Accurate estimation of crop evapotranspiration (ET) is essential for the efficient utilization of agricultural water resources, crop production enhancement, and sustainable agricultural development. However, direct measurement of ET is highly expensive, intricate, and time-consuming, highlighting the imperative of establishing a novel model to accurately estimate ET in agricultural ecosystems. To address the above problems, this study proposed a novel model (GWA-CNN-BiLSTM), which incorporates Grey Wolf Algorithm (GWA), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory network (BiLSTM) as a hyperparameter adjuster, feature extractor, and regression component, respectively, to estimate ET built upon various input combinations comprising net solar radiation (R), vapor pressure deficit (VPD), average air temperature (T), soil water content (SWC), and leaf area index (LAI) about winter wheat-spring maize rotation system during 2012–2020 in the Loess Plateau. Besides, following a comparative assessment within GWA-CNN-BiLSTM, Convolutional Bidirectional Long Short-Term Memory network (CNN-BiLSTM), BiLSTM, Long Short-Term Memory network (LSTM), and Shuttleworth-Wallace (SW) models, the results revealed that GWA-CNN-BiLSTM under varied inputs obtained the superior performance, ranging from 0.562 to 0.957 in determination coefficient (R), 8.4–41.5 % in relative root mean square error (RRMSE), 0.349 mm d to 1.521 mm d in mean absolute error (MAE), −3.26 % to 14.11 % in percent bias (PBIAS), and 0.820–1.091 in regression coefficient (b), respectively. Moreover, while the accuracy of BiLSTM over LSTM was evident, its performance was notably improved by the incorporation of the CNN module. Additionally, LSTM-type models under complete input combination present better precision than SW by 29.7−51.4 % in R, 44.2−76.1 % in RRMSE, and 33.6−63.4 % in MAE, respectively. Furthermore, the accuracy of all models under varied inputs exhibited excellence in winter wheat compared to spring maize, and corresponding improvements ranged 1.4−4.3 % in R, 5.1−20.1 % in RRMSE, and 3.1−17.9 % in MAE, respectively. Besides, the meteorological factors (R, VPD, T) proved to be the most important inputs for ET estimation in winter wheat and spring maize. Wherein the importance of SWC exceeded that of LAI in winter wheat, while the opposite trend was observed in spring maize. In brief, GWA-CNN-BiLSTM is the highly recommended model to estimate ET of winter wheat-spring maize rotation system under diverse input data scenarios in the Loess Plateau, which can facilitate to offer valuable assistance in regional agriculture water management decisions.

中文翻译：

---

灰狼算法混合卷积双向长短期记忆网络估算黄土高原地区小麦-玉米轮作系统作物蒸散量


准确估算农作物蒸散量（ET）对于农业水资源的高效利用、农作物增产和农业可持续发展至关重要。然而，直接测量蒸散量非常昂贵、复杂且耗时，这凸显了建立一种新模型来准确估计农业生态系统中蒸散量的必要性。为了解决上述问题，本研究提出了一种新颖的模型（GWA-CNN-BiLSTM），该模型结合了灰狼算法（GWA）、卷积神经网络（CNN）和双向长短期记忆网络（BiLSTM）作为超参数分别是调整器、特征提取器和回归组件，用于根据各种输入组合（包括净太阳辐射 (R)、蒸气压赤字 (VPD)、平均气温 (T)、土壤含水量 (SWC) 和叶子）估计 ET黄土高原2012-2020年冬小麦-春玉米轮作制度面积指数(LAI)此外，经过对 GWA-CNN-BiLSTM、卷积双向长短期记忆网络 (CNN-BiLSTM)、BiLSTM、长短期记忆网络 (LSTM) 和 Shuttleworth-Wallace (SW) 模型的比较评估，结果研究表明，GWA-CNN-BiLSTM 在不同输入下获得了优异的性能，决定系数（R）为 0.562 至 0.957，相对均方根误差（RRMSE）为 8.4-41.5%，平均值为 0.349 mm d 至 1.521 mm d绝对误差 (MAE)、偏倚百分比 (PBIAS) 分别为 -3.26% 至 14.11%，回归系数 (b) 分别为 0.820–1.091。此外，虽然 BiLSTM 相对于 LSTM 的准确性是显而易见的，但通过加入 CNN 模块，其性能显着提高。 此外，在完整输入组合下，LSTM 型模型在 R 中的精度比 SW 好 29.7−51.4%，在 RRMSE 中比 SW 好 44.2−76.1%，在 MAE 中比 SW 好 33.6−63.4%。此外，与春玉米相比，不同投入条件下所有模型的准确性在冬小麦中表现出优异的表现，R 中的相应改进范围为 1.4−4.3%，RRMSE 中为 5.1−20.1%，MAE 中为 3.1−17.9%。此外，气象因素（R、VPD、T）被证明是冬小麦和春玉米蒸散发估算的最重要输入。其中冬小麦中SWC的重要性超过LAI，而春玉米中则相反。简而言之，GWA-CNN-BiLSTM是强烈推荐的模型，用于估算黄土高原地区不同输入数据场景下冬小麦-春玉米轮作系统的ET，可以为区域农业用水管理决策提供有价值的帮助。