Drought prediction model based on GPSGSO-BPNN parallel ensemble learning algorithm

LI Jingming, NI Zhiwei, ZHU Xuhui, XU Ying

Systems Engineering - Theory & Practice ›› 2018, Vol. 38 ›› Issue (5) : 1343-1353.

PDF(970 KB)
PDF(970 KB)
Systems Engineering - Theory & Practice ›› 2018, Vol. 38 ›› Issue (5) : 1343-1353. DOI: 10.12011/1000-6788(2018)05-1343-11

Drought prediction model based on GPSGSO-BPNN parallel ensemble learning algorithm

  • LI Jingming1,2, NI Zhiwei1, ZHU Xuhui1, XU Ying3
Author information +
History +

Abstract

Aiming at defects of slow learning speed, trapped in local solution and inaccurate operating result of traditional BP neural network in the practical application of drought prediction, a drought prediction model based on parallel ensemble learning algorithm of good point set glowworm swarm optimization algorithm (GPSGSO) and back propagation neural network (BPNN) is proposed. Firstly, a new kind of improved glowworm swarm algorithm based on good point set theory and inertia weight function is constructed, and the validity of the algorithm is analyzed theoretically. Secondly, GPSGSO algorithm and BPNN are combined to construct parallel ensemble learning algorithm. GPSGSO is used to optimize the weight and threshold of BPNN, and the ensemble strategy is carried out for the best weights and thresholds. Finally, the parallel ensemble learning algorithm is applied to the prediction of agricultural drought disaster, which can accurately determine the drought level. The effectiveness of the GPSGSO algorithm in terms of convergence speed, accuracy and stability is verified by 8 Benchmark functions. At the same time, agricultural meteorological data of Northern Anhui Province is used to simulate validate experiment, the experimental results show that the algorithm has obvious advantages over the traditional BPNN, GSO-BPNN and GA-BPNN algorithm in terms of convergence speed, operation accuracy and stability. Therefore, the drought prediction model based on GPSGSO-BPNN parallel learning algorithm can effectively improve the accuracy of agricultural drought prediction.

Key words

good point set glowworm swarm optimization algorithm / back propagation neural network / parallel ensemble learning / drought prediction model

Cite this article

Download Citations
LI Jingming , NI Zhiwei , ZHU Xuhui , XU Ying. Drought prediction model based on GPSGSO-BPNN parallel ensemble learning algorithm. Systems Engineering - Theory & Practice, 2018, 38(5): 1343-1353 https://doi.org/10.12011/1000-6788(2018)05-1343-11

References

[1] AghaKouchak A. A multivariate approach for persistence-based drought prediction:Application to the 2010-2011 East Africa drought[J]. Journal of Hydrology, 2015, 526:127-135.
[2] Gong Z, Forrest J Y L. Special issue on meteorological disaster risk analysis and assessment:On basis of grey systems theory[J]. Natural Hazards, 2014, 71(2):995-1000.
[3] 曹永强, 伊吉美, 游海林. 投影寻踪技术在农业旱灾脆弱性评价中的应用[J]. 人民黄河, 2010, 32(2):12-13. Cao Y Q, Yi J M, You H L. Projection pursuit technique used in the evaluation of agricultural drought vulnerability[J]. People Yellow River, 2010, 32(2):12-13.
[4] Cheng J, Tao J. Fuzzy comprehensive evaluation of drought vulnerability based on the analytic hierarchy process:An empirical study from Xiaogan City in Hubei Province[J]. Agriculture and Agricultural Science Procedia, 2010, 1:126-135.
[5] Sun Z, Zhang J, Zhang Q, et al. Integrated risk zoning of drought and water logging disasters based on fuzzy comprehensive evaluation in Anhui Province, China[J]. Natural hazards, 2014, 71(3):1639-1657.
[6] Jia H, Pan D, Yuan Y, et al. Using a BP neural network for rapid assessment of populations with difficulties accessing drinking water because of drought[J]. Human and Ecological Risk Assessment:An International Journal, 2015, 21(1):100-116.
[7] Abarghouei H B, Kousari M R, Zarch M A A. Prediction of drought in dry lands through feed forward artificial neural network abilities[J]. Arabian Journal of Geosciences, 2013, 6(5):1417-1433.
[8] 冯平, 钟翔, 张波. 基于人工神经网络的干旱程度评估方法[J]. 系统工程理论与实践, 2000, 20(3):141-144. Feng P, Zhong X, Zhang B. A drought degree evaluation method based on the artificial neural network[J]. Systems Engineering-Theory & Practice, 2000, 20(3):141-144.
[9] Hecht-Nielsen R. Theory of the backpropagation neural network[M]//Neural networks for perception, 1992:65-93.
[10] Shi L, Tang X, Lü J. PCA-based PSO-BP neural network optimization algorithm[C]//The 27th Chinese Control and Decision Conference (2015 CCDC). IEEE, 2015:1720-1725.
[11] Pan X T, Qu K Q. Wind power output prediction with BP neural network combining genetic algorithms[C]//Advanced Materials Research. Trans Tech Publications, 2014, 860:2526-2529.
[12] Movahedi M, Kokabi A H, Reihani S M S, et al. Prediction and optimization of back-break and rock fragmentation using an artificial neural network and a bee colony algorithm[J]. Bulletin of Engineering Geology and the Environment, 2016, 75(1):27-36.
[13] Hou Y, Li H Y. Chaotic time series prediction for tent mapping based on BP neural network optimized glowworm swarm optimization[C]//Applied Mechanics and Materials. Trans Tech Publications, 2014, 513:1096-1100.
[14] Krishnanand K N, Ghose D. Glowworm swarm based optimization algorithm for multimodal functions with collective robotics applications[J]. Multiagent and Grid Systems, 2006, 2(3):209-222.
[15] Krishnanand K N, Ghose D. Glowworm swarm optimisation:A new method for optimising multi-modal functions[J]. International Journal of Computational Intelligence Studies, 2009, 1(1):93-119.
[16] Krishnanand K N, Ghose D. Detection of multiple source locations using a glowworm metaphor with applications to collective robotics[C]//Proceedings 2005 IEEE Swarm Intelligence Symposium, 2005:84-91.
[17] Rani K S S, Devarajan N. Optimization model for sensor node deployment[J]. European Journal of Scientific Research, 2012, 70(4):491-498.
[18] Couceiro M S, Martins F M L, Rocha R P, et al. Mechanism and convergence analysis of a multi-robot swarm approach based on natural selection[J]. Journal of Intelligent and Robotic Systems, 2014, 76(2):353-381.
[19] Aljarah I, Ludwig S A. A new clustering approach based on glowworm swarm optimization[C]//2013 IEEE Congress on Evolutionary Computation. IEEE, 2013:2642-2649.
[20] 华罗庚, 王元. 数论在近似分析中的应用[M]. 北京:科学出版社, 1978. Hua L G, Wang Y. The application of number theory in approximation[M]. Beijing:Science Press, 1978.
[21] 张铃, 张钹. 佳点集遗传算法[J]. 计算机学报, 2001, 24(9):917-922. Zhang L, Zhang B. Good point set based genetic algorithm[J]. Chinese Journal of Computers, 2001, 24(9):917-922.
[22] Zhongqun L, Hua Z, Chengming P. Particle swarm optimization algorithm based on adaptive inertia weight[C]//20102nd International Conference on Signal Processing Systems (ICSPS). IEEE, 2010, 3:454-459.
[23] Yazdani D, Sadeghi-Ivrigh S, Yazdani D, et al. Fish swarm search algorithm:A new algorithm for global optimization[J]. International Journal of Artificial Intelligence, 2015, 13(2):17-45.

Funding

Training Program of the Major Research Plan of National Natural Science Foundation of China (91546108); Major Research Plan of National Natural Science Foundation of China (71490725); National Natural Science Youth Fund Project (71601061); Key Natural Science Program of Department of Education of Anhui Province (KJ2016A308)
PDF(970 KB)

385

Accesses

0

Citation

Detail

Sections
Recommended

/