Blue water (BW) and green water (GW) are crucial components of the hydrological cycle, but their accurate simulation and interpretation remain challenging in data-scarce basins. We propose the SWAT-ELM-SHAP model, coupling the Soil and Water Assessment Tool (SWAT), Ensemble Learning Model (ELM), and Shapley Additive Explanations (SHAP) method. This novel approach bridges the gap between a physically-based hydrological model, a data-driven machine learning (ML) model, and a holistically-interpreted SHAP method, offering accurate blue-green water simulation and holistic result interpretation for improved water resources management in data-scarce basins. We took the transfer simulation of blue-green water from the Xiangjiang River Basin (source basin) to the Zishui River Basin (target basin) as a case study to test and evaluate the feasibility of the coupled model during 1991–2022. The model performance results indicate that the simulation accuracy of our new coupled model is improved in data-scarce basins. In combination with hydrological response features generated by SWAT and meteorological features as the ELM input, our model enhances the daily blue-green water simulation. The Nash-Sutcliffe Efficiency coefficient (NSE) for BW, Green water flow (GWF), and Green water storage (GWS) consistently exceeds 0.77 during the calibration period (1991–2010) and exceeds 0.8 during the testing period (2011–2022). The interpretation results of coupled model demonstrate that SHAP holistic interpretation provides good interpretability for blue-green water simulation results in data-scarce basins. In general, the SWAT-ELM-SHAP offers a referenced approach that can reliably and efficiently simulate blue-green water in data-scarce basins, but more importantly, can further our understanding of the potential causal relationships, influence mechanisms, and variation mechanisms of blue-green water under changing environmental conditions.

中文翻译：

---

弥合差距：用于数据稀缺流域蓝绿水模拟的可解释耦合模型 （SWAT-ELM-SHAP）


蓝水 （BW） 和绿水 （GW） 是水文循环的重要组成部分，但在数据稀缺的流域中，它们的准确模拟和解释仍然具有挑战性。我们提出了 SWAT-ELM-SHAP 模型，耦合了土壤和水评估工具 （SWAT）、集成学习模型 （ELM） 和 Shapley 加法解释 （SHAP） 方法。这种新颖的方法弥合了基于物理的水文模型、数据驱动的机器学习 （ML） 模型和整体解释的 SHAP 方法之间的差距，提供准确的蓝绿水模拟和整体结果解释，以改善数据稀缺流域的水资源管理。本文以湘江流域（源流域）向湄水河流域（目标流域）的蓝绿水转移模拟为案例研究，对 1991—2022 年耦合模式的可行性进行了检验和评价。模型性能结果表明，在数据稀缺的流域中，我们新的耦合模型的模拟精度得到了提高。结合 SWAT 生成的水文响应特征和作为 ELM 输入的气象特征，我们的模型增强了日常蓝绿水模拟。BW、绿水流 （GWF） 和绿水储存 （GWS） 的 Nash-Sutcliffe 效率系数 （NSE） 在校准期间（1991-2010 年）始终超过 0.77，在测试期间（2011-2022 年）超过 0.8。耦合模型的解释结果表明，SHAP整体解释为数据稀缺流域的蓝绿水模拟结果提供了良好的可解释性。 总的来说，SWAT-ELM-SHAP 提供了一种参考方法，可以可靠、有效地模拟数据稀缺流域中的蓝绿水，但更重要的是，可以进一步让我们了解蓝绿水在不断变化的环境条件下的潜在因果关系、影响机制和变化机制。