Big Data in agriculture is growing rapidly through advancements in metagenomics, precision agriculture, and on‐farm sensor technologies, as well as through increased capacity to collect, process, and store these data. Concurrent with 60% increases in food production demands by 2050 and the need for sustainable intensification, is the increased need for data synthesis across temporal and spatial scales. Therefore, in our data‐rich world, what is lacking is a data management system across spatial and temporal resolutions including workflows, interpretation methodology, and a delivery structure for identifying optimal systems for sustainable intensification or diversification. Consequently, the objective of this paper is to explore the current state of handling spatially and temporally disparate data and offer solutions for developing a platform for bridging component parts (encompassing multiple scales and disciplines) to analyze system functionality for greater resiliency, which may help manage risk. Two datasets were generated using bibliometrics (research articles from systematic literature reviews) evaluated trends and historical Big Data applications in agronomy. Results indicate research and industry progress is advancing towards web‐based real‐time output delivery systems using several well‐established Big Data handling platforms (e.g., Amazon Web Service, Google Cloud, Microsoft Azure), which are not yet widely used by or designed for agronomic researchers. Cloud‐based computing may provide opportunities to extrapolate agricultural research results across larger scales. Authors suggest training and educating agricultural practitioners on Big Data principles, database management, improved data visualization, as well as incentives for data sharing for optimizing Big Data in systems agriculture as these research innovations emerge.

中文翻译：

---

系统农业中时空分布的数据：问题和解决方案

农业的大数据通过宏基因组学，精密农业和农场传感器技术的进步，以及通过增强的收集，处理和存储这些数据的能力而迅速增长。到2050年，粮食生产需求将增长60％，同时需要可持续集约化，与此同时，对跨时空尺度数据综合的需求也在增加。因此，在我们这个数据丰富的世界中，缺少的是跨时空分辨率的数据管理系统，包括工作流，解释方法以及用于确定可持续集约化或多样化的最佳系统的交付结构。所以，本文的目的是探讨处理空间和时间上分散的数据的当前状态，并提供解决方案，以开发一个平台来桥接组件（包括多个规模和学科），以分析系统功能以获得更大的弹性，这可能有助于管理风险。使用文献计量学（系统文献综述的研究文章）生成了两个数据集，用于评估趋势和农学中大数据的历史应用。结果表明，研究和行业进步正在朝着使用几个成熟的大数据处理平台（例如，Amazon Web Service，Google Cloud，Microsoft Azure）的基于Web的实时输出交付系统发展，这些平台尚未被广泛使用或设计。供农艺研究人员使用。基于云的计算可能会提供机会，以推断更大范围的农业研究成果。作者建议对农业从业人员进行大数据原理，数据库管理，改进的数据可视化以及随着这些研究创新而出现的数据共享激励，以优化系统农业中的大数据，对农业从业人员进行培训。