The field of earth science is undergoing rapid advancements driven by emerging technologies. These technologies aid in understanding atmospheric and environmental systems while addressing global challenges, ultimately optimizing resources to improve agricultural productivity and sustainability. Artificial Intelligence (AI)-driven computational approaches are becoming pivotal for resource allocation, data analysis, and prediction in agriculture. Machine Learning (ML) optimization models and predictive analytics enable the forecasting resource demands and yield outcomes based on weather patterns, soil conditions, and historical data. Additionally, agent-based modelling and multi-agent systems are employed to optimize land use, water resource distribution, and infrastructure management. Reinforcement learning algorithms further enhance the decision-making in irrigation schedules and fertilizer application strategies as per crop growth stages. Fuzzy logic systems also provide flexibility in decision making accounting for uncertain data such as crop conditions and soil moisture levels. AI is reshaping agriculture landscapes by offering simulation models to test different agriculture methods under varying climate scenarios and resource constraints. AI-powered Internet of Things (IoT) systems analyse the data collected from sensors, satellites, and drones to provide actionable insights, automating decisions in real time. These AI models, integrated with IoT sensors, are particularly beneficial for providing real-time monitoring of soil moisture, weather conditions, water stress, and crop health. The collected data is further processed and analysed using ML and deep learning algorithms to inform resource allocation decisions. Moreover, optimization algorithms are used to find the best solutions for resource distribution. While remote sensing and ML and big data analytics help to analyse market trends and predict crop demand, enabling farmers to make informed planting decisions and reduce food wastage. AI-driven strategies for crop rotation and diversity also contribute in improving soil health and crop yield. Beside this, AI-based blockchain and cloud computing systems enhance monitoring and real-time resource management across multiple farms. Overall, AI-driven approaches and machine learning algorithms are playing a significant role in transforming agriculture practices, facilitating data-driven and sustainable resource allocation over large agriculture areas.