摘要
卷积神经网络(convolutional neural network,CNN)和双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)是目前流行的用于地面沉降预测深度学习架构.然而,深度学习模型超参数的选择既费时又复杂,且超参数选择不当可能会导致模型整体性能不佳.针对这一问题,本文融合黑翅鸢优化算法(black-winged kite optimization algorithm,BKA)构建了BKA-CNNBiLSTM组合模型,并以西宁市为例进行实验分析,并将实验结果与其他四种模型的实验结果进行对比.结果表明:在与传统模型的对比中,BKA-CNN-BiLSTM模型的训练与预测效果更好,其决定系数(R2)较BiLSTM模型提高了17.43%~25.77%,较CNN-BiLSTM模型提高了12.04%~13.75%,平均绝对误差(mean absolute error,MAE)、均方误差(mean square error,MSE)、均方根误差(root mean square error,RMSE)指标均为最优.在与遗传算法(genetic algorithm,GA)、粒子群优化(particle swarm optimization,PSO)算法优化的CNN-BiLSTM模型对比中,此模型依然表现出了更高的的可靠性与预测性能,其R2分别提高了6.20%~17.76%、1.18%~12.76%.这些结果证明了BKA-CNN-BiLSTM模型的优越性能.这不仅为地表沉降建模提供了新的技术思路,也为深度学习在相关领域的应用提供了有价值的参考和解决方案.
Convolutional neural networks(CNN)and bidirectional long short-term memory(BiLSTM)networks are currently among the most popular deep learning architectures for surface subsidence prediction.However,the selection of hyper parameters for such models remains both time-consuming and complex,and improper choices can significantly degrade model performance.To address this issue,this study integrates the black-winged kite optimization algorithm(BKA)for hyper parameter optimization,constructing a hybrid BKA-CNN-BiLSTM model.Taking Xining city as a case study,experimental analyses were conducted and the results were compared with those of four other models.The findings reveal that the proposed BKA-CNNBiLSTM model achieves superior performance in both training and prediction.Compared to the BiLSTM model,the coefficient of determination(R2)improvement ranges from 17.43%to 25.77%,and compared to the CNN-BiLSTM model,the improvement ranges from 12.04%to 13.75%.The proposed model also obtains the lowest MAE,MSE,and RMSE among all models.When compared with CNN-BiLSTM models optimized by genetic algorithm(GA)and particle swarm optimization(PSO),the BKA-CNN-BiLSTM model continues to demonstrate higher reliability and prediction accuracy,with R2 improvements of 6.20%—17.76%and 1.18%—12.76%,respectively.These results validate the superior performance of the proposed model and offer a novel technical pathway for surface subsidence modeling,while providing practical insights for the application of deep learning in related domains.
作者
杨勇杰
胡祥祥
王鹏
石亚亚
宋宝
吴成永
于志远
YANG Yongjie;HU Xiangxiang;WANG Peng;SHI Yaya;SONG Bao;WU Chengyong;YU Zhiyuan(School of Resources and Environmental Engineering,Tianshui Normal University,Tianshui 741001,China;Xining Surveying and Mapping Institute,Xining 810000,China;School of Automation,Beijing Institute of Technology,Beijing 100081,China)
出处
《全球定位系统》
2025年第4期95-104,共10页
Gnss World of China
基金
国家自然科学基金(42361020,42461064)
2024年甘肃省高等学校人才培养质量提升项目(甘教高函[2024]18号)
天水师范学院创新基金(CXJ2023-19)。
