PMID- 37112620
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20230501
IS  - 2305-6304 (Electronic)
IS  - 2305-6304 (Linking)
VI  - 11
IP  - 4
DP  - 2023 Apr 21
TI  - Potential of Coupling Metaheuristics-Optimized-XGBoost and SHAP in Revealing PAHs 
      Environmental Fate.
LID - 10.3390/toxics11040394 [doi]
LID - 394
AB  - Polycyclic aromatic hydrocarbons (PAHs) refer to a group of several hundred 
      compounds, among which 16 are identified as priority pollutants, due to their 
      adverse health effects, frequency of occurrence, and potential for human 
      exposure. This study is focused on benzo(a)pyrene, being considered an indicator 
      of exposure to a PAH carcinogenic mixture. For this purpose, we have applied the 
      XGBoost model to a two-year database of pollutant concentrations and 
      meteorological parameters, with the aim to identify the factors which were mostly 
      associated with the observed benzo(a)pyrene concentrations and to describe types 
      of environments that supported the interactions between benzo(a)pyrene and other 
      polluting species. The pollutant data were collected at the energy industry 
      center in Serbia, in the vicinity of coal mining areas and power stations, where 
      the observed benzo(a)pyrene maximum concentration for a study period reached 43.7 
      ngm-3. The metaheuristics algorithm has been used to optimize the XGBoost 
      hyperparameters, and the results have been compared to the results of XGBoost 
      models tuned by eight other cutting-edge metaheuristics algorithms. The 
      best-produced model was later on interpreted by applying Shapley Additive 
      exPlanations (SHAP). As indicated by mean absolute SHAP values, the temperature 
      at the surface, arsenic, PM10, and total nitrogen oxide (NOx) concentrations 
      appear to be the major factors affecting benzo(a)pyrene concentrations and its 
      environmental fate.
FAU - Jovanovic, Gordana
AU  - Jovanovic G
AUID- ORCID: 0000-0001-8657-423X
AD  - Institute of Physics Belgrade, National Institute of the Republic of Serbia, 
      University of Belgrade, 11000 Belgrade, Serbia.
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
FAU - Perisic, Mirjana
AU  - Perisic M
AUID- ORCID: 0000-0002-8287-4136
AD  - Institute of Physics Belgrade, National Institute of the Republic of Serbia, 
      University of Belgrade, 11000 Belgrade, Serbia.
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
FAU - Bacanin, Nebojsa
AU  - Bacanin N
AUID- ORCID: 0000-0002-2062-924X
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
FAU - Zivkovic, Miodrag
AU  - Zivkovic M
AUID- ORCID: 0000-0002-4351-068X
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
FAU - Stanisic, Svetlana
AU  - Stanisic S
AUID- ORCID: 0000-0002-1842-7366
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
FAU - Strumberger, Ivana
AU  - Strumberger I
AUID- ORCID: 0000-0002-1154-6696
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
FAU - Alimpic, Filip
AU  - Alimpic F
AUID- ORCID: 0000-0003-2083-8065
AD  - Institute of Physics Belgrade, National Institute of the Republic of Serbia, 
      University of Belgrade, 11000 Belgrade, Serbia.
FAU - Stojic, Andreja
AU  - Stojic A
AUID- ORCID: 0000-0002-5293-9533
AD  - Institute of Physics Belgrade, National Institute of the Republic of Serbia, 
      University of Belgrade, 11000 Belgrade, Serbia.
AD  - Faculty of Informatics and Computing, Singidunum University, 11000 Belgrade, 
      Serbia.
LA  - eng
PT  - Journal Article
DEP - 20230421
PL  - Switzerland
TA  - Toxics
JT  - Toxics
JID - 101639637
PMC - PMC10142005
OTO - NOTNLM
OT  - benzo(a)pyrene
OT  - explainable artificial intelligence
OT  - extreme gradient boosting
OT  - machine learning
OT  - metaheuristics optimization
OT  - sine cosine algorithm
OT  - swarm intelligence
COIS- The authors declare no conflict of interest.
EDAT- 2023/04/28 06:42
MHDA- 2023/04/28 06:43
PMCR- 2023/04/21
CRDT- 2023/04/28 01:53
PHST- 2023/02/25 00:00 [received]
PHST- 2023/04/17 00:00 [revised]
PHST- 2023/04/19 00:00 [accepted]
PHST- 2023/04/28 06:43 [medline]
PHST- 2023/04/28 06:42 [pubmed]
PHST- 2023/04/28 01:53 [entrez]
PHST- 2023/04/21 00:00 [pmc-release]
AID - toxics11040394 [pii]
AID - toxics-11-00394 [pii]
AID - 10.3390/toxics11040394 [doi]
PST - epublish
SO  - Toxics. 2023 Apr 21;11(4):394. doi: 10.3390/toxics11040394.