Abstract

Precision nutrient management optimizes fertilizer application to enhance crop productivity while minimizing environmental impacts. This study explores the integration of artificial intelligence (AI) with soil and plant sensors to monitor and manage nitrogen (N) and phosphorus (P) in temperate and semi-arid agricultural systems. Field experiments evaluated AI-driven sensors for real-time nutrient monitoring, coupled with machine learning models to predict crop nutrient needs. Results showed that AI-integrated systems improved nutrient use efficiency (NUE, PUE) by 15–25% and reduced fertilizer inputs by 20–30% compared to conventional methods. Soil microbial activity and crop yields were enhanced, particularly in temperate soils. These findings highlight the potential of AI-integrated sensors for sustainable agriculture, though challenges include high initial costs and data calibration needs.