1
|
Li Y, Yu Q, Du Z. Sand cat swarm optimization algorithm and its application integrating elite decentralization and crossbar strategy. Sci Rep 2024; 14:8927. [PMID: 38637550 PMCID: PMC11026427 DOI: 10.1038/s41598-024-59597-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2024] [Accepted: 04/12/2024] [Indexed: 04/20/2024] Open
Abstract
Sand cat swarm optimization algorithm is a meta-heuristic algorithm created to replicate the hunting behavior observed by sand cats. The presented sand cat swarm optimization method (CWXSCSO) addresses the issues of low convergence precision and local optimality in the standard sand cat swarm optimization algorithm. It accomplished this through the utilization of elite decentralization and a crossbar approach. To begin with, a novel dynamic exponential factor is introduced. Furthermore, throughout the developmental phase, the approach of elite decentralization is incorporated to augment the capacity to transcend the confines of the local optimal. Ultimately, the crossover technique is employed to produce novel solutions and augment the algorithm's capacity to emerge from local space. The techniques were evaluated by performing a comparison with 15 benchmark functions. The CWXSCSO algorithm was compared with six advanced upgraded algorithms using CEC2019 and CEC2021. Statistical analysis, convergence analysis, and complexity analysis use statistics for assessing it. The CWXSCSO is employed to verify its efficacy in solving engineering difficulties by handling six traditional engineering optimization problems. The results demonstrate that the upgraded sand cat swarm optimization algorithm exhibits higher global optimization capability and demonstrates proficiency in dealing with real-world optimization applications.
Collapse
Affiliation(s)
- Yancang Li
- School of Civil Engineering, Hebei University of Engineering, Handan, 056038, Hebei, China
| | - Qian Yu
- School of Civil Engineering, Hebei University of Engineering, Handan, 056038, Hebei, China.
| | - Zunfeng Du
- School of Civil Engineering, Tianjin University, Tianjin, 300354, China
| |
Collapse
|
2
|
Zhao L, Qing S, Li H, Qiu Z, Niu X, Shi Y, Chen S, Xing X. Estimating maize evapotranspiration based on hybrid back-propagation neural network models and meteorological, soil, and crop data. Int J Biometeorol 2024; 68:511-525. [PMID: 38197984 DOI: 10.1007/s00484-023-02608-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 11/16/2023] [Accepted: 12/14/2023] [Indexed: 01/11/2024]
Abstract
Crop evapotranspiration is a key parameter influencing water-saving irrigation and water resources management of agriculture. However, current models for estimating maize evapotranspiration primarily rely on meteorological data and empirical coefficients, and the estimated evapotranspiration contains uncertainties. In this study, the evapotranspiration data of summer maize were collected from typical stations in Northern China (Yucheng Station), and a back-propagation neural network (BP) model for predicting maize evapotranspiration was constructed based on meteorological data, soil data, and crop data. To further improve its accuracy, the maize evapotranspiration model was optimized using three bionic optimization algorithms, namely the sand cat swarm optimization (SCSO) algorithms, hunter-prey optimizer (HPO) algorithm, and golden jackal optimization (GJO) algorithm. The results showed that the fusion of meteorological, soil moisture, and crop data can effectively improve the accuracy of the maize evapotranspiration model. The model showed higher accuracy with the hybrid optimization model SCSO-BP compared to the stand-alone BP neural network model, with improvements of 2.7-4.8%, 17.2-25.5%, 13.9-26.8%, and 3.3-5.6% in terms of R2, RMSE, MAE, and NSE, respectively. Comprehensively compared with existing maize evapotranspiration models, the SCSO-BP model presented the highest accuracy, with R2 = 0.842, RMSE = 0.433 mm/day, MAE = 0.316 mm/day, NSE = 0.840, and overall global evaluation index (GPI) ranking the first. The results have reference value for the calculation of daily evapotranspiration of maize in similar areas of northern China.
Collapse
Affiliation(s)
- Long Zhao
- College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Shunhao Qing
- College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Hui Li
- College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Zhaomei Qiu
- College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Xiaoli Niu
- College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Yi Shi
- College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Shuangchen Chen
- College of Horticulture and Plant Protection, Henan University of Science and Technology, Luoyang, 471000, Henan Province, China
| | - Xuguang Xing
- Key Laboratory for Agricultural Soil and Water Engineering in Arid Area of Ministry of Education, Northwest A&F University, Yangling, Xianyang, 712100, Shaanxi Province, China.
| |
Collapse
|