Neural networks method in predicting oil palm FFB yields for the Peninsular States of Malaysia


Citation

Hilal Yousif Y., . and A. Yahya, . and W. I. W. Ismail, . and Z. H. Asha’ari, . Neural networks method in predicting oil palm FFB yields for the Peninsular States of Malaysia. pp. 400-412. ISSN 2811-4701

Abstract

Reliable and accurate predictions in oil palm production can provide the basis for management decisions of budgeting storage distribution and marketing. Artificial Neural Network (ANN) and Non-linear Autoregressive Exogenous Neural Network (NARX) models were developed based on 19 440 data set of 15 inputs variables namely percentage of mature area and percentage of immature area rainfall rainy days humidity radiation temperature surface wind speed evaporation and cloud cover ozone (O‚ ) carbon monoxide (CO) nitrogen dioxide (NO‚‚ ) sulphur dioxide (SO‚‚) and particulate matter of less than 10 microns in size (PM‚�‚) for predicting oil palm fresh fruit bunch (FFB). The results were validated with an independent validation dataset. Results showed that NARX models performed more accurately with multiple coefficients of determination (R) reached 97 and mean square errors (MSE) between 0.0104-0.0665 besides being an easy-to-use tool. Generally NARX models proved to give more accurate predictions than the predictions of common ANN and Multi Linear Regression (MLR) models. Finally 15-10-4-1 is chosen as the architecture of NARX for the states of Kedah Kelantan Perak Pahang Selangor and Terengganu. The 15-7-4-1 is the best architecture of NARX for the state of Melaka and Pulau Pinang while 15-13-4-1 architecture is for the state of Johor. This study showed that all of these architectures gave high accuracy with acceptable MSE values.


Download File

Full text available from:

Abstract

Reliable and accurate predictions in oil palm production can provide the basis for management decisions of budgeting storage distribution and marketing. Artificial Neural Network (ANN) and Non-linear Autoregressive Exogenous Neural Network (NARX) models were developed based on 19 440 data set of 15 inputs variables namely percentage of mature area and percentage of immature area rainfall rainy days humidity radiation temperature surface wind speed evaporation and cloud cover ozone (O‚ ) carbon monoxide (CO) nitrogen dioxide (NO‚‚ ) sulphur dioxide (SO‚‚) and particulate matter of less than 10 microns in size (PM‚�‚) for predicting oil palm fresh fruit bunch (FFB). The results were validated with an independent validation dataset. Results showed that NARX models performed more accurately with multiple coefficients of determination (R) reached 97 and mean square errors (MSE) between 0.0104-0.0665 besides being an easy-to-use tool. Generally NARX models proved to give more accurate predictions than the predictions of common ANN and Multi Linear Regression (MLR) models. Finally 15-10-4-1 is chosen as the architecture of NARX for the states of Kedah Kelantan Perak Pahang Selangor and Terengganu. The 15-7-4-1 is the best architecture of NARX for the state of Melaka and Pulau Pinang while 15-13-4-1 architecture is for the state of Johor. This study showed that all of these architectures gave high accuracy with acceptable MSE values.

Additional Metadata

[error in script]
Item Type: Article
AGROVOC Term: Oil palm
AGROVOC Term: Crop yield
AGROVOC Term: Data collection
AGROVOC Term: Data analysis
AGROVOC Term: Agricultural industry
AGROVOC Term: Research scientists
AGROVOC Term: Expert systems
AGROVOC Term: government agencies
AGROVOC Term: Crop management
AGROVOC Term: precision agriculture
Depositing User: Mr. AFANDI ABDUL MALEK
Last Modified: 24 Apr 2025 00:55
URI: http://webagris.upm.edu.my/id/eprint/10248

Actions (login required)

View Item View Item