In the Sultanate of Oman, optimizing agricultural crop selection is crucial for enhancing food security and sustainability. This innovative approach aims to increase agricultural productivity in Oman while promoting sustainable practices, ultimately contributing to the nation’s food security and economic resilience. This study proposes an integrated sensor-based machine learning (ML) framework that leverages artificial intelligence (AI) to facilitate optimal crop selection tailored to the unique environmental and climatic conditions of the region. By utilizing various sensors, such as soil moisture, temperature, humidity, pH value of the soil, and rain, data is collected and analyzed to assess the suitability of different crops. Machine learning algorithms, including decision trees, random forests, and support vector machines, are employed to model crop performance based on historical data and current environmental factors. The framework provides farmers with actionable insights and recommendations, enabling them to make informed decisions that improve yield and resource efficiency. Findings from the study demonstrate that Corn is a superior crop when using measured values of temperature, humidity, soil moisture, pH level of the soil and rainfall. Muskmelon is the least grown crop when compared to all other crops under these same measured conditions.