地球物理

• 替换

查看 最近的 文章

显示 2025年07月25日， 星期五 新的列表

替换提交 (展示 1 之 1 条目 )

[1] arXiv:2507.18423 (替换) [中文pdf, pdf, 其他]

标题： 多模型集成与水库计算用于无观测流域的河流径流预测 显示英文标题

标题： Multi-Model Ensemble and Reservoir Computing for River Discharge Prediction in Ungauged Basins

Mizuki Funato, Yohei Sawada

主题： 机器学习 (cs.LG) ; 地球物理 (physics.geo-ph)

尽管准确的洪水预测和水资源管理至关重要，但许多地区缺乏足够的河流流量观测数据，这限制了降雨径流分析的技能。 虽然存在许多基于物理的和机器学习模型，能够在数据稀缺条件下实现高精度、可解释性和计算效率仍然是一个重大挑战。 我们通过一种新颖的方法 HYdrological Prediction with multi-model Ensemble and Reservoir computing (HYPER) 来解决这一挑战，该方法利用多模型集成和水库计算（RC）。 我们的方法首先对43个“未校准”的基于流域的概念水文模型应用贝叶斯模型平均（BMA）。 然后通过线性回归训练一个RC模型来校正BMA输出中的误差，这是一个非迭代过程，确保了高的计算效率。 对于无观测流域，我们通过将它们与有观测流域的流域属性联系起来来推断所需的BMA和RC权重，创建了一个可推广的框架。 我们使用日本87个河流流域的数据评估了HYPER。 在数据丰富的场景下，HYPER（中位数Kling-Gupta效率，KGE，为0.56）的表现与基准LSTM（KGE 0.55）相当，但仅需其5%的计算时间。 在数据稀缺场景下（23%的流域有观测），HYPER保持了稳健的表现（KGE 0.55）和较低的不确定性，而LSTM的表现显著下降（KGE -0.04）。 这些结果表明，当有效地构建大型集成并结合基于机器学习的偏差校正时，单个概念水文模型不一定需要校准。 HYPER为流量预测提供了一种稳健、高效且可推广的解决方案，特别是在无观测流域中，使其适用于广泛的区域。 显示英文摘要

Despite the critical need for accurate flood prediction and water management, many regions lack sufficient river discharge observations, limiting the skill of rainfall-runoff analyses. Although numerous physically based and machine learning models exist, achieving high accuracy, interpretability, and computational efficiency under data-scarce conditions remains a major challenge. We address this challenge with a novel method, HYdrological Prediction with multi-model Ensemble and Reservoir computing (HYPER) that leverages multi-model ensemble and reservoir computing (RC). Our approach first applies Bayesian model averaging (BMA) to 43 "uncalibrated" catchment-based conceptual hydrological models. An RC model is then trained via linear regression to correct errors in the BMA output, a non-iterative process that ensures high computational efficiency. For ungauged basins, we infer the required BMA and RC weights by linking them to catchment attributes from gauged basins, creating a generalizable framework. We evaluated HYPER using data from 87 river basins in Japan. In a data-rich scenario, HYPER (median Kling-Gupta Efficiency, KGE, of 0.56) performed comparably to a benchmark LSTM (KGE 0.55) but required only 5% of its computational time. In a data-scarce scenario (23% of basins gauged), HYPER maintained robust performance (KGE 0.55) and lower uncertainty, whereas the LSTM's performance degraded significantly (KGE -0.04). These results reveal that individual conceptual hydrological models do not necessarily need to be calibrated when an effectively large ensemble is assembled and combined with machine-learning-based bias correction. HYPER provides a robust, efficient, and generalizable solution for discharge prediction, particularly in ungauged basins, making it applicable to a wide range of regions.