PMID- 31830651
OWN - NLM
STAT- MEDLINE
DCOM- 20200116
LR  - 20200116
IS  - 1879-2448 (Electronic)
IS  - 0043-1354 (Linking)
VI  - 170
DP  - 2020 Mar 1
TI  - Soft detection of 5-day BOD with sparse matrix in city harbor water using deep 
      learning techniques.
PG  - 115350
LID - S0043-1354(19)31124-8 [pii]
LID - 10.1016/j.watres.2019.115350 [doi]
AB  - To better control and manage harbor water quality is an important mission for 
      coastal cities such as New York City (NYC). To achieve this, managers and 
      governors need keep track of key quality indicators, such as temperature, pH, and 
      dissolved oxygen. Among these, the Biochemical Oxygen Demand (BOD) over five days 
      is a critical indicator that requires much time and effort to detect, causing 
      great inconvenience in both academia and industry. Existing experimental and 
      statistical methods cannot effectively solve the detection time problem or 
      provide limited accuracy. Also, due to various human-made mistakes or facility 
      issues, the data used for BOD detection and prediction contain many missing 
      values, resulting in a sparse matrix. Few studies have addressed the sparse 
      matrix problem while developing statistical detection methods. To address these 
      gaps, we propose a deep learning based model that combines Deep Matrix 
      Factorization (DMF) and Deep Neural Network (DNN). The model was able to solve 
      the sparse matrix problem more intelligently and predict the BOD value more 
      accurately. To test its effectiveness, we conducted a case study on the NYC 
      harbor water, based on 32,323 water samples. The results showed that the proposed 
      method achieved 11.54%-17.23% lower RMSE than conventional matrix completion 
      methods, and 19.20%-25.16% lower RMSE than traditional machine learning 
      algorithms.
CI  - Copyright (c) 2019 Elsevier Ltd. All rights reserved.
FAU - Ma, Jun
AU  - Ma J
AD  - Department of Civil and Environmental Engineering, the Hong Kong University of 
      Science and Technology, Hong Kong.
FAU - Ding, Yuexiong
AU  - Ding Y
AD  - Department of Research and Development, Big Bay Innovation Research and 
      Development Limited, Hong Kong.
FAU - Cheng, Jack C P
AU  - Cheng JCP
AD  - Department of Civil and Environmental Engineering, the Hong Kong University of 
      Science and Technology, Hong Kong.
FAU - Jiang, Feifeng
AU  - Jiang F
AD  - Department of Architecture and Civil Engineering, City University of Hong Kong, 
      Hong Kong.
FAU - Xu, Zherui
AU  - Xu Z
AD  - Shenzhen Yunzhe Technology Co. Ltd., Shenzhen, China. Electronic address: 
      xuzherui0527@outlook.com.
LA  - eng
PT  - Journal Article
DEP - 20191204
PL  - England
TA  - Water Res
JT  - Water research
JID - 0105072
RN  - 059QF0KO0R (Water)
SB  - IM
MH  - Cities
MH  - *Deep Learning
MH  - Humans
MH  - Machine Learning
MH  - New York City
MH  - *Water
OTO - NOTNLM
OT  - Biochemical oxygen demand
OT  - Deep matrix factorization
OT  - Deep neural network
OT  - Harbor water
OT  - Sparse matrix
EDAT- 2019/12/13 06:00
MHDA- 2020/01/17 06:00
CRDT- 2019/12/13 06:00
PHST- 2019/08/01 00:00 [received]
PHST- 2019/11/23 00:00 [revised]
PHST- 2019/11/27 00:00 [accepted]
PHST- 2019/12/13 06:00 [pubmed]
PHST- 2020/01/17 06:00 [medline]
PHST- 2019/12/13 06:00 [entrez]
AID - S0043-1354(19)31124-8 [pii]
AID - 10.1016/j.watres.2019.115350 [doi]
PST - ppublish
SO  - Water Res. 2020 Mar 1;170:115350. doi: 10.1016/j.watres.2019.115350. Epub 2019 
      Dec 4.