Bayesian convolutional neural networks for predicting the terrestrial water storage anomalies during GRACE and GRACE-FO gap
Bayesian convolutional neural networks for predicting the terrestrial water storage anomalies during GRACE and GRACE-FO gap
复制标题
用于预测 GRACE 和 GRACE-FO 间隙期间陆地水储量异常的贝叶斯卷积神经网络
DOI：
10.1016/j.jhydrol.2021.127244
复制
发表时间：
2022
影响因子：
6.4
通讯作者：
André Revil
中科院分区：
文献类型：
--
作者：
Shaoxing Mo;Yulong Zhong;Ehsan Forootan;Nooshin Mehrnegar;Xin Yin;Jichun Wu;Wei Feng;André Revil
·提出了一种贝叶斯卷积神经网络来重建GRACE和GRACE-FO间隙期间的TWSA信号。贝叶斯训练策略能够量化预测的不确定性。·与以前的研究相比，获得了明显改善的间隙填充性能。·改进后的加密产品可以可靠地保持数据的连续性，增强数据的一致性。重力恢复与气候实验（GRACE）卫星与其后续卫星（GRACE-FO）之间差距期间的月地面水储量异常（TWSA）观测数据缺失，导致时间序列的不连续性，从而阻碍了数据的充分利用和分析。尽管先前已努力解决此问题，但仍缺乏在全球范围内具有所需准确度的填补空白的TWSA产品。在这项研究中，提出了一个简单的水文气候数据驱动的贝叶斯卷积神经网络（BCNN）来弥合这一差距。受益于BCNN在处理图像数据方面的出色能力以及最新深度学习进展（包括残差跳过连接和空间通道注意力）的集成，所提出的方法可以从多个预测数据中自动提取用于TWSA预测的信息特征。BCNN预测与重新分析/模拟TWSA，Swarm解决方案，以及最近三项研究产生的TWSA预测产品进行了比较，使用常用的准确性指标。结果表明，BCNN的上级性能，以获得更高质量的TWSA预测，特别是在相对干旱的地区。此外，在流域尺度上与两个独立数据集的比较进一步表明，BCNN填充的TWSA是可靠的，以弥合差距，提高数据的一致性。我们的填补空白产品最终有助于纠正长期趋势估计中的偏差，保持TWSA时间序列的连续性，从而有利于后续需要连续数据记录的应用。
• A Bayesian convolutional neural network is proposed to reconstruct the TWSA signals during GRACE and GRACE-FO gap. • The Bayesian training strategy enables the quantification of predictive uncertainties. • A clearly improved gap-filling performance is obtained in comparison with previous studies. • The improved infilling product can reliably maintain the data continuity and enhance data consistency. The monthly terrestrial water storage anomaly (TWSA) observations during the gap period between the Gravity Recovery and Climate Experiment (GRACE) satellite and its Follow-On (GRACE-FO) are missing, leading to discontinuity in the time series, and thus, impeding full utilization and analysis of the data. Despite previous efforts undertaken to tackle this issue, a gap-filling TWSA product with desirable accuracy at a global scale is still lacking. In this study, a straightforward and hydroclimatic data-driven Bayesian convolutional neural network (BCNN) is proposed to bridge this gap. Benefiting from the excellent capability of BCNN in handling image data and the integration of recent deep learning advances (including residual-skip connections and spatial-channel attentions), the proposed method can automatically extract informative features for TWSA predictions from multiple predictor data. The BCNN predictions are compared with reanalyzed/simulated TWSA, Swarm solution, and the TWSA prediction products generated by three recent studies, using commonly used accuracy metrics. Results demonstrate BCNN’s superior performance to obtain higher-quality TWSA predictions, particularly in relatively arid regions. Additionally, a comparison with two independent datasets at the basin scale further suggests that the BCNN-infilled TWSA is reliable to bridge the gap and enhance data consistency. Our gap-filling product can ultimately contribute to correcting the bias in long-term trend estimates, maintaining the continuity of TWSA time series and thus benefiting subsequent applications desiring continuous data records.