Human - Centered Process Mining With Generative - Ai for Sustainable and Energy-Efficient Agriculture Systems

Agriculture is under the greatest challenge due to climate fluctuation, soil erosion, and growing food demands in the world. To solve these problems, this study suggests a Human-Centered Process Mining (HCPM) framework, combined with Generative Artificial Intelligence (GenAI) that can help to create sustainable and energy-efficient agricultural systems. The paper takes advantage of the Crop Yield and Environmental Factors Dataset (20142023), a collection of various climatic and soil parameters in ten selected crops. Process mining methods were used to detect latent dependencies, operational inefficiencies, and time series patterns in agricultural processes, and generative AI models were used to simulate adaptive situations in order to optimize the yield, resource distribution and energy consumption. HITL approach which was used provided transparency, interpretability and ethical validation whereby domain experts were free to refine and validate AI-generated insights. The key performance metrics including accuracy, precision, recall, F1-score, and ROC-AUC were used to evaluate the framework based on sustainability indicators, including energy efficiency and environmental stability. The results of the experiment showed that process mining when combined with generative AI are more predictively accurate and interpretable than the standard machine learning models, and human feedback increases contextual relevance and confidence in system recommendations. It is the combination of human thinking and the intelligent automation that result in the development of dynamic agricultural management plans that will be able to adjust to changes in the environmental conditions and reduce the ecological footprint. The paper concludes that an explainable, generative, and human-centered AI framework is a possible solution to sustainable agricultural change, which facilitates energy-conserving agricultural practices, productivity resilience, and responsible AI implementation in food systems. The study is relevant to the emerging literature on AI as a sustainability strategy, that is, the collaboration of the human and machine can lead to significant changes in achieving climate-intelligent, data-driven agriculture.