Simulation of Phosphorus Inflow and Outflow Fluxes and Water Quality Prediction in Dongting Lake Area of the Yangtze River Basin: A Coupled Approach of Machine Learning and Traditional Hydrological Modeling
-
摘要: 磷通量的波动对出入湖河流生态系统的稳定有直接影响.在水质波动显著的洞庭湖区，使用SWAT模型模拟该区域的出入湖磷通量，并分析各水系区间的磷滞留情况.基于水文物理过程搭建耦合模型，再利用SWAT模型的模拟结果进行训练，并利用该模型对湖区近期水质进行情景预测.结果表明：洞庭湖区出入湖磷通量均呈明显的季节变化，其中无机磷是主要的磷形态.2012—2021年洞庭湖区平均TP入湖通量为2.94×104 t/a，平均出湖TP通量为3.34×104 t/a，平均出湖TP浓度为0.13 mg/L.其中，三口区间作为入湖磷通量贡献最大的区间，其TP输出浓度也最高，是污染治理的关键区域.洞庭湖区TP滞留率较低，使其成为长江下游重要的TP来源.耦合模型对于洞庭湖区的出入磷通量的输出过程模拟效果良好，NSE值均 > 0.8，在RPE值处于10%水平下的RMSE值均较低，实现了LSTM网络替代大型分布式物理模型的仿真建模.基于上述模型根据《洞庭湖水环境综合治理规划》对洞庭湖近期TP输出浓度进行了预测，在各区间入湖TP浓度控制在0.1 mg/L的情景下，能够实现湖区水环境规划目标.Abstract: Fluctuations in phosphorus fluxes to and from the lake have a direct impact on the stability of river ecosystems. In the Dongting Lake area, where water quality fluctuates, the SWAT model was used to simulate the phosphorus inflow and outflow fluxes and to analyze the retention rate in each area. A coupled model was constructed based on hydrophysical processes, being trained by the results of the SWAT model and using the model to make scenario predictions of recent water quality in the lake area. The results showed that the inflow and outflow phosphorus fluxes in Dongting Lake showed obvious seasonal variations, with inorganic phosphorus being the main phosphorus format. From 2012 to 2021, the average TP inflow flux in Dongting Lake was 2.94×104 t/a, the average TP outflow flux was 3.34×104 t/a, and the average TP outflow concentration was 0.13 mg/L. Among the sub-basins, the Sankou area as the area with the largest contribution of phosphorus flux into the lake and the highest TP output concentration, should be emphasized to manage the phosphorus pollution in this area. The low TP retention rate in the Dongting Lake area may turn it into an important source of TP in the lower reaches of the Yangtze River. Coupled modeling is relatively precise for simulating the output process of river phosphorus fluxes, with all NSE values > 0.8, and all RMSE values are low at the RPE value at 10% level, which realizes the simulation modeling of the LSTM network instead of the large-scale distributed physical model.Based on the above model, the recent TP output concentration of Dongting Lake area was predicted according to the "Dongting Lake Water Environment Comprehensive Management Plan", and the scenario of controlling the TP concentration inflow into the lake in each area at 0.1 mg/L can realize the water environment planning objectives of the lake area.
-
图 3 耦合模型基本搭建过程和子流域尺度验证结果
Fig. 3. Basic construction process of the coupled model and sub-basin scale validation results
图 4 洞庭湖区出入湖磷通量及组分的年际变化与回归分析
Fig. 4. Inter-annual variation and regression analysis of phosphorus fluxes and fractions in Dongting Lake area
图 5 洞庭湖区出入湖磷通量年内变化及其特征
Fig. 5. Inter-annual variation of TP outflow concentration and linear regression analysis of phosphorus fluxes in Dongting Lake area
图 6 洞庭湖区入湖磷通量及其浓度的空间特征
Fig. 6. Spatial characteristics of phosphorus flux and TP concentrations into the lake in Dongting Lake area
图 7 耦合模型对三口区间流量、泥沙输出量和TP入湖量的预测结果
Fig. 7. The prediction results of the coupling model for the flow, sediment output and TP inflow in the Sankou area
图 8 耦合模型对洞庭湖区TP出湖量的预测结果
Fig. 8. The prediction results of the coupling model on the amount of TP outflow in the Dongting Lake area
图 9 综合治理目标下洞庭湖出口TP输出浓度的年内变化
Fig. 9. Intra-annual variation of TP output concentrations at the outlet of Dongting Lake under comprehensive treatment target
表 1 洞庭湖区SWAT模型的率定结果
Table 1. Calibration and validation results of SWAT model in Dongting Lake area
流量率定结果 泥沙率定结果 水质率定结果 水文站点 R2 NSE 水文站点 R2 NSE 水文站点 R2 NSE 伍市 0.84 0.80 伍市 0.80 0.74 小河咀 0.91 0.57 南县 0.92 0.67 南县 0.70 0.59 八仙桥 0.80 0.58 南咀 0.93 0.66 南咀 0.93 0.66 小河咀 0.96 0.87 小河咀 0.77 0.74 城陵矶 0.92 0.90 城陵矶 0.58 0.13 
下载: 导出CSV
表 2 洞庭湖区河道磷通量的滞留情况
Table 2. Retention of river phosphorus fluxes in the Dongting Lake area
水系区间 面积（km2） TP入河量（104t） TP滞留量（104t） TP滞留率（%） 三口区间 10 146.83 1.87 1.20 54.6 澧水区间 787.00 0.22 0.04 14.9 沅江区间 2 513.83 0.32 0.11 19.1 资水区间 2 200.40 0.38 0.08 15.2 湘江区间 538.14 0.10 0.06 14.2 汨罗江流域 5 236.27 0.41 0.25 60.3 新墙河流域 2597.23 0.36 0.21 57.5 洞庭湖区间 2 951.85 3.89 1.67 33.3
下载: 导出CSV
表 3 洞庭湖区入湖磷通量耦合模拟的效果评价
Table 3. Evaluation of the effectiveness of coupled modeling of phosphorus fluxes into lakes in Dongting Lake area
水系区间 径流输出量 泥沙输出量 入湖磷通量 RMSE RPE(%) NSE RMSE RPE(%) NSE RMSE RPE(%) NSE 三口区间 1.49 1.8 0.99 1.46 2.8 0.99 0.33 5.5 0.92 澧水区间 0.68 3.4 0.95 1.03 4.5 0.89 0.16 5.3 0.92 沅江区间 0.08 1.1 0.99 0.26 1.9 0.99 0.98 5.9 0.87 资水区间 0.05 2.9 0.98 0.05 3.4 0.97 0.73 7.3 0.86 湘江区间 0.17 2.2 0.98 0.58 5.3 0.90 0.91 6.6 0.84 汨罗江流域 0.20 5.4 0.94 0.15 5.6 0.91 1.00 10.2 0.92 新墙河流域 0.11 6.2 0.92 0.10 6.2 0.84 0.36 6.5 0.92
下载: 导出CSV
-
Adu, J., Kumarasamy, M. V., 2018. Assessing Non-Point Source Pollution Models: A Review. Polish Journal of Environmental Studies, 27(5): 1913-1922. https://doi.org/10.15244/pjoes/76497 Billen, G., Garnier, J., 1997. The Phison River Plume: Coastal Eutrophication in Response to Changes in Land Use and Water Management in the Watershed. Aquatic Microbial Ecology, 13: 3-17. https://doi.org/10.3354/ame013003 Brown, L. C., Barnwell, T. O., 1987. The Enhanced Stream Water Quality Models QUAL2E and QUAL2E-UNCAS Documentation and User Manual. Environmental Protection Agency, GA, Athens. Chen, C., Zhang, H., Shi, W. X., et al., 2023a. A Novel Paradigm for Integrating Physics-Based Numerical and Machine Learning Models: A Case Study of Eco- Hydrological Model. Environmental Modelling & Software, 163: 105669. https://doi.org/10.1016/j.envsoft.2023.105669 Chen, S. Y., Huang, J. L., Huang, J. C., 2023b. Improving Daily Streamflow Simulations for Data-Scarce Watersheds Using the Coupled SWAT-LSTM Approach. Journal of Hydrology, 622: 129734. https://doi.org/10.1016/j.jhydrol.2023.129734 Elsbury, K. E., Paytan, A., Ostrom, N. E., et al., 2009. Using Oxygen Isotopes of Phosphate to Trace Phosphorus Sources and Cycling in Lake Erie. Environmental Science & Technology, 43(9): 3108-3114. https://doi.org/10.1021/es8034126 Fergus, C. E., Brooks, J. R., Kaufmann, P. R., et al., 2020. Lake Water Levels and Associated Hydrologic Characteristics in the Conterminous U. S., Journal of the American Water Resources Association, 56(3): 450-471. https://doi.org/10.1111/1752-1688.12817 Geng, M. M., Li, F., Gao, Y., et al., 2021a. Wetland Area Change from 1986-2016 in the Dongting Lake Watershed at the Sub-Watershed Scale. Polish Journal of Environmental Studies, 30(2): 1611-1620. https://doi.org/10.15244/pjoes/127268 Geng, M. M., Wang, K. L., Yang, N., et al., 2021b. Spatiotemporal Water Quality Variations and Their Relationship with Hydrological Conditions in Dongting Lake after the Operation of the Three Gorges Dam, China. Journal of Cleaner Production, 283: 124644. https://doi.org/10.1016/j.jclepro.2020.124644 Geng, M. M., Wang, K. L., Qian, Z., et al., 2023. Is Water Resources Management at the Expense of Deteriorating Water Quality in a Large River-Connected Lake after the Construction of a Lake Sluice?. Ecological Engineering, 197: 107124. https://doi.org/10.1016/j.ecoleng.2023.107124 He, Q. H., Yu, D. Q., Yu, S. C., et al., 2021. Changes of Water Resources Amount in Dongting Lake before and after the Operation of the Three Gorges Reservoir. Earth Science, 46(1): 293-307 (in Chinese with English abstract). Hong, B., Swaney, D. P., McCrackin, M., et al., 2017. Advances in NANI and NAPI Accounting for the Baltic Drainage Basin: Spatial and Temporal Trends and Relationships to Watershed TN and TP Fluxes. Biogeochemistry, 133(3): 245-261. https://doi.org/10.1007/s10533-017-0330-0 Hu, G. W., Liang, Y. W., Zhuang, S. Q., et al., 2023. Spatial-Temporal Variation of Agricultural Non-Point Source Pollution Emission in Dongting Lake Basin. Environmental Ecology, 5(3): 59-65 (in Chinese with English abstract). Hu, T. F., Mao, J. Q., Pan, S. Q., et al., 2018. Water Level Management of Lakes Connected to Regulated Rivers: An Integrated Modeling and Analytical Methodology. Journal of Hydrology, 562: 796-808. https://doi.org/10.1016/j.jhydrol.2018.05.038 Huang, R. X., Ma, C. X., Ma, J., et al., 2021. Machine Learning in Natural and Engineered Water Systems. Water Research, 205: 117666. https://doi.org/10.1016/j.watres.2021.117666 Huo, S. L., Ma, C. Z., Li, W. P., et al., 2023. Spatiotemporal Differences in Riverine Nitrogen and Phosphorus Fluxes and Associated Drivers across China from 1980 to 2018. Chemosphere, 310: 136827. https://doi.org/10.1016/j.chemosphere.2022.136827 Karpatne, A., Ebert-Uphoff, I., Ravela, S., et al., 2019. Machine Learning for the Geosciences: Challenges and Opportunities. IEEE Transactions on Knowledge and Data Engineering, 31(8): 1544-1554. https://doi.org/10.1109/TKDE.2018.2861006 Kratzert, F., Klotz, D., Shalev, G., et al., 2019. Towards Learning Universal, Regional, and Local Hydrological Behaviors Via Machine Learning Applied to Large-Sample Datasets. Hydrology and Earth System Sciences, 23(12): 5089-5110. https://doi.org/10.5194/hess-23-5089-2019 Lindemann, B., Müller, T., Vietz, H., et al., 2021. A Survey on Long Short-Term Memory Networks for Time Series Prediction. Procedia CIRP, 99: 650-655. https://doi.org/10.1016/j.procir.2021.03.088 Liu, J. J., Yuan, X., Zeng, J. H., et al., 2022a. Ensemble Streamflow Forecasting over a Cascade Reservoir Catchment with Integrated Hydrometeorological Modeling and Machine Learning. Hydrology and Earth System Sciences, 26(2): 265-278. https://doi.org/10.5194/hess-26-265-2022 Liu, X., Lu, D. W., Zhang, A. Q., et al., 2022b. Data-Driven Machine Learning in Environmental Pollution: Gains and Problems. Environmental Science & Technology, 56(4): 2124-2133. https://doi.org/10.1021/acs.est.1c06157 Liu, X. P., Lu, M. Z., Chai, Y. Z., et al., 2021. A Comprehensive Framework for HSPF Hydrological Parameter Sensitivity, Optimization and Uncertainty Evaluation Based on SVM Surrogate Model: A Case Study in Qinglong River Watershed, China. Environmental Modelling & Software, 143: 105126. https://doi.org/10.1016/j.envsoft.2021.105126 Long, X., Lin, H., An, X., et al., 2022. Evaluation and Analysis of Ecosystem Service Value Based on Land use/Cover Change in Dongting Lake Wetland. Ecological Indicators, 136: 108619. https://doi.org/10.1016/j.ecolind.2022.108619 Nasr, A., Bruen, M., Jordan, P., et al., 2007. A Comparison of SWAT, HSPF and SHETRAN/GOPC for Modelling Phosphorus Export from Three Catchments in Ireland. Water Research, 41(5): 1065-1073. https://doi.org/10.1016/j.watres.2006.11.026 Nie, L. J., Zeng, L. H., Ji, J., et al., 2022. Centurial Changes in Sedimentary Phosphorus Forms and Trace Elements in Response to Damming and Anthropogenic Pollution in a Floodplain Lake, Central China. Environmental Science and Pollution Research, 29(19): 28446-28457. https://doi.org/10.1007/s11356-021-18476-1 People's Government of Hunan Province, 2019. Hunan Provincial People's Government on the Issuance of the Implementation Program of Hunan Province Dongting Lake Water Environment Comprehensive Management Plan (2018-2025). Gazette of the People's Government of Hunan Province, (21): 2-22 (in Chinese). Powers, S. M., Bruulsema, T. W., Burt, T. P., et al., 2016. Long-Term Accumulation and Transport of Anthropogenic Phosphorus in Three River Basins. Nature Geoscience, 9: 353-356. https://doi.org/10.1038/ngeo2693 Rezaeianzadeh, M., Stein, A., Tabari, H., et al., 2013. Assessment of a Conceptual Hydrological Model and Artificial Neural Networks for Daily Outflows Forecasting. International Journal of Environmental Science and Technology, 10(6): 1181-1192. https://doi.org/10.1007/s13762-013-0209-0 Sharpley, A. N., Williams, J. R., 1990. EPIC-Erosion/ Productivity Impact Calculator: 1. Model Documentation. US Department of Agriculture, Washington D. C. . Singh, V. P., Frevert, D. K., 2002. Mathematical Models of Large Watershed Hydrology. Water Resources Publications, Highlands Ranch, Colo. Sutton, M. A., Mason, K. E., Bleeker, A., et al., 2020. Global Nitrogen and Phosphorus Pollution. Springer International Publishing AG, Switzerland, 421-431. Tan, Y., Chen, M., Zhang, L. L., et al., 2022. Flux and Spatial Pattern of Phosphorus in the Shigatse Section of the Yarlung Zangbo River, China. Ecological Indicators, 135: 108552. https://doi.org/10.1016/j.ecolind.2022.108552 Wang, D. Y., Han, J. C., Li, R., et al., 2023. Nutritional Characteristics in the Waterbody of Lake Dongting Area Nutrient Condition and Associated Improvement Measures under the Extreme Drought in 2022. Journal of Lake Sciences, 35(6): 1970-1978 (in Chinese with English abstract). Wang, H. Y., Ti, C. P., Wang, L. J., et al., 2022. SpatioTemporal Distribution Characteristics and Key Sources of Nitrogen Pollution in a Typical Agricultural Watershed Based on SWAT Model. Journal of Lake Sciences, 34(2): 517-527 (in Chinese with English abstract). doi: 10.18307/2022.0213 Wang, Y. D., Ouyang, W., Zhang, Y. H., et al., 2021. Quantify Phosphorus Transport Distinction of Different Reaches to Estuary under Long-Term Anthropogenic Perturbation. Science of the Total Environment, 780: 146647. https://doi.org/10.1016/j.scitotenv.2021.146647 Wang, Y. S., Xie, X., Liu, C., et al., 2020. Variation of Net Anthropogenic Phosphorus Inputs (NAPI) and Riverine Phosphorus Fluxes in Seven Major River Basins in China. Science of the Total Environment, 742: 140514. https://doi.org/10.1016/j.scitotenv.2020.140514 Xu, B., Li, Y., Han, F., et al., 2020. The Transborder Flux of Phosphorus in the Lancang-Mekong River Basin: Magnitude, Patterns and Impacts from the Cascade Hydropower Dams in China. Journal of Hydrology, 590: 125201. https://doi.org/10.1016/j.jhydrol.2020.125201 Wei, K., Ouyang, C. J., Duan, H. T., et al., 2020. Reflections on the Catastrophic 2020 Yangtze River Basin Flooding in Southern China. Innovation (Cambridge (Mass)), 1(2): 100038. https://doi.org/10.1016/j.xinn.2020.100038 Wu, X. C., Ma, T., Du, Y., et al., 2021. Phosphorus Cycling in Freshwater Lake Sediments: Influence of Seasonal Water Level Fluctuations. Science of the Total Environment, 792: 148383. https://doi.org/10.1016/j.scitotenv.2021.148383 Zhang, X. Q., Zhao, D., Wang, T., et al., 2022. A Novel Rainfall Prediction Model Based on CEEMDAN-PSO-ELM Coupled Model. Water Supply, 22(4): 4531-4543. https://doi.org/10.2166/ws.2022.115 Zhao, A. Z., Zhao, Y. L., Liu, X. F., et al., 2016. Impact of Human Activities and Climate Variability on Green and Blue Water Resources in the Weihe River Basin of Northwest China. Scientia Geographica Sinica, 36(4): 571-579 (in Chinese with English abstract). Zhao, G., Merder, J., Ballard, T. C., et al., 2023. Warming may Offset Impact of Precipitation Changes on Riverine Nitrogen Loading. Proceedings of the National Academy of Sciences of the United States of America, 120(33): e2220616120. https://doi.org/10.1073/pnas.2220616120 贺秋华, 余德清, 余姝辰, 等, 2021. 三峡水库运行前后洞庭湖水资源量变化. 地球科学, 46(1): 293-307. 胡光伟, 梁业伟, 庄少奇, 等, 2023. 洞庭湖流域农业面源污染时空分异特征与防治建议. 环境生态学, 5(3): 59-65. 湖南省人民政府, 2019. 湖南省人民政府关于印发《湖南省洞庭湖水环境综合治理规划实施方案(2018—2025年)》的通知. 湖南省人民政府公报, (21): 2-22. 王丹阳, 韩锦诚, 黎睿, 等, 2023. 2022年极端干旱下洞庭湖区水体营养状态变化及改善对策. 湖泊科学, 35(6): 1970-1980. 王慧勇, 遆超普, 王良杰, 等, 2022. 基于SWAT模型的典型农业小流域氮污染时空分布特征及关键源解析. 湖泊科学, 34(2): 517-527. 赵安周, 赵玉玲, 刘宪锋, 等, 2016. 气候变化和人类活动对渭河流域蓝水绿水影响研究. 地理科学, 36(4): 571-579. -
点击查看大图
图(9) / 表(3)
计量
- 文章访问数: 344
- HTML全文浏览量: 128
- PDF下载量: 50
- 被引次数: 0
