摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑-机器学习的最新研究结果已经发表。根据NewsRx记者在加州戴维斯的新闻报道，研究表明，“灌溉是全球淡水消耗最大的部分。决定合适的灌溉量对于可持续的水管理和粮食生产至关重要。”新闻记者从加州大学戴维斯分校的研究中引用了一句话，“Penman-Monteith(P-M)参考作物蒸散量(ETO)是灌溉管理和调度的黄金标准；然而，它的计算需要在扩展参考草地表面的多个传感器进行测量。为了应对这一挑战，本研究旨在开发一个输入受限的ETO估算应用程序Roach，该应用程序基于历史天气数据和机器学习(ML)算法，以满足对参考草地表面的需求。这种方法被称为“SolarET”。以太阳辐射(RS)数据为唯一输入数据。遥感是ETO唯一不依赖于测量面的气象驱动因子。为了测试SolarET的可变性，我们测试了它在加州各地看不见的任意位置的性能。由于加州是世界上水文变化最大、农业生产最多的地区之一，因此被选为案例研究。本研究使用了131个自动气象站的19088736个小时数据样本。ML模型在114个站点上进行了训练，在17个看不见的站点上进行了测试，每个站点代表了加州的气候区。结果表明基于决策树的算法相对于新网络的优越性。SolarET在加州以灌溉为导向的地区效果最好。中央山谷），在沿海和沙漠地区不太准确。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Machine Learn ing have been published. According to news reporting from Davis, California, by NewsRx journalists, research stated, “Irrigation is the most significant consume r of freshwater worldwide. Deciding on the right amount of irrigation is crucial for sustainable water management and food production.” The news correspondents obtained a quote from the research from the University o f California Davis, “The Penman-Monteith (P-M) reference crop evapotranspiration (ETO) is the gold standard in irrigation management and scheduling; however, it s calculation requires measurements from multiple sensors over an extended refer ence grass surface. The cost of land, sensors, maintenance, and water to keep th e grass surface green impedes having a dense network of ETO stations. To solve t his challenge, this research aims to develop an input-limited ETO estimation app roach based on historical weather data and machine learning (ML) algorithms to r elax the need for a reference grass surface. This approach, called ‘SolarET,’ ta kes solar radiation (RS) data as its sole input. RS is the only meteorological d riving factor of ETO that does not rely on the measuring surface. To test the ge neralizability of SolarET, we test its performance over unseen arbitrary locatio ns across California. California is chosen as the case study since it is one of the world’s most hydrologically altered and agriculturally productive regions. I n total, 19,088,736 hourly data samples from 131 automated weather stations have been used in this study. The ML models have been trained over 114 stations and tested over 17 unseen stations, each representing a California climatic zone. Ou r findings point to the superiority of decision tree-based algorithms versus neu ral networks. SolarET works best in irrigation-oriented regions of California (e .g., Central Valley) and is less accurate in coastal and desert zones.”
NETL
NSTL