? Simple model based on artificial neural network for early prediction and simulation winter rapeseed yield
JIA
      
Quick Search in JIA      Advanced Search  
    2019, Vol. 18 Issue (01): 54-61     DOI: 10.1016/S2095-3119(18)62110-0
Crop Science Current Issue | Next Issue | Archive | Adv Search  |   
Simple model based on artificial neural network for early prediction and simulation winter rapeseed yield
Gniewko Niedba?a
Institute of Biosystems Engineering, Faculty of Agronomy and Bioengineering, Poznań University of Life Sciences, Poznań 60-627, Poland
 Download: PDF in ScienceDirect (1633 KB)   HTML (1 KB)   Export: BibTeX | EndNote (RIS)      Supporting Info
Abstract 
The aim of the research was to create a prediction model for winter rapeseed yield.  The constructed model enabled to perform simulation on 30 June, in the current year, immediately before harvesting.  An artificial neural network with multilayer perceptron (MLP) topology was used to build the predictive model.  The model was created on the basis of meteorological data (air temperature and atmospheric precipitation) and mineral fertilization data.  The data were collected in the period 2008–2017 from 291 productive fields located in Poland, in the southern part of the Opole region.  The assessment of the forecast quality created on the basis of the neural model has been verified by defining forecast errors using relative approximation error (RAE), root mean square error (RMS), mean absolute error (MAE), and mean absolute percentage error (MAPE) metrics.  An important feature of the created predictive model is the ability to forecast the current agrotechnical year based on current weather and fertilizing data.  The lowest value of the MAPE error was obtained for a neural network model based on the MLP network of 21:21-13-6-1:1 structure, which was 9.43%.  The performed sensitivity analysis of the network examined the factors that have the greatest impact on the yield of winter rape.  The highest rank 1 was obtained by an independent variable with the average air temperature from 1 January to 15 April of 2017 (designation by the T1-4_CY model).
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Gniewko Niedbał
a
Key wordsforecast     MLP network     neural model     prediction error     sensitivity analysis     yield simulation     
Received: 2018-05-08; Accepted: 2018-09-29
Corresponding Authors: Correspondence Gniewko Niedba?a, Tel: +48-61-8487156, E-mail: gniewko@up.poznan.pl    
Cite this article:   
Gniewko Niedbała. 2019. Simple model based on artificial neural network for early prediction and simulation winter rapeseed yield. Journal of Integrative Agriculture, 18(01): 54-61.
URL:  
http://www.chinaagrisci.com/Jwk_zgnykxen/EN/10.1016/S2095-3119(18)62110-0      or     http://www.chinaagrisci.com/Jwk_zgnykxen/EN/Y2019/V18/I01/54
 
No references of article
[1] DAI Wei, LI Yao, ZHU Jun, GE Lin-quan, YANG Guo-qing, LIU Fang. Selectivity and sublethal effects of some frequently-used biopesticides on the predator Cyrtorhinus lividipennis Reuter (Hemiptera: Miridae)[J]. Journal of Integrative Agriculture, 2019, 18(01): 124-133.
Copyright © 2015 ChinaAgriSci.com, All Rights Reserved
Chinese Academy of Agricultural Sciences (CAAS) No. 12 South Street, Zhongguancun, Beijing 100081, P. R. China
http://www.ChinaAgriSci.com   JIA E-mail: jia_journal@caas.cn