본문 바로가기

Long short-term memory models of water quality in inland water environments

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
Water Research X21 · 2023
피인용
Web of Science 85Scopus 101
FWCI (Scopus)
2.09
JCR IF
JCR 2022 7.5
ISSN
2589-9147

저자

  1. 표종철제1저자Pusan Natl Univ, Dept Environm Engn, Busan 46241, South Korea
  2. Pachepsky, YakovUSDA ARS, Environm Microbial & Food Safety Lab, Beltsville, MD USA
  3. Kim, SoobinUlsan Natl Inst Sci & Technol, Sch Civil Urban Earth & Environm Engn, 50 UNIST Gil, Ulsan 44919, South Korea
  4. Abbas, AtherKing Abdullah Univ Sci & Technol, Phys Sci & Engn, Thuwal 239556900, Saudi Arabia
  5. Kim, MinjeongKorea Atom Energy Res Inst KAERI, Disposal Safety Evaluat R&D Div, 111,Daedeok Daero 989 Beon Gil, Daejeon 34057, South Korea
  6. Kwon, Yong SungNatl Inst Ecol, Div Ecol Assessment Res, Environm Impact Assessment Team, Seocheon 33657, South Korea
  7. Ligaray, MayzoneeUniv Philippines Diliman, Inst Environm Sci & Meteorol, Coll Sci, Quezon City 1101, Philippines
  8. Cho, Kyung Hwa교신저자Korea Univ, Sch Civil Environm & Architectural Engn, Seoul 02841, South Korea

초록

Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and relationships from variables. Long short-term memory (LSTM), one of deep learning models for water quality prediction, is a type of recurrent neural network that can account for longer-term traits of time-dependent data. It is the most widely applied network used to predict the time series of water quality variables. First, we reviewed applications of a standalone LSTM and discussed its calculation time, prediction accuracy, and good robustness with process-driven numerical models and the other machine learning. This review was expanded into the LSTM model with data pre-processing techniques, including the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method and Synchrosqueezed Wavelet Transform. The review then focused on the coupling of LSTM with a convolutional neural network, attention network, and transfer learning. The coupled networks demonstrated their performance over the standalone LSTM model. We also emphasized the influence of the static variables in the model and used the transformation method on the dataset. Outlook and further challenges were addressed. The outlook for research and application of LSTM in hydrology concludes the review.

키워드

Deep learning modelsEnsemble LSTMInland waterLong short-term memoryWater qualityNEURAL-NETWORKSLSTMUNCERTAINTYSENSITIVITYPERFORMANCE

식별자

Scopus EID
2-s2.0-85178205916
WoS UID
001125366400001