Stepwise genetic algorithm for adaptive management: Application to air quality monitoring network optimization

Abstract A novel algorithm named the stepwise genetic algorithm (SGA) is proposed to optimize the air quality monitoring network of mainland China under the framework of adaptive management. SGA is adapted from the genetic algorithm by modifying the operators of “mutation” and “crossover” to increase the number of removed sites by one at each step. Approximately half of the sites are adequate to achieve the same mean kriging variance (MKV) as that from all the sites, and the PM2.5 maps interpolated from these two site sets are very similar. Based on the site array proposed by SGA, the MKV shows a U-shaped trend with the number of removed sites, where the initial decrease of MKV (indicating improvement of interpolation accuracy by removing some sites) has only rarely been reported before. Mathematical proof demonstrates that the clustered sites tend to cause collinearity in the covariance matrix and hence result in MKV inflation.

[1]  Krista G. Hilchey,et al.  A review of citizen science and community-based environmental monitoring: issues and opportunities , 2011, Environmental monitoring and assessment.

[2]  X. Zhao,et al.  Analysis of a winter regional haze event and its formation mechanism in the North China Plain , 2013 .

[3]  Tormod Næs,et al.  Understanding the collinearity problem in regression and discriminant analysis , 2001 .

[4]  Enrique Alba,et al.  Parallel Genetic Algorithms , 2011, Studies in Computational Intelligence.

[5]  Min Li,et al.  Prediction of PM2.5 concentration based on the similarity in air quality monitoring network , 2018, Building and Environment.

[6]  Yi Li,et al.  National-Scale Estimates of Ground-Level PM2.5 Concentration in China Using Geographically Weighted Regression Based on 3 km Resolution MODIS AOD , 2016, Remote. Sens..

[7]  J. Aalto,et al.  New gridded daily climatology of Finland: Permutation‐based uncertainty estimates and temporal trends in climate , 2016 .

[8]  Hans Wackernagel,et al.  Multivariate Geostatistics: An Introduction with Applications , 1996 .

[9]  Alexandra M. Schmidt,et al.  Stochastic search algorithms for optimal design of monitoring networks , 2009 .

[10]  Jianguo Wu,et al.  A multi-objective assessment of an air quality monitoring network using environmental, economic, and social indicators and GIS-based models , 2014, Journal of the Air & Waste Management Association.

[11]  Jin Li,et al.  Spatial interpolation methods applied in the environmental sciences: A review , 2014, Environ. Model. Softw..

[12]  Yu Zhan,et al.  Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm , 2017 .

[13]  Qi Ying,et al.  Spatial and temporal variability of PM2.5 and PM10 over the North China Plain and the Yangtze River Delta, China , 2014 .

[14]  Margaret A. Oliver,et al.  A tutorial guide to geostatistics: Computing and modelling variograms and kriging , 2014 .

[15]  Luca Scrucca,et al.  On Some Extensions to GA Package: Hybrid Optimisation, Parallelisation and Islands EvolutionOn some extensions to GA package: hybrid optimisation, parallelisation and islands evolution , 2016, R J..

[16]  S. Pickett,et al.  Multicontaminant air pollution in Chinese cities , 2018, Bulletin of the World Health Organization.

[17]  Luca Scrucca,et al.  GA: A Package for Genetic Algorithms in R , 2013 .

[18]  Kouhei Yamamoto,et al.  Optimization of air monitoring networks using chemical transport model and search algorithm , 2015 .

[19]  Tomislav Hengl,et al.  A Practical Guide to Geostatistical Mapping , 2009 .

[20]  Samer Majdalani,et al.  Estimating preferential water flow parameters using a binary genetic algorithm inverse method , 2008, Environ. Model. Softw..

[21]  R. Clark,et al.  Adaptive management of natural resources: theory, concepts, and management institutions. , 2005 .

[22]  Paul H. Calamai,et al.  Adapting Genetic Algorithms for Combinatorial Optimization Problems in Dynamic Environments , 2008 .

[23]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[24]  Edzer J. Pebesma,et al.  Applied Spatial Data Analysis with R - Second Edition , 2008, Use R!.

[25]  Laijun Zhao,et al.  Identifying redundant monitoring stations in an air quality monitoring network , 2018, Atmospheric Environment.

[26]  K. Hubacek,et al.  The characteristics and drivers of fine particulate matter (PM2.5) distribution in China , 2017 .

[27]  Edzer J. Pebesma,et al.  Multivariable geostatistics in S: the gstat package , 2004, Comput. Geosci..

[28]  Atsuyuki Okabe,et al.  Spatial Tessellations: Concepts and Applications of Voronoi Diagrams , 1992, Wiley Series in Probability and Mathematical Statistics.

[29]  B Ainslie,et al.  Application of an entropy-based Bayesian optimization technique to the redesign of an existing monitoring network for single air pollutants. , 2009, Journal of environmental management.

[30]  Dimiter Prodanov,et al.  Spatial clustering analysis in neuroanatomy: Applications of different approaches to motor nerve fiber distribution , 2007, Journal of Neuroscience Methods.

[31]  Jürgen Pilz,et al.  Network optimization algorithms and scenarios in the context of automatic mapping , 2011, Comput. Geosci..

[32]  C. Clerbaux,et al.  First simultaneous space measurements of atmospheric pollutants in the boundary layer from IASI: A case study in the North China Plain , 2014 .

[33]  Kenneth L. Demerjian,et al.  A review of national monitoring networks in North America , 2000 .

[34]  Ting Yang,et al.  Investigation of the sources and evolution processes of severe haze pollution in Beijing in January 2013 , 2014 .

[35]  Jun Wang,et al.  Optimization of a Coastal Environmental Monitoring Network Based on the Kriging Method: A Case Study of Quanzhou Bay, China , 2016, BioMed research international.

[36]  S. M. Shiva Nagendra,et al.  Urban air quality management-A review , 2015 .

[37]  Y. Xing,et al.  The impact of PM2.5 on the human respiratory system. , 2016, Journal of thoracic disease.

[38]  M. Sambridge,et al.  On entropy and clustering in earthquake hypocentre distributions , 2000 .

[39]  Joseph R. Kasprzyk,et al.  Introductory overview: Optimization using evolutionary algorithms and other metaheuristics , 2019, Environ. Model. Softw..

[40]  Wenzhao Xu,et al.  Detecting spatial patterns of rivermouth processes using a geostatistical framework for near-real-time analysis , 2017, Environ. Model. Softw..

[41]  Xiaohong Liu,et al.  Characteristics and formation mechanism of continuous extreme hazes in China: a case study in autumn of 2014 in the North China Plain , 2015 .

[42]  R. O’Brien,et al.  A Caution Regarding Rules of Thumb for Variance Inflation Factors , 2007 .

[43]  Saravanan Arunachalam,et al.  Bayesian maximum entropy integration of ozone observations and model predictions: an application for attainment demonstration in North Carolina. , 2010, Environmental science & technology.

[44]  Y. H. Zhang,et al.  Characteristics and formation mechanism of continuous hazes in China: a case study during the autumn of 2014 in the North China Plain , 2015 .

[45]  P. Fraser,et al.  Greenhouse gas network design using backward Lagrangian particle dispersion modelling - Part 1: Methodology and Australian test case , 2014 .

[46]  M. Cunha,et al.  Optimization of a hydrometric network extension using specific flow, kriging and simulated annealing , 2017 .

[47]  Michaela Saisana,et al.  Multi-objective optimization of air quality monitoring , 2007, Environmental monitoring and assessment.

[48]  Mikko Kolehmainen,et al.  Evolving the neural network model for forecasting air pollution time series , 2004, Eng. Appl. Artif. Intell..

[49]  Jens Borken-Kleefeld,et al.  Cost-effective control of air quality and greenhouse gases in Europe: Modeling and policy applications , 2011, Environ. Model. Softw..

[50]  Nan Wang,et al.  Numerical simulations for the sources apportionment and control strategies of PM2.5 over Pearl River Delta, China, part I: Inventory and PM2.5 sources apportionment. , 2018, The Science of the total environment.

[51]  Edzer Pebesma,et al.  Spatio-Temporal Interpolation using gstat , 2016, R J..

[52]  Yang Liu,et al.  Satellite-Based Spatiotemporal Trends in PM2.5 Concentrations: China, 2004–2013 , 2015, Environmental health perspectives.

[53]  Sujing Wang,et al.  Multiobjective Optimization for Air-Quality Monitoring Network Design , 2015 .