Using Big Data and Machine Learning to Optimize Agricultural Resource Allocation and Ecological and Economic Benefit Evaluation

Introduction

In the context of global population growth and limited resources, the efficient allocation of agricultural resources has become a key issue in improving agricultural productivity and promoting sustainable development. Traditional agricultural resource allocation methods rely on experience and manual judgment, leading to uneven resource utilization, waste, and low efficiency. With the rapid development of information technology, especially big data and machine learning, these technologies provide new solutions for optimizing the allocation of agricultural resources. Existing studies have shown that data-driven water resource allocation optimization can effectively improve water use efficiency in agriculture and reduce waste (G. Liu et al., 2018). At the same time, machine learning algorithms, such as the particle swarm optimization algorithm, have also been proven to significantly optimize digital agricultural resource allocation (Hou & Meen, 2023). In the field of green agricultural technologies and ecological restoration, comprehensive assessments of ecological and economic benefits have already been widely researched (Wang et al., 2022; Wei et al., 2024).

In the field of agricultural resource allocation, with the development of big data and machine learning technologies, research has gradually focused on how to utilize these technologies to improve resource utilization efficiency and optimize allocation. Cui et al. (2015) proposed an agricultural water resource management system based on a two-stage stochastic fractional programming model, emphasizing the importance of reasonable water resource allocation. H. Chen et al. (2024) assessed green poverty reduction strategies in ecologically fragile areas and explored the interrelationship between agricultural resource allocation and ecological restoration. Ji et al. (2023) used the entropy method and coupling harmony degree model to evaluate the ecological benefits of urban green spaces in Nanjing, providing a theoretical framework for assessing agricultural land ecological benefits.

In the context of intelligent agricultural resource allocation Hariprasath et al. (2023), Kethineni and Gera (2023), and Kayhomayoon et al. (2022) proposed a simulation-optimization-based water resource management model applied to semi-arid regions, demonstrating the potential of big data and machine learning in agricultural resource optimization. Hassan-Esfahani et al. (2015) utilized water balance methods, machine learning, and remote sensing data to optimize irrigation water allocation, advancing the digital management of agricultural resources. Meanwhile, Ojo et al. (2024) optimized hydroponic crop resource allocation by precisely estimating phenotypic parameters, improving resource allocation efficiency. F. Chen and Hu (2021) proposed a big data-based agricultural and rural ecological management system, highlighting the importance of data integration and analysis in optimizing resource allocation in complex systems. Tan et al. (2024) explored the impact of digital policies and green innovation on the transformation of the agricultural industry, proposing the potential of digital technologies in promoting green agricultural development. Su and Jiang (2021) evaluated the economic and environmental efficiency of land use from the perspective of decision makers’ subjective preferences, offering a different perspective on agricultural resource allocation.