
Medium and Long term Runoff Forecasting and Uncertainty Analysis for the Three Gorges Reservoir
Hua-ping HUANG, Yu-jie LI, Dong WANG, Gao-yang JIN
Medium and Long term Runoff Forecasting and Uncertainty Analysis for the Three Gorges Reservoir
In this paper, the Lightweight Gradient Boosting Tree Model (LGB) is employed to simulate and forecast monthly runoff sequences of the Three Gorges Reservoir, and the forecasting uncertainties are analyzed by using the Hydrological Uncertainty Processor (HUP). The findings of this paper are as follows: ① the comparison between predictions of GBDT and LGB models indicates that the LGB model has higher accuracy than the GBDT model for both calibration and validation periods; ② the preferred forecasts (Q50 values) generated by the HUP model present a higher accuracy than the deterministic prediction generated by the LGB model, especially for the flood season; ③ the 90% uncertainty confidence interval with a narrow bandwidth for both calibration and validation periods can cover most observed points, which suggests that the result of uncertainty analysis is accurate and reasonable.
Three Gorges Reservoir / medium and long term forecasting / LGB model / hydrological uncertainty processor / uncertainty analysis {{custom_keyword}} /
Tab.1 Selected predictors for two typical months (January and August)表1 典型月份对应预测因子统计表 |
1月预测因子(相关系数) | 8月预测因子(相关系数) |
---|---|
前一年11月印度洋暖池强度指数(0.57) | 前一年11月欧亚纬向环流指数(0.47) |
前一年10月热带印度洋全区一致海温模态指数(0.56) | 当年7月径流量(0.46) |
前一年8月东大西洋遥相关型指数(0.55) | 前一年8月全球综合角动量指数(0.46) |
前一年11月西半球暖池指数(0.54) | 前一年11月亚洲纬向环流指数(0.42) |
前一年10月大西洋多年代际振荡指数(0.54) | 当年2月西半球暖池指数(0.41) |
前一年4月西太平洋暖池强度指数(0.54) | 前一年11月热带印度洋海温偶极子指数(0.40) |
前一年6月北大西洋副高强度指数(0.52) | 前一年11月NINO1+2区海表温度距平指数(0.40) |
前一年5月北半球副高强度指数(0.52) | 当年6月北美区极涡面积指数(0.39) |
前一年10月印度洋暖池面积指数(0.51) | 当年4月50 hPa纬向风指数(0.37) |
前一年10月大西洋经向模海温指数(0.49) | 前一年10月北大西洋-欧洲区极涡强度指数(0.36) |
Fig.1 The observed and simulated monthly runoff series from 1965 to 2016 for the Three Gorges Reservoir图1 三峡水库1965-2016年逐月流量过程对比 |
Fig.2 Scatter plots of observed and predicted monthly runoff for the Three Gorges Reservoir图2 三峡水库实测与模拟月流量散点图 |
Tab.2 Performance Indices for the calibration and validation periods表2 模型率定期及验证期精度评价 |
模型 | 评价指标 | MAPE/% | CC | NSE |
---|---|---|---|---|
GBDT模型 | 率定期 | 16.1 | 0.91 | 0.84 |
验证期 | 25.8 | 0.89 | 0.71 | |
LGB模型 | 率定期 | 15.7 | 0.91 | 0.86 |
验证期 | 23.0 | 0.90 | 0.75 |
Tab.3 Performance Indices for the calibration and validation periods (Q50 predictions)表3 HUP模型率定期及验证期精度评价(Q50预报值) |
评价指标 | MAPE/% | CC | NSE |
---|---|---|---|
率定期 | 15.0 | 0.92 | 0.87 |
验证期 | 21.1 | 0.90 | 0.77 |
Fig.3 The observed runoff and Q50 values series for the Three Gorges Reservoir图3 三峡水库1965-2016年逐月流量观测系列与Q50系列对比图 |
Fig.5 Uncertainty analysis of the predicted monthly runoff sequences of the Three Gorges Reservoir图5 三峡水库月流量不确定性分析结果 |
Tab.4 Performance Indices for uncertainty confidence intervals表4 不确定性区间精度评价 |
指标 | 率定期 | 验证期 | ||||
---|---|---|---|---|---|---|
CR | RB | RD | CR | RB | RD | |
LGB-HUP | 0.86 | 0.58 | 0.16 | 0.83 | 0.64 | 0.22 |
1 |
李红波,夏潮军,王淑英.中长期径流预报研究进展及发展趋势[J].人民黄河,2012,34(8):36-38,40.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
刘甜,梁忠民,邱辉,等.基于CFS的汉江上游梯级水库系统月入库径流预测[J].水电能源科学,2019,37(8):14-17,10.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
夏军.中长期径流预报的一种灰关联模式识别与预测方法[J].水科学进展,1993(3):190-197.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
邢兰辉,吕惠萍,张锦辉. 周期叠加方差分析法预报河川径流量[J].水文, 2007,27(4):41-44.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
钟平安,邴建平,赵星,等. 小波变换对中长期入库径流预测的适应性研究[J]. 水力发电, 2007(1):17-19,31.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
赵铜铁钢,杨大文,蔡喜明,等. 基于随机森林模型的长江上游枯水期径流预报研究[J]. 水力发电学报, 2012(3):20-26,40.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
岳兆新,艾萍,熊传圣,等.基于改进深度信念网络模型的中长期径流预测[J].水力发电学报,2020,39(10):33-46.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |