Automation of Machine Learning Model in Dynamic Production Environment

Deploying machine learning models in production environments, especially in agriculture, is a complex and resource-intensive task which requires significant manual effort to manage unseen data and maintain consistent performance. This research addresses these challenges by developing innovative approaches to automate model deployment in the context of precision agriculture, leveraging scripting techniques to simplify and accelerate the deployment process. The primary objectives of this study are to create a comprehensive framework for efficient and reliable automation, implement dynamic data preprocessing for unseen agricultural data, and establish an intelligent monitoring system to ensure consistent and accurate predictions in real-world farming environments. Additionally, this research incorporates Explainable Artificial Intelligence (XAI) techniques to enhance interpretability and promote transparency in AI-driven agricultural decision-making. Integrating a Streamlit-based interface facilitates interactive visualization of model explanations, enabling farmers and agricultural stakeholders to comprehend the reasoning behind recommended decisions. These improvements are consistent with recent advancements in XAI-enhanced smart farming systems, as illustrated in the companion study “XAI Streamlit-Based Enhancing Crop Recommendation System with Advanced Explainable Artificial Intelligence for Smart Farming ”Combining automation and explainability, this study contributes to developing a robust, transparent, and scalable framework that bridges the gap between advanced AI techniques and their practical application in sustainable agriculture.