• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) µö·¯´× ±â¹Ý ħ¼ö ¼öÀ§ ¿¹Ãø:¹Ì±¹ Åػ罺 Æ®¸®´ÏƼ°­ »ç·Ê¿¬±¸
¿µ¹®Á¦¸ñ(English Title) Water Level Forecasting based on Deep Learning : A Use Case of Trinity River-Texas-The United States
ÀúÀÚ(Author) Æ®¶õ±¤Ä«ÀÌ   ¼Û»ç±¤   Quang-Khai Tran   Sa-kwang Song  
¿ø¹®¼ö·Ïó(Citation) VOL 44 NO. 06 PP. 0607 ~ 0612 (2017. 06)
Çѱ۳»¿ë
(Korean Abstract)
µµ½Ã¿¡¼­ È«¼ö ÇÇÇظ¦ ¹æÁöÇϱâ À§ÇÑ Ä§¼ö¸¦ ¿¹ÃøÇϱâ À§ÇØ º» ³í¹®¿¡¼­´Â µö·¯´×(Deep Learning)±â¹ýÀ» Àû¿ëÇÑ´Ù. µö·¯´× ±â¹ý Áß ½Ã°è¿­ µ¥ÀÌÅÍ ºÐ¼®¿¡ ÀûÇÕÇÑ Recurrent Neural Networks (RNNs)À» È°¿ëÇÏ¿© °­ÀÇ ¼öÀ§ °üÃø µ¥ÀÌÅ͸¦ ÇнÀÇÏ°í ħ¼ö °¡´É¼ºÀ» ¿¹ÃøÇÏ¿´´Ù. ¿¹Ãø Á¤È®µµ °ËÁõÀ» À§ÇØ »ç¿ëÇÑ µ¥ÀÌÅÍ´Â ¹Ì±¹ÀÇ Æ®¸®´ÏƼ°­ÀÇ µ¥ÀÌÅÍ·Î, ÇнÀÀ» À§ÇØ 2013 ³âºÎÅÍ 2015 ³â±îÁö µ¥ÀÌÅ͸¦ »ç¿ëÇÏ¿´°í Æò°¡ µ¥ÀÌÅͷδ 2016 ³â µ¥ÀÌÅ͸¦ »ç¿ëÇÏ¿´´Ù. ÀÔ·ÂÀº 16°³ÀÇ ·¹ÄÚµå·Î ±¸¼ºµÈ 15ºÐ´ÜÀ§ÀÇ ½Ã°è¿­ µ¥ÀÌÅ͸¦ »ç¿ëÇÏ¿´°í, Ãâ·ÂÀ¸·Î´Â 30ºÐ°ú 60ºÐ ÈÄÀÇ °­ÀÇ ¼öÀ§ ¿¹Ãø Á¤º¸ÀÌ´Ù. ½ÇÇè¿¡ »ç¿ëÇÑ µö·¯´× ¸ðµ¨µéÀº Ç¥ÁØ RNN, RNN-BPTT(Back Propagation Through Time), LSTM(Long Short-Term Memory)À» »ç¿ëÇߴµ¥, ±× Áß LSTMÀÇ NE(Nash Efficiency)°¡ 0.98À» ³Ñ´Â Á¤È®µµ·Î ±âÁ¸ ¿¬±¸¿¡ ºñÇØ ¸Å¿ì ³ôÀº ¼º´É Çâ»óÀ» º¸¿´°í, Ç¥ÁØ RNN°ú RNN-BPTT¿¡ ºñÇؼ­µµ ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the model, we use water observation data of a station in the Trinity river, Texas, the U.S., with data from 2013 to 2015 for training and data in 2016 for testing. Input of the neural networks is a 16-record-length sequence of 15-minute-interval time-series data, and output is the predicted value of the water level at the next 30 minutes and 60 minutes. In the experiment, we compare three Deep Learning models including standard RNN, RNN trained with Back Propagation Through Time (RNN-BPTT), and Long Short-Term Memory (LSTM). The prediction quality of LSTM can obtain Nash Efficiency exceeding 0.98, while the standard RNN and RNN-BPTT also provide very high accuracy.
Å°¿öµå(Keyword) ħ¼ö ¿¹Ãø   µö·¯´×   RNN   BPTT   LSTM   water level forecasting   deep learning   recurrent neural networks   back propagation through time   long short-term memory  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå