Understanding and predicting global soil moisture (SM) is crucial for water resource management and agricultural production. While deep learning methods (DL) have shown strong performance in SM prediction, imbalances in training samples with different characteristics pose a significant challenge. We propose that improving the diversity and balance of batch training samples during gradient descent can help address this issue. To test this hypothesis, we developed a Cluster-Averaged Sampling (CAS) strategy utilizing unsupervised learning techniques. This approach involves training the model with evenly sampled data from different clusters, ensuring both sample diversity and numerical consistency within each cluster. This approach prevents the model from overemphasizing specific sample characteristics, leading to more balanced feature learning. Experiments using the LandBench1.0 dataset with five different seeds for 1-day lead-time global predictions reveal that CAS outperforms several Long Short-Term Memory (LSTM)-based models that do not employ this strategy. The median Coefficient of Determination (R2) improved by 2.36 % to 4.31 %, while Kling-Gupta Efficiency (KGE) improved by 1.95 % to 3.16 %. In high-latitude areas, R2 improvements exceeded 40 % in specific regions. To further validate CAS under realistic conditions, we tested it using the Soil Moisture Active and Passive Level 3 (SMAP-L3) satellite data for 1 to 3-day lead-time global predictions, confirming its efficacy. The study substantiates the CAS strategy and introduces a novel training method for enhancing the generalization of DL models.

中文翻译：

---

通过聚类平均采样策略改进全球土壤水分预测


了解和预测全球土壤湿度 （SM） 对于水资源管理和农业生产至关重要。虽然深度学习方法 （DL） 在 SM 预测方面表现出强大的性能，但具有不同特征的训练样本的不平衡构成了重大挑战。我们建议，在梯度下降过程中改善批量训练样本的多样性和平衡性可以帮助解决这个问题。为了验证这一假设，我们开发了一种利用无监督学习技术的整群平均采样 （CAS） 策略。这种方法涉及使用来自不同集群的均匀采样数据来训练模型，从而确保每个集群内的样本多样性和数值一致性。这种方法可以防止模型过分强调特定的样本特征，从而实现更平衡的特征学习。使用 LandBench1.0 数据集和五个不同的种子进行 1 天提前期全局预测的实验表明，CAS 优于几个不采用此策略的基于长短期记忆 （LSTM） 的模型。决定系数 （R2） 中位数提高了 2.36 % 至 4.31 %，而 Kling-Gupta 效率 （KGE） 提高了 1.95 % 至 3.16 %。在高纬度地区，特定区域的 R2 改进超过 40%。为了在现实条件下进一步验证 CAS，我们使用土壤水分主动和被动 3 级 （SMAP-L3） 卫星数据对其进行了 1 到 3 天提前期全球预测，证实了其有效性。该研究证实了 CAS 策略，并引入了一种新的训练方法来增强 DL 模型的泛化。