The dataset described here includes estimates of historical (1980–2020) daily surface water temperature, lake metadata, and daily weather conditions for lakes bigger than 4 ha in the conterminous United States (n = 185,549), and also in situ temperature observations for a subset of lakes (n = 12,227). Estimates were generated using a long short-term memory deep learning model and compared to existing process-based and linear regression models. Model training was optimized for prediction on unmonitored lakes through cross-validation that held out lakes to assess generalizability and estimate error. On the held-out lakes with in situ observations, median lake-specific error was 1.24°C, and the overall root mean squared error was 1.61°C. This dataset increases the number of lakes with daily temperature predictions when compared to existing datasets, as well as substantially improves predictive accuracy compared to a prior empirical model and a debiased process-based approach (2.01°C and 1.79°C median error, respectively).

中文翻译：

---

使用深度学习估算的美国本土 185,549 个湖泊的每日表面温度（1980-2020 年）

此处描述的数据集包括对美国本土 ( n = 185,549)大于 4 公顷的湖泊的历史（1980-2020 年）每日地表水温、湖泊元数据和每日天气状况的 估计，以及对湖泊子集 ( n = 12,227)。估计是使用长期短期记忆深度学习模型生成的，并与现有的基于过程的线性回归模型进行比较。通过交叉验证对模型训练进行了优化，以预测未受监控的湖泊，该交叉验证支持湖泊评估泛化性和估计误差。在进行实地观测的保留湖泊中，特定湖泊误差中位数为 1.24°C，总体均方根误差为 1.61°C。与现有数据集相比，该数据集增加了具有每日温度预测的湖泊数量，并且与先前的经验模型和基于去偏过程的方法（分别为 2.01°C 和 1.79°C 中值误差）相比，大大提高了预测准确性.