用卫星影像和机器学习精准估算水库储水量，提升干旱预警能力。
Satellite-Surface-Area Machine-Learning Models for Reservoir Storage Estimation: Regime-Sensitive Evaluation and Operational Deployment at Loskop Dam, South Africa
- 结合40年卫星数据与水位观测，构建分阶段的储水预测模型。
- 岭回归模型误差最低，达1230万立方米，优于其他算法16%以上。
- 推荐分场景使用不同模型，保障供水调度与干旱预警精度。
在半干旱地区，可靠的日度水库储水量估计对水资源分配和干旱应对至关重要。南非奥利芬茨河主要水库——洛斯科普大坝的传统水位-库容曲线因泥沙淤积和间歇性放水变得越来越不可靠。本文融合1984–2024年40年的数字非洲（DEA）地表面积档案与实测水位数据，构建了在90天最大放水约束下运行的数据驱动体积预测模型。评估了四组特征：原始水面面积、幂律计算的体积代理、六项河流几何指标及全库容高程。五种算法（梯度提升、随机森林、岭回归、套索、弹性网络）经20次随机搜索调参，并采用五折时间序列分割验证以避免前瞻偏差。预测误差按低（<250×10⁶ m³）与高（>250×10⁶ m³）储水阶段分解。岭回归交叉验证均方根误差最低（12.3×10⁶ m³），较梯度提升低16%，较随机森林低7%。在低储水段表现最优（18.0对比22.7 MCM），高储水段与随机森林持平（约12 MCM）。梯度提升看似优越（6.8–5.4 MCM）实为过拟合所致。最终采用岭回归元堆叠集成（含GB、RF、Ridge）将整体序列均方根误差降至约11 MCM（约活库容的3%）。建议：日常运营用每日重训的梯度提升；干旱预警用岭回归；所有气象仪表盘用堆叠模型。建议每季度滚动重训并采用分段指标，确保精度低于水务与卫生部要求的5%阈值。
原文摘要 · Abstract (English)
Reliable daily estimates of reservoir storage are pivotal for water allocation and drought response decisions in semiarid regions. Conventional rating curves at Loskop Dam, the primary storage on South Africa's Olifants River, have become increasingly uncertain owing to sedimentation and episodic drawdown. A 40 year Digital Earth Africa (DEA) surface area archive (1984-2024) fused with gauged water levels to develop data driven volume predictors that operate under a maximum 9.14%, a 90 day drawdown constraint. Four nested feature sets were examined: (i) raw water area, (ii) +a power law "calculated volume" proxy, (iii) +six river geometry metrics, and (iv) +full supply elevation. Five candidate algorithms, Gradient Boosting (GB), Random Forest (RF), Ridge (RI), Lasso (LA) and Elastic Net (EN), were tuned using a 20 draw random search and assessed with a five fold Timeseries Split to eliminate look ahead bias. Prediction errors were decomposed into two regimes: Low (<250 x 10^6 cubic meters) and High (>250 x 10^6 cubic meters) storage regimes. Ridge regression achieved the lowest cross validated RMSE (12.3 x 10^6 cubic meters), outperforming GB by 16% and RF by 7%. In regime terms, Ridge was superior in the Low band (18.0 ver. 22.7 MCM for GB) and tied RF in the High band (~12 MCM). In sample diagnostics showed GB's apparent dominance (6.8-5.4 MCM) to be an artefact of overfitting. A Ridge meta stacked ensemble combining GB, RF, and Ridge reduced full series RMSE to ~ 11 MCM (~ 3% of live capacity). We recommend (i) GB retrained daily for routine operations, (ii) Ridge for drought early warning, and (iii) the stacked blend for all weather dashboards. Quarterly rolling retraining and regime specific metrics are advised to maintain operational accuracy below the 5% threshold mandated by the Department of Water and Sanitation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。