A socio-technical agent-based simulation model for predicting smart agriculture adoption dynamics

Area of Science:

• Agricultural Economics
• Sociology of Technology
• Computational Social Science

Background:

• Traditional models inadequately capture socio-technical factors in agricultural technology adoption.
• Existing approaches overlook dynamic social interactions, trust networks, and heterogeneous decision-making.
• This gap limits predictive accuracy and effective policy design for smart agriculture.

Purpose of the Study:

• To present AdoptAgriSim, a Socio-Technical Agent-Based Simulation Model for Predicting Smart Agriculture Adoption Dynamics.
• To integrate economic, social, and technological dimensions for a unified framework.
• To improve understanding and prediction of technology diffusion in agriculture.

Main Methods:

• Developed a Socio-Technical Agent-Based Simulation Model (AdoptAgriSim).
• Employed multi-agent reinforcement learning and socio-economic network modelling.
• Incorporated a multi-objective decision mechanism balancing economic and social learning via trust networks.

Main Results:

• AdoptAgriSim achieved 94.2% prediction accuracy for five-year adoption intervals across diverse datasets (USA, Europe, India).
• The model reproduced emergent behaviors like technology clustering and peer-driven influence cascades.
• Social factors were found to contribute 34% more to adoption variance than previously estimated.

Conclusions:

• Social factors and trust networks are central to accelerating agricultural technology diffusion.
• Strengthening social connectivity and network interventions can drive sustainable agricultural transformation.
• AdoptAgriSim provides valuable insights for policymakers and technology designers in smart agriculture.