Evapotranspiration is a key component of the hydrologic cycle. Accurate short-, medium-, and long-term forecasts of actual evapotranspiration (ET_a) are crucial not only for quantifying the impacts of climate change on the water and energy balance, but also for real-time estimation of crop water demand and irrigation water allocation in agriculture. Despite considerable advances in satellite remote sensing technology and the availability of long ground-measured and remotely sensed ET_a timeseries, real-time ET_a forecasts are deficient. Applying a state-of-the-art deep learning (DL) approach, Long Short-Term Memory (LSTM) models were employed to nowcast (real-time) and forecast (ahead of time) ET_a based on (1) major meteorological and ground-measured (i.e., soil moisture) input variables and (2) long ET_a timeseries from the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard of the NASA Aqua satellite. The conventional LSTM and convolutional LSTM (ConvLSTM) DL models were evaluated for seven distinct climatic zones across the contiguous United States. The employed LSTM and ConvLSTM models were trained and evaluated with data from the National Climate Assessment-Land Data Assimilation System (NCA-LDAS) and with MODIS/Aqua Net Evapotranspiration MYD16A2 product data. The obtained results indicate that when major atmospheric and soil moisture input variables are used for the conventional LSTM models, they yield accurate daily ET_a forecasts for short (1, 3, and 7 days) and medium (30 days) time scales, with normalized root mean squared errors (NRMSE) and Nash-Sutcliffe efficiencies (NSE) of less than 10% and greater than 0.77, respectively. At the watershed scale, the univariate ConvLSTM models yielded accurate weekly spatiotemporal ET_a forecasts (mean NRMSE less than 6.4% and NSE greater than 0.66) with higher computational efficiency for various climatic conditions. The employed models enable precise forecasts of both the current and future states of ET_a, which is crucial for understanding the impact of climate change on rapidly depleting water resources.

蒸散是水文循环的重要组成部分。_{对实际蒸散量 (ET a} ) 进行准确的短期、中期和长期预测不仅对于量化气候变化对水和能量平衡的影响至关重要，而且对于实时估计作物需水量和灌溉也至关重要农业用水分配。尽管卫星遥感技术取得了相当大的进步，并且可以获得长时间的地面测量和遥感 ET _a时间序列，但实时 ET _a预测仍然不足。应用最先进的深度学习 (DL) 方法，长短期记忆 (LSTM) 模型被用于临近预报（实时）和预测（提前）ET _a基于 (1) 主要气象和地面测量（即土壤水分）输入变量和 (2)来自 NASA Aqua 卫星的中分辨率成像光谱仪 (MODIS) 的_{长ET 时间序列。}针对美国毗连的七个不同气候区评估了传统的 LSTM 和卷积 LSTM (ConvLSTM) DL 模型。使用的 LSTM 和 ConvLSTM 模型使用来自国家气候评估-土地数据同化系统 (NCA-LDAS) 的数据和 MODIS/Aqua Net Evapotranspiration MYD16A2 产品数据进行了训练和评估。所得结果表明，当主要大气和土壤水分输入变量用于常规 LSTM 模型时，它们会产生准确的每日 ET _a短期（1、3 和 7 天）和中期（30 天）时间尺度的预测，归一化均方根误差 (NRMSE) 和纳什-萨特克利夫效率 (NSE) 分别小于 10% 和大于 0.77。在分水岭尺度上，单变量 ConvLSTM 模型产生了准确的每周时空 ET _a预测（平均 NRMSE 小于 6.4%，NSE 大于 0.66），在各种气候条件下具有更高的计算效率。_{所采用的模型能够精确预测 ET a}的当前和未来状态，这对于了解气候变化对迅速枯竭的水资源的影响至关重要。