摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-调查人员讨论机器学习的新发现。根据NewsRx记者从澳大利亚默多克发回的新闻报道，研究表明：“霜冻严重降低了全球小麦产量。小麦作物的温度发展是一个复杂而动态的过程。”这项研究的财政支持来自默多克大学数字农业连通性博士奖学金。新闻记者引用了默多克大学的一项研究:“在霜冻事件中,由于土壤和冠层边界的热量损失,从土壤到冠层的垂直温度梯度发展。了解Se温度梯度对于改进小麦霜冻管理策略至关重要。我们假设冠层温度与冠层温度之间的关系。”植物和地面可以作为霜冻的早期指标。我们采集了大田小麦作物的(IRT)热图像,提取了作物冠层、植物层和地面层的温度特征,分析了这些温度特征,并应用四种机器学习(ML)模型检测了不同严重程度霜冻夜的冷度等级。研究表明，在这三层中，温度之间存在一定的关系，可以用来判断霜冻的发生。霜冻夜这三层温度的变化规律不同于冬季寒冷的无霜夜，无霜夜的冠层最冷，植物最暖，土壤最暖。而这三种温度并没有接近。另一方面，在霜冻发生之前的一个霜夜，当冷空气进入冠层时，冠层和植物的温度趋于一致，这些温度分布模式被转化为一个ML问题，以便早期发现霜冻.根据一定严重程度的霜冻形成温度对冷度等级进行分类.结果表明，ML模型可以自动确定冷度等级，准确率为93%－98%.
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning. According to news reporting from Murdoch, Australia, by NewsRx journalists, research stated, "Frost damage significantly reduces global wheat production. Temperature development in wheat crops is a complex and dynamic proc ess." Financial support for this research came from Murdoch University Digital Agricul -ture Connectivity PhD scholarship. The news correspondents obtained a quote from the research from Murdoch Universi ty, "During frost events, a vertical temperature gradient develops from soil to canopy due to the heat loss from the soil and canopy boundary. Understanding the se temperature gradients is essential for improving frost management strategies in wheat crops. We hypothesise that the relationship between the temperatures of the canopy, plant and ground can be an early indicator of frost. We collected i nfrared thermal (IRT) images from fieldgrown wheat crops and extracted the temp eratures from the canopy, plant and ground layers. We analysed these temperature s and applied four machine learning (ML) models to detect coldness scales leadin g to frost nights with different degrees of severity. We implemented a gated rec urrent unit, convolutional neural network, random forest and support vector mach ines to evaluate the classification. Our study shows that in these three layers, temperatures have a relationship that can be used to determine frost early. The patterns of these three temperatures on a frost night differ from a cold no-fro st winter night. On a no-frost night we observed that the canopy is the coldest, plant is warm, and the soil is warmest, and these three temperatures did not co nverge. On the other hand, on a frost night, before the frost event, the canopy and plant temperatures converged as the cold air penetrated through the canopy. These patterns in temperature distribution were translated into an ML problem to detect frost early. We classified coldness scales based on the temperatures con ducive to frost formation of a certain severity degree. Our results show that th e ML models can determine the coldness scales automatically with 93% -98% accuracy across the four models."
NETL
NSTL