抄録
Global agriculture is facing severe challenges, including increasing crop yields, addressing climate change, and coping with resource shortages. Accurate prediction of crop growth is crucial for sustainable agricultural development. Traditional prediction methods have limitations in data processing capacity and forecasting accuracy, while the introduction of artificial intelligence (AI) offers new opportunities for optimizing prediction models. This paper systematically reviews the key technologies and applications of AI in crop growth prediction, covering machine learning, deep learning, and ensemble learning methods under various crop and climate conditions. It further explores the decisive impact of data quality and quantity on AI model performance and analyzes pressing challenges such as model interpretability, data privacy, and security. Based on existing research, this paper proposes future research directions and application strategies for AI-driven intelligent agriculture, aiming to provide theoretical support and practical guidance for precision and smart farming.
