摘要
由一名新闻记者兼机器人与机器学习的工作人员新闻编辑每日新闻-关于机器学习的详细数据已经呈现。根据NewsRx编辑对南非开普敦的新闻报道，研究称：“本研究的主要目的是评估Sentinel 2和机器学习技术对南非阿古拉斯角Heun Ingnes集水区季节性土地利用覆被(LULC)年变化进行分类的有效性。该研究集中在2017年7月、2017年10月和2018年3月。2018年7月，代表集水区的旱季和雨季。我们的新闻记者引用了西开普大学的研究，“该研究还评估了降雨和温度变化以及它们与LULC短期变化的联系。分类结果显示，2017年10月至2018年7月裸岩和土壤覆盖范围持续增加。2017年7月和2018年7月的雨季植被覆盖百分比最高。SVM分类的总体精度介于用Kappa统计量对支持向量机的性能进行了评价，结果表明，在0.43～0.69.之间有中等到相当程度的一致性。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on Machine Learning have been presented. According to news reporting out of Cape Town, South Africa, by NewsRx editors, research stated, “The primary objective of this study was to eva luate the effectiveness of Sentinel 2 and machine-learning technique for classif ying seasonal land use land cover (LULC) changes on an annual basis, in the Heun ingnes Catchment in Cape Agulhas, South Africa. The study focused on July 2017, October 2017, March 2018, and July 2018, representing both dry and wet seasons w ithin the Catchment.” Our news journalists obtained a quote from the research from the University of t he Western Cape, “The study also assessed the rainfall and temperature variation s and how they link with these short-term changes in LULC. The classification re sults revealed a consistent increase in the extent of bare rock and soil cover f rom October 2017 to July 2018. The wet seasons of July 2017 and July 2018 exhibi ted the highest percentage of vegetation cover. The overall accuracy of the SVM classification ranged between 55 % and 75 %, with the wet seasons demonstrating higher overall accuracies of 75 %. The p erformance of SVM was evaluated using kappa statistics, which indicated a modera te to substantial level of agreement ranging from 0.43 to 0.69.”
NETL
NSTL