Cotton yield prediction with Markov Chain Monte Carlo-based simulation model integrated with genetic programing algorithm: a new hybrid copula-driven approach

Ali, Mumtaz and Deo, Ravinesh C. and Downs, Nathan J. and Maraseni, Tek (2018) Cotton yield prediction with Markov Chain Monte Carlo-based simulation model integrated with genetic programing algorithm: a new hybrid copula-driven approach. Agricultural and Forest Meteorology, 263. pp. 428-448. ISSN 0168-1923

Abstract

Reliable data-driven models designed to accurately estimate cotton yield, an important agricultural commodity,can be adopted by farmers, agricultural system modelling experts and agricultural policy-makers in strategicdecision-making processes. In this paper a hybrid genetic programing model integrated with the Markov ChainMonte Carlo (MCMC) based Copula technique is developed to incorporate climate-based inputs as the predictorsof cotton yield, for selected study regions: Faisalabad (31.4504 °N, 73.1350 °E), Multan (30.1984 °N, 71.4687 °E)and Nawabshah (26.2442 °N, 68.4100 °E), as important cotton growing hubs in the developing nation ofPakistan. Several different types of GP-MCMC-copula models were developed, each with the well-known copulafamilies (i.e., Gaussian, student t, Clayton, Gumble Frank and Fischer-Hinzmann functions) to screen and utilizean optimal cotton yield forecast model for the present study region. The results of the GP-MCMC based hybridcopula model were evaluated with a standalone GP and the MCMC based copula model in accordance withstatistical analysis of the predicted yield based on correlation coefficient (r), Willmott’s index (WI), Nash-Sutcliffe coefficient (NSE), root mean squared error (RMSE) and mean absolute error (MAE) in the independenttest phase. Further performance preciseness was evaluated by the Akiake Information Criterion (AIC), theBayesian Information Criterion (BIC) and the Maximum Likelihood (MaxL) for the GP-MCMC based copula aswell as the MCMC based copula model. GP-MCMC-Clayton copula model generated the most accurate result forthe Multan station. For the optimal GP-MCMC-Clayton copula model, the acquired model evaluation metrics forMultan were: (LM≈0.952; RRMSE≈2.107%; RRMAE≈1.771%) followed by the MCMC based Gaussian copulamodel (LM≈0.895; RRMSE≈4.541%; RRMAE≈0.3.214%) and the standalone GP model (LM≈0.132;RRMSE≈23.638%; RRMAE≈22.652%), indicating the superiority of the GP-MCMC-Clayton copula model inrespect to the other benchmark models. The performance of GP-MCMC based copula model was also found to besuperior in the case of Faisalabad and Nawabshah station as confirmed by AIC, BIC, MaxLmetrics, including alarger value of the Legates-McCabe’s (LM) index, utilized in conjunction with the relative percentage RRMSE andthe relative mean absolute error (RMAE). Accordingly, it is averred that the developed GP-MCMC copula modelcan be considered as a pertinent data-intelligent tool used for accurate prediction of cotton yield, utilizing thereadily available climate datasets in agricultural regions and is of relevance to agricultural yield simulation andsectoral decision-making


Statistics for USQ ePrint 34872
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Permanent restricted access to Published version, in accordance with the copyright policy of the publisher. This study was supported by USQ PhD Scholarship 2016 - 2018. The principal supervisor was Dr Ravinesh Deo and associate supervisors Drs Nathan Downs and A/Prof Tek Maraseni.
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences
Date Deposited: 27 Sep 2018 01:30
Last Modified: 13 Mar 2019 22:34
Uncontrolled Keywords: crop yield prediction; cotton yield; climate data; genetic programming; Markov Chain Monte Carlo-based copula model
Fields of Research : 07 Agricultural and Veterinary Sciences > 0701 Agriculture, Land and Farm Management > 070103 Agricultural Production Systems Simulation
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080110 Simulation and Modelling
07 Agricultural and Veterinary Sciences > 0703 Crop and Pasture Production > 070302 Agronomy
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970105 Expanding Knowledge in the Environmental Sciences
Identification Number or DOI: 10.1016/j.agrformet.2018.09.002
URI: http://eprints.usq.edu.au/id/eprint/34872

Actions (login required)

View Item Archive Repository Staff Only