Development of geospatial model for predicting Metisa plana's prevalence in Malaysian oil palm plantation

International Conference on Green Agro-industry and Bioeconomy

农业科学;工业技术（总论）;经济学

Ruslan, S.A.^1 ; Muharam, F.M.^1 ; Omar, D.^2 ; Zulkafli, Z.D.^3 ; Zambri, M.P.^4

Department of Agriculture Technology, Faculty of Agriculture, Universiti Putra Malaysia, Selangor, Malaysia^1

Department of Plant Protection, Faculty of Agriculture, Universiti Putra Malaysia, Selangor, Malaysia^2

Department of Civil Engineering, Faculty of Engineering, Universiti Putra Malaysia, Selangor, Malaysia^3

Department of Agronomy and Innovation, TH Plantations Berhad, Kuala Lumpur, Malaysia^4

关键词: Climatic stress;    Early Warning System;    Geo-spatial data;    Geospatial model;    Geospatial technology;    Landscape ecology;    Normalized difference vegetation index;    Oil palm plantations;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/230/1/012110/pdf
DOI  :  10.1088/1755-1315/230/1/012110

来源: IOP

【 摘 要 】

Metisa plana (Walker) is leaves defoliating insect that is able to cause a staggering loss of USD 2.32 billion within two years to Malaysian oil palm industry. Therefore, an early warning system to predict the outbreak of Metisa plana that is sustainable in terms of cost, time, and energy is crucial. Nonetheless, the current approaches of conventional practices are highly dependent on ineffective and time-consuming in-situ data collection. Geospatial technologies can be used to obtain data in rapid, harmless, and cost-effective manners. Hence, this study utilized the technologies such as land surface temperature (LST), rainfall (RF), relative humidity (RH), and Normalized Difference Vegetation Index (NDVI) to i) examine climatic stresses that cause the outbreak of Metisa plana, ii) to construct the relationship between geospatial data and Metisa plana outbreak, and iii) to predict the outbreak of Metisa plana in oil palm plantation. LST between 24°C and 28°C showed a strong relationship with the presence of Metisa plana. Consistent day pattern was absent in the correlation between LST, RF, RH with Metisa plana. Presence of Metisa plana was not correlated with NDVI. ANN prediction models with the highest accuracy of 95.42% was achieved by using RH data. Model generated by combined variables were Able to predict the presence of Metisa plana with the accuracy of 72.64%. In summary, the elucidation of Metisa plana's landscape ecology is possible with the utilization of geospatial technology, and temperature has been found to be the most important factor that influence the presence of Metisa plana.