Artificial Intelligence–Driven Precision Agriculture Systems for Sustainable Crop Yield Optimization Under Climate Change Conditions

Abstract

Agriculture faces severe pressure from climate variability, population growth, shrinking natural
resources, and the need for sustainable food production. Traditional farming methods based on generalized practices often fail to address field-level variability and emerging climatic risks. Artificial intelligence (AI) has become a transformative force in precision agriculture by enabling data-driven decisions that optimize
crop productivity while conserving resources. This paper examines AI-driven precision agriculture systems for sustainable crop yield optimization under climate change conditions. It analyzes the integration of remote sensing, Internet of Things (IoT) sensors, machine learning, robotics, and predictive analytics into modern farming ecosystems. AI models can estimate yield, detect diseases, optimize irrigation, recommend
fertilizer dosage, forecast pest outbreaks, and adapt cropping schedules according to changing weather conditions. These capabilities reduce input waste, improve profitability, and strengthen resilience against droughts, floods, and heat stress. The paper also evaluates implementation barriers such as fragmented landholdings, high capital costs, weak digital infrastructure, limited farmer literacy, and concerns regarding data ownership. A comprehensive framework is proposed in which satellite data, drone imagery, soil information, and farm operations are processed through cloud-edge intelligence systems to generate real-time recommendations. The study concludes that AI-driven precision agriculture offers one of the most practical pathways toward climate-smart and sustainable farming. However, inclusive adoption requires
affordable technologies, policy support, open data ecosystems, rural connectivity, and continuous capacity building among farming communities.