In light of the dynamic challenges facing agricultural land markets, the conventional analytical frameworks fall short in capturing the intricate interplay of strategic decisions and evolving complexities. This necessitates the development of a novel method, integrating deep learning into Agent-based Modelling, to provide a more realistic and nuanced understanding of land market dynamics, enabling informed policy assessments and contributing to a comprehensive discourse on agricultural structural change. In this paper, different deep learning models are tested and evaluated, as emulators of AgriPoliS (Agricultural Policy Simulator). AgriPoliS is an agent-based model used to model the evolution of structural change in agriculture resultant on the change in the policy environment. This study is part of preliminary works towards integrating deep learning methods and predictions with AgriPoliS to capture strategic decision making and actions of agents in land markets. The paper tests the models on their suitability, computational requirements and run-time complexities. The output from AgriPoliS serves as the input features for the deep learning models. Models are evaluated using a combination of coefficient of determination (R2 score), mean absolute error, visual displays and runtime. The models were able to replicate the variable of interest with a high degree of accuracy with R2 score of more than 90%. The CNN was the most suited for replicating the data. Through this work, we learned the required complexities, computational and training efforts needed to integrate deep learning and AgriPoliS to capture strategic decision-making.