59
Tecnología y Ciencias del Agua
, vol. VIII, núm. 2, marzo-abril de 2017, pp. 51-60
Kan
et al.
,
Daily streamflow simulation based on improved machine learning method
ISSN 2007-2422
•
owed to the addition of the
K
-means cluster-
ing method combined with the utilization of
multiple PEK modules. With the clustering
method and multiple PEK modules, the PKEK
model can simulate the characteristics of the RR
relationship much precisely and it’s forecasting
capability and stability becomes better. Further-
more, the hydrographs simulated by the PKEK
model are much smoother and more consistent
with the observed hydrographs. The smoother
performance of the PKEK model is attributed
to the autoregressive nature of the ANN which
allocates a higher weighting to the antecedent
discharge inputs.
Acknowledgments
This research was funded by the IWHR Research &
Development Support Program (JZ0145B052016), China
Postdoctoral Science Foundation on Grant (Grant NO.
2016M600096, 2016M591214), Major International (Regional)
Joint Research Project – China’s Water and Food Security
under Extreme Climate Change Impact: Risk Assessment
and Resilience (G0305, 7141101024), International Project
(71461010701), Study of distributed flood risk forecast model
and technology based on multi-source data integration and
hydro meteorological coupling system (2013CB036406),
China National Flash Flood Disaster Prevention and Control
Project (126301001000150068), Natural Science Founda-
tion of China (41601569), Specific Research of China Institute
of Water Resources and Hydropower Research (Grant Nos.
Fangji 1240), and the Third Sub-Project: Flood Forecasting,
Controlling and Flood Prevention Aided Software Develop-
ment - Flood Control Early Warning Communication System
and Flood Forecasting, Controlling and Flood Prevention
Aided Software Development for Poyang Lake Area of
Jiangxi Province (0628-136006104242, JZ0205A432013,
SLXMB200902). We gratefully acknowledge the support of
NVIDIA Corporation with the donation of the Tesla K40
GPU used for this research. Guangyuan Kan, Minglei Ren,
and Tianjie Lei are the corresponding authors. Guangyuan
Kan and Ke Liang contributed equally to this work. The
author(s) declare(s) that there is no conflict of interest re-
garding the publication of this paper.
References
Chen, S., Kan, G., Liang, K., Li, J., Hong, Y., Zuo, D., Lei, T.,
Xu, W., Zhang, M., Shi, W., & Chen, X. (2017). Air quality
analysis and forecast for environment and public health
protection: a case study in Beijing, China.
Transylvanian
Review
,
24
(12), 3575-3591.
Dong, J., Zheng, C., Kan, G., Wen, J., Zhao, M., &Yu, J. (2015).
Applying the ensemble artificial neural network-based
hybrid data-driven model to daily total load forecasting.
Neural Computing & Applications
,
26
(3), 603-611.
Grigorios, T., & Aristidis, L. (2014). The MinMax k-means
clustering algorithm.
Pattern Recognition
,
47
(7), 2505-2516.
Kan, G., Yao, C., Li, Q., Li, Z., Yu, Z., Liu, Z., Ding, L., He,
X., & Liang, K. (2015a). Improving event-based rainfall-
runoff simulation using an ensemble artificial neural
network based hybrid data-driven model.
Stochastic
Environmental Research and Risk Assessment
. DOI: 10.1007/
s00477-015-1040-6.
Kan, G., Li, J., Zhang, X., Ding, L., He, X., Liang, K., Jiang,
X., Ren, M., Li, H., Wang, F., Zhang, Z., & Hu, Y. (2015b).
Anew hybrid data-driven model for event-based rainfall-
runoff simulation.
Neural Computing & Applications
,
27
(2),
DOI: 10.1007/s00521-016-2200-4.
Kan, G., He, X., Li, J., Ding, L., Zhang, D., Lei, T., Hong, Y.,
Liang, K., Zuo, D., Bao, Z., & Zhang, M. (2016a). A novel
hybrid data-driven model for multi-input single-output
system simulation.
Neural Computing & Applications
, DOI:
10.1007/s00521-016-2534-y.
Kan, G., Liang, K., Li, J., Ding, L., He, X., Hu, Y., & Mark,
A. (2016b). Accelerating the SCE-UA global optimization
method based on multi-core CPU and many-core GPU.
Advances in Meteorology
, 8483728, 10 pages. Recovered
from
Kan, G., Lei, T., Liang, K., Li, J., Ding, L., He, X., Yu, H.,
Zhang, D., Zuo, D., Bao, Z., Mark, A., Hu, Y., & Zhang, M.
(2016c). Amulti-core CPU and many-core GPU based fast
parallel shuffled complex evolution global optimization
approach.
IEEE Transactions on Parallel and Distributed
Systems
, DOI: 10.1109/TPDS.2016.2575822.
Kan, G., Zhang, M., Liang, K., Wang, H., Jiang, Y., Li,
J., Ding, L., He, X., Hong, Y., Zuo, D., Bao, Z., & Li,
C. (2016d). Improving water quantity simulation &
forecasting to solve the energy-water-food nexus issue
by using heterogeneous computing accelerated global
optimization method.
Applied Energy
. Recovered from
Kan, G., He, X., Ding, L., Li, J., Lei, T., Liang, K., & Hong,
Y. (2016e). An improved hybrid data-driven model and
its application in daily rainfall-runoff simulation.
IOP
Conference Series: Earth and Environmental Science
,
46
(2016),
012029 (6th Digital Earth Summit), DOI: 10.1088/1755-
1315/46/1/012029.
Kapageridis, I. K. (2015). Variable lag variography using
K-means clustering.
Computers & Geosciences
, SI, B, 85,
49-63.
Lei, T., Pang, Z., Wang, X., Li, L., Fu, J., Kan, G., Zhang, X.,
Ding, L., Li, J., Huang, S., & Shao, C. (2016). Drought and
