AI-Driven Productivity Impact Analysis Using GIS and IoT Data in Sugar Industries: A Pilot Study

Abstract

Background: Increasing demands in terms of efficient operations, cost reduction, and improving productivity have emerged in the sugar industry due to increased competition and sustainable developments. The current pilot study suggests a framework to evaluate the impact that integration of AI, GIS, and IoT would bring on productivity of sugar mills. Method: This research adopts a mixed frameworks approach to investigate the impact of integrated AI, GIS and IoT technologies on sugar mill productivity. Based on the simulated data that represents more than 20 sugar mills operating in Maharashtra, India, our findings suggest that adoption metrics concerning these technologies positively correlate with performance metrics such as productivity index, cost reduction, downtime reduction, and improvement in sugar recovery. Result: AI adoption correlated most strongly with productivity index (r = 0.264), followed by integration of IoT technologies (r = 0.119) and GIS-based monitoring (r = 0.042). Random Forest regression provided R² value of 0.082. Among the most significant predictors, predictive maintenance score (14.8%) and scores of AI adoption and road quality index (13.5% each) were detected. The average productivity index was at 85.82, while average reductions in cost, downtime, and sugar recovery amounted to 14.12%, 31.92%, and 4.86% correspondingly. Conclusion: In general, it could be noted that the proposed framework is applicable to various locations where sugar is produced. This study provides a methodology that can be replicated to explore the relationship between technology and productivity in the agro- industrial sector, while emphasizing the importance of predictive maintenance and AI decision-making systems to achieve business outcomes.