PMID- 33569684
OWN - NLM
STAT- Publisher
LR  - 20240222
IS  - 1614-7499 (Electronic)
IS  - 0944-1344 (Linking)
DP  - 2021 Feb 10
TI  - Presenting a soft sensor for monitoring and controlling well health and pump 
      performance using machine learning, statistical analysis, and Petri net modeling.
LID - 10.1007/s11356-021-12643-0 [doi]
AB  - Groundwater resources play a key role in supplying urban water demands in 
      numerous societies. In many parts of the world, wells provide a reliable and 
      sufficient source of water for domestic, irrigation, and industrial purposes. In 
      recent decades, artificial intelligence (AI) and machine learning (ML) methods 
      have attracted a considerable attention to develop Smart Control Systems for 
      water management facilities. In this study, an attempt has been made to create a 
      smart framework to monitor, control, and manage groundwater wells and pumps using 
      a combination of ML algorithms and statistical analysis. In this research, 8 
      different learning methods and regressions namely support vector regression 
      (SVR), extreme learning machine (ELM), classification and regression tree (CART), 
      random forest (RF), artificial neural networks (ANNs), generalized regression 
      neural network (GRNN), linear regression (LR), and K-nearest neighbors (KNN) 
      regression algorithms have been applied to create a forecast model to predict 
      water flow rate in Mashhad City wells. Moreover, several descriptive statistical 
      metrics including mean squared error (MSE), root mean square error (RMSE), mean 
      absolute error (MAE), and cross predicted accuracy (CPA) are calculated for these 
      models to evaluate their performance. According to the results of this 
      investigation, CART, RF, and LR algorithms have indicated the highest levels of 
      precision with the lowest error values while SVM and MLP are the worst 
      algorithms. In addition, sensitivity analysis has demonstrated that the LR and RF 
      algorithms have produced the most accurate models for deep and shallow wells 
       respectively. Finally, a Petri net model has been presented to illustrate the 
      conceptual model of the smart framework and alarm management system.
FAU - Amini, Mohammad Hossein
AU  - Amini MH
AD  - Big Data Lab, Imam Reza International University, Mashhad, Iran.
AD  - Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.
FAU - Arab, Maliheh
AU  - Arab M
AD  - Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.
FAU - Faramarz, Mahdieh Ghiyasi
AU  - Faramarz MG
AD  - Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.
FAU - Ghazikhani, Adel
AU  - Ghazikhani A
AUID- ORCID: 0000-0003-2055-5209
AD  - Big Data Lab, Imam Reza International University, Mashhad, Iran. 
      a_ghazikhani@yahoo.com.
AD  - Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad, Iran. 
      a_ghazikhani@yahoo.com.
FAU - Gheibi, Mohammad
AU  - Gheibi M
AD  - Department of Civil Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.
AD  - Zistpardazesharia Knowledge based company , Mashhad, Iran.
LA  - eng
PT  - Journal Article
DEP - 20210210
PL  - Germany
TA  - Environ Sci Pollut Res Int
JT  - Environmental science and pollution research international
JID - 9441769
SB  - IM
OTO - NOTNLM
OT  - Groundwater resource
OT  - Machine learning (ML)
OT  - Petri net
OT  - Sensitivity analysis
OT  - Statistical analysis
EDAT- 2021/02/12 06:00
MHDA- 2021/02/12 06:00
CRDT- 2021/02/11 05:57
PHST- 2020/11/02 00:00 [received]
PHST- 2021/01/20 00:00 [accepted]
PHST- 2021/02/11 05:57 [entrez]
PHST- 2021/02/12 06:00 [pubmed]
PHST- 2021/02/12 06:00 [medline]
AID - 10.1007/s11356-021-12643-0 [pii]
AID - 10.1007/s11356-021-12643-0 [doi]
PST - aheadofprint
SO  - Environ Sci Pollut Res Int. 2021 Feb 10. doi: 10.1007/s11356-021-12643-0.