发表机构
University of Texas at San Antonio; Jodhpur Institute of Engineering and Technology; Edwards Aquifer Authority（德克萨斯大学圣安东尼奥分校; 焦特布尔工程技术学院; 爱德华兹含水层管理局）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一个智能体AI框架，利用简约机器学习模型（以极端梯度提升为最优）对岩溶含水层进行1-12周预测，实现高精度和可审计的自动化操作。
AI 中文摘要
岩溶含水层动态预测具有挑战性，因为补给响应是非线性的、事件驱动的，并受高度异质性的流动路径控制。本研究开发并评估了一个面向部署的框架，用于基于德克萨斯州爱德华兹含水层约79年的水文气候观测数据，进行1至12周前的泉水流量和地下水位预测。在统一的时间评估设计下比较了五种模型族：极端梯度提升、极度随机树、长短期记忆网络、卷积神经网络和Transformer。预测结果使用决定系数、Kling-Gupta效率、均方根误差以及与运营干旱阈值的吻合度进行评估。极端梯度提升始终最为可靠，在1-4周、5-8周和9-12周的时间尺度上，R²分别至少为0.97、0.96和0.94，并且在所有时间尺度上，前三个干旱阶段的临界阶段吻合度均大于90%。深度模型在短时间尺度上具有竞争力，但在较长提前期时性能逐渐下降，并出现孤立的失败。我们将这种对比归因于树分区与低维、轴对齐的水文气候预测因子之间的对齐，以及神经模型倾向于平滑不规则极值的特性。经过验证的模型被嵌入到一个五智能体操作架构中，该架构自动化了数据获取、模型分配、确定性预测、阈值监测、前瞻性验证、文献检索和报告。因此，本研究的贡献在于提供了一个可转移的框架，该框架结合了简约模型选择、泄漏感知的多时间尺度评估、决策相关的阈值技能以及可审计的智能体自动化。
英文摘要
Forecasting karst aquifer dynamics is difficult because recharge responses are nonlinear, event-driven, and governed by strongly heterogeneous flow paths. This study develops and evaluates a deployment-aware framework for 1-12-week-ahead prediction of spring discharge and groundwater level using approximately 79 years of hydroclimatic observations from the Edwards Aquifer, Texas. Five model families were compared under a common temporal evaluation design: extreme gradient boosting, extremely randomized trees, long short-term memory, convolutional neural networks, and Transformers. Predictions were evaluated using coefficient of determination, Kling-Gupta efficiency, root-mean-square error, and agreement with operational drought thresholds. Extreme gradient boosting was consistently most reliable, with R2 at least 0.97, 0.96, and 0.94 across 1-4-, 5-8-, and 9-12-week horizons, respectively, and greater than 90% critical-stage agreement at the first three drought stages across all horizons. Deep models were competitive at short horizons but degraded progressively and exhibited isolated failures at longer lead times. We attribute this contrast to an alignment between tree partitioning and low-dimensional, axis-aligned hydroclimatic predictors, together with the tendency of neural models to smooth irregular extremes. The validated models were embedded in a five-agent operational architecture that automates data acquisition, model assignment, deterministic prediction, threshold monitoring, prospective verification, literature retrieval, and reporting. The contribution is therefore a transferable framework joining parsimonious model selection, leakage-aware multi-horizon evaluation, decision-relevant threshold skill, and auditable agentic automation.
