• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1159-1172
• /
• 2020

This study applied deep convolution neural network based on U-Net and SegNet using long period weather radar data to very short-term rainfall prediction. And the results were compared and evaluated with the translation model. For training and validation of deep neural network, Mt. Gwanak and Mt. Gwangdeoksan radar data were collected from 2010 to 2016 and converted to a gray-scale image file in an HDF5 format with a 1km spatial resolution. The deep neural network model was trained to predict precipitation after 10 minutes by using the four consecutive radar image data, and the recursive method of repeating forecasts was applied to carry out lead time 60 minutes with the pretrained deep neural network model. To evaluate the performance of deep neural network prediction model, 24 rain cases in 2017 were forecast for rainfall up to 60 minutes in advance. As a result of evaluating the predicted performance by calculating the mean absolute error (MAE) and critical success index (CSI) at the threshold of 0.1, 1, and 5 mm/hr, the deep neural network model showed better performance in the case of rainfall threshold of 0.1, 1 mm/hr in terms of MAE, and showed better performance than the translation model for lead time 50 minutes in terms of CSI. In particular, although the deep neural network prediction model performed generally better than the translation model for weak rainfall of 5 mm/hr or less, the deep neural network prediction model had limitations in predicting distinct precipitation characteristics of high intensity as a result of the evaluation of threshold of 5 mm/hr. The longer lead time, the spatial smoothness increase with lead time thereby reducing the accuracy of rainfall prediction The translation model turned out to be superior in predicting the exceedance of higher intensity thresholds (> 5 mm/hr) because it preserves distinct precipitation characteristics, but the rainfall position tends to shift incorrectly. This study are expected to be helpful for the improvement of radar rainfall prediction model using deep neural networks in the future. In addition, the massive weather radar data established in this study will be provided through open repositories for future use in subsequent studies.

• The Korean Journal of Air & Space Law and Policy
• /
• v.29 no.2
• /
• pp.205-237
• /
• 2014

Last 50 years there were a lot of space subjects launched by space activities of many states and these activities also had created tremendous, significant space debris contaminating the environment of outer space. The large number of space debris which are surrounding the earth have the serious possibilities of destroying a satellite or causing huge threat to the space vehicles. For example, Chinese anti-satellite missile test was conducted by China on January 11, 2007. As a consequence a Chinese weather satellite was destroyed by a kinetic kill vehicle traveling with a speed of 8 km/s in the opposite direction. Anti-satellite missile tests like this,contribute to the formation of enormous orbital space debris which can remain in orbit for many years and could interfere with future space activity (Kessler Syndrome). The test is the largest recorded creation of space debris in history with at least 2,317 pieces of trackable size (golf ball size and larger) and an estimated 150,000 debris particles and more. Several nations responded negatively to the test and highlighted the serious consequences of engaging in the militarization of space. The timing and occasion aroused the suspicion of its demonstration of anti-satellite (ASAT) capabilities following the Chinese test of an ASAT system in 2007 destroying a satellite but creating significant space debris. Therefore this breakup seemed to serve as a momentum of the UN Space Debris Mitigation Guidelines and the background of the EU initiatives for the International Code of Conduct for Outer Space Activities. The UN Space Debris Mitigation Guidelines thus adopted contain many technical elements that all the States involved in the outer space activities are expected to observe to produce least space debris from the moment of design of their launchers and satellites until the end of satellite life. Although the norms are on the voluntary basis which is normal in the current international space law environment where any attempt to formulate binding international rules has to face opposition and sometimes unnecessary screening from many corners of numerous countries. Nevertheless, because of common concerns of space-faring countries, the Guidelines could be adopted smoothly and are believed faithfully followed by most countries. It is a rare success story of international cooperation in the area of outer space. The EU has proposed an International Code of Conduct for Outer Space Activities as a transparency and confidence-building measure. It is designed to enhance the safety, security and sustainability of activities in outer space. The purpose of the Code to reduce the space debris, to allow exchange of the information on the space activities, and to protect the space objects through safety and security. Of the space issues, the space debris reduction and the space traffic management require some urgent attention. But the current legal instruments of the outer space do not have any binding rules to be applied thereto despite the incresing activities on the outer space. We need to start somewhere sometime soon before it's too late with the chaotic situation. In this article, with a view point of this problem, focused on the the Chinese test of an ASAT system in 2007 destroying a satellite but creating significant space debris and tried to analyse the issues of space debris reduction.