

Rice lodging is an annual occurrence caused by typhoons accompanied by strong winds and strong rainfall, resulting in damage relating to pre-harvest sprouting during the ripening period. Thus, rapid estimations of the area of lodged rice are necessary to enable timely responses to damage. To this end, we obtained images related to rice lodging using a drone in Gimje, Buan, and Gunsan, which were converted to 128 × 128 pixels images. A convolutional neural network (CNN) model, a deep learning model based on these images, was used to predict rice lodging, which was classified into two types (lodging and non-lodging), and the images were divided in a 8:2 ratio into a training set and a validation set. The CNN model was layered and trained using three optimizers (Adam, Rmsprop, and SGD). The area of rice lodging was evaluated for the three fields using the obtained data, with the exception of the training set and validation set. The images were combined to give composites images of the entire fields using Metashape, and these images were divided into 128 × 128 pixels. Lodging in the divided images was predicted using the trained CNN model, and the extent of lodging was calculated by multiplying the ratio of the total number of field images by the number of lodging images by the area of the entire field. The results for the training and validation sets showed that accuracy increased with a progression in learning and eventually reached a level greater than 0.919. The results obtained for each of the three fields showed high accuracy with respect to all optimizers, among which, Adam showed the highest accuracy (normalized root mean square error: 2.73%). On the basis of the findings of this study, it is anticipated that the area of lodged rice can be rapidly predicted using deep learning.

• Journal of the Korean Geographical Society
• /
• v.31 no.3
• /
• pp.447-468
• /
• 1996

The peat layer was deposited on the abandoned channel of incised meander of River Banbyuncheon with 7 meter thickness on Youngyang basin. The late Quaternary environmental change on the study area was discussed based on pollen anaalysis and radiocarbon-dating from this peat. The swamp which was caused to sediment the peat, was produced by which the fan debris from the adjacent slope damed the waterflow on the abandoned channel. The peat layer contains continuous vegetational history from 60,000y.B.P. to Recent. The peat deposit was divided into two layers by the organic thin sand horizon, which was sedimented at one time and made unconformity between the lower decomposed compact peat layers and the upper fresh fiberous peat layer. As the result of the pollen analysis, both peat layers from the two boring sites, Profile YY1 and Profile YY2 were divided into five Pollenzones(Pollenzone I, II, III, IV and V) and 12 Subzones which were mainly corresponded by the AP (Arboreal Pollen)-Dominance. The two profiles have some differences on the sedimentary facies and on the pollen composition as well. Therefore these were in common with the Pollenone III, however the Pollenzone I and II existed only on the Profile YY1 and the Pollenzone IV and V existed only on the Profile YY2. The lower layer containing the Pollenzone I, II and III revealed vegetational records of Pleistocene, which was characterized as tundra-like landscape and thin forested landscapes. It represented the NAP (Non-Arboreal Pollen)-period with a plenty of Artemisia sp., Sanguisorba sp., Umbelliferae, Gramineae and Cyperaceae. However a relatively high proportion of the boreal trees with Picea sp., Pinus sp. and Betula sp. as AP was observed in the lower layer. The upper layer contained the Pollenzone IVb and V and vegetational history in Holocene which was characterized by thick forested landscape with rich tree pollen. It represented AP-period with plenty of Pinus sp. and Quercus sp. as temperate trees. The temperature fluctuation supposed from the vegetational records is as follows; the Pollenzone I(Betula-Dominance, about 57,000y.B.P.) represents relatively cold period. The Pollenzone II(EMW-Domi-nance, 57,000-43,000y.B.P.)represents relatively warm period. This period is supposed to be Interstadial, the transi-tional stage from Alt- to Mittel Wurm. The Pollenzone III(Butula-, Pinus- and Picea-Dominace in turns, 43,000-15,000y.B.P.) reproesents cold period which had been built from Mittel-to Jung Wurm. Especially the Subzone IIId represents the coldest period throughout the Pollenzone III. It is corresponds to Wurm Glacial Maximu. It is supposed that the mean temperature in July of this period was coller about 10${^\circ}$C than present. The Pollenzone IV and V represent the vegetational history of Holocene. Tilia, Quercus and Pinus were dominant in turns during this period. Subzone IVb and Pollenzone I and II at east coastal plain of Korean penninsula reported by JO(1979).