知识卡片
预报特征必须当时可得
用整季气象汇总预测整季产量时,要区分事后估计与提前预报。如果播种前尚不知道整季降雨和温度,不能把实际未来天气当作已知输入。验证应按真实预测时点组织特征,并区分观测值与天气预测值。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
Guntur district weather data and rice yield data from 1997 to 2014. Once preprocessing is completed, the dataset is split into 80:20. To anticipate crop yield production, we have to describe various attributes which indirectly or directly influence crop yield. The input variables of yield estimation are rainfall (mm), temperature (°C), sunshine (hours), and evapotranspiration (mm). The complete dataset structure is shown in Table 1.
参考来源
- 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第14章《水稻产量的个性化神经网络预测》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C14.html)
- 结论依据:摘录中关于预报特征必须当时可得的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:Guntur district weather data and rice yield data from 1997 to 2014. Once preprocessing is completed, the dataset is split into 80:20. To anticipate crop yield production, we have to describe various attributes which indirectly or directly influence crop yield. The input variables of yield estimation are rainfall (mm), temperature (°C), sunshine (hours), and evapotranspiration (mm). The complete dataset structure is shown in Table 1.