Spatial intelligent decision support system for increasing productivity on natural rubber agroindustry by green productivity approach

Abstract

Purpose The purpose of this paper is to develop a spatial intelligent decision support system (SIDSS) for increasing productivity in the rubber agroindustry by green productivity (GP) approach. The SIDSS was used to measure the productivity of rubber plantation and rubber agroindustry by GP approach, and select the best strategies for increasing the productivity of rubber agroindustry. Design/methodology/approach This system was developed by combining spatial analysis, GP, and fuzzy analytic network process (ANP) with the model-based management system, which is able to provide comprehensive and meaningful decision alternatives for the development of natural rubber agroindustry. Rubber plantation productivity measurement model was used to find the productivity level of rubber plantation with fuzzy logic, and also to provide information and decision alternatives to all stakeholders regarding spatial condition of rubber agroindustry, production process flow, and analysis of the seven green wastes at each production process flow using the geographic information system. GP measurement model was used to determine the productivity performance of the rubber agroindustry with the green productivity index (GPI). The best strategy for increasing the productivity was determined with fuzzy ANP. Findings Rubber plantation measurement model showed that the average of plantation productivity was 6.25 kg/ha/day. GP measurement model showed that the GPI value of ribbed smoked sheet (RSS) was 0.730, whereas of crumb rubber (CR) was 0.126. The best strategy for increasing the productivity of rubber agroindustry was raw material characteristics control. Based on the best strategy, the GPI value of RSS was 1.340, whereas of CR was 0.228. Research limitations/implications This decision support system is still limited as it is based on static data; it needs further development so that it can be more dynamically based on developments in the rubber agroindustry related levels of productivity and environmental impact. In addition, details regarding the decision to increase the productivity of the rubber section by benchmarking efforts should be studied further, both among plantation as well as among countries such as Thailand so that the productivity of rubber plantation and agroindustry can be integrated. Practical implications This research can help the planters to select superior clones for rubber trees, to improve the technique of tapping latex, and to use a better coagulant. The good quality and quantity of raw material is a key factor in increasing the productivity of rubber agroindustry; if the quality of latex is good then the resulting product will also have a good quality and production cost can be reduced. In addition, the application of GP through the calculation of GPI value using improvement scenarios can be used as a reference and comparison for evaluating the performance of rubber agroindustry to reduce the waste generated by the activities of rubber processing plant. Social implications Reduction of waste generated by production activities can improve the quality of life of the workforce and the environment. The calculation of GPI value can also be used as a basis to use raw materials, water, and electricity more efficiently. Originality/value This system was developed by combining spatial analysis, GP, and fuzzy ANP with the model-based management system, which is able to provide comprehensive and meaningful decision alternatives for the development of natural rubber agroindustry.

The conceptual design of intelligent spatial decision support system for the fishery-industry logistic

“…A combination of DSS and GIS can be used for market segmentation, early risk warning, forecasting, and export trade risk management can automate decision-making by creating information instantaneously accessible to all actors [23]. According to [24] and Marimin et al [25], an intelligent DSS can measure productivity and provide solutions and simulations. They did not mention the spatial DSS in either article.…”

Exploring the sustainability dimensions of coffee agro-industry: a critical review and future research agenda

“…The steps to develop sustainability in the supply chain lead to a balance of three aspects, namely economic, social, and environmental, or to a triple bottom line balance, namely profit, people, and planet [12]. Appropriate data analysis techniques are needed, and an integrated approach between economic, social, and environmental aspects is reflected in the concept of green productivity [19].…”

Spatial-based model for oil palm plantation suitability rating and its smallholder farmers’ competitiveness: a case study at Kampar Regency, Riau Province, Indonesia

“…In this study, WebGIS was used to visualize spatial data which were carried out through data processing results extraction which was then used to determine fertilizer dose. Teniwut et al (2017) used GIS in the case of rubber agro-industry by aggregating the spatial conditions of rubber plantations, the flow of production processes and the analysis of seven sources of waste generation. The aim is to increase the productivity of the rubber agro-industry through the integration and combination of various models.…”