Intelligent irrigation management using machine learning, sensors, and crop models

为了应对全世界日益严重的缺水和粮食需求，农业需要增加产量，同时尽量减少对有限淡水资源的压力。在这种情况下，该项目的总体目标是评估和开发新的机器学习和人工智能技术，以支持下一代实时灌溉决策支持工具。通过该项目将探讨三个关键的研究问题：（1）相对于现有的基于规则的灌溉调度，采用自适应实时灌溉控制系统对农民有什么好处（减少用水量，提高作物产量，提高利润）？(2)哪种类型的观测或预测数据对灌溉决策的有效实时优化最有用？(3)如何使用机器学习和人工智能来支持这些技术和方法在现实世界的农业系统中的可扩展应用和吸收？

In response to growing water scarcity and food demands worldwide, there is a need for agriculture to increase production while minimizing pressure on limited freshwater resources. In this context, the overall aim of this project is to evaluate and develop novel machine-learning and artificial intelligence techniques to support the next-generation of real-time irrigation decision support tools. Three key research questions will be explored through the project: (1) What are the gains for farmers (water use reductions, improved crop yields, higher profits) from adoption of adaptive real-time irrigation control systems relative to existing rule-based irrigation scheduling? (2) Which types of observation or forecast data are most useful for efficient real-time optimization of irrigation decision-making? (3) How can machine learning and artificial intelligence be used to support scalable application and uptake of these technologies and methods in real-world farming systems?