A benchmark-based method for evaluating hyperparameter optimization techniques of neural networks for surface water quality prediction  

作　　者：Xuan Wang Yan Dong Jing Yang Zhipeng Liu Jinsuo Lu 

机构地区：[1]School of Environmental and Municipal Engineering,Xi’an University of Architecture and Technology,Xi’an,710055,China [2]Shaanxi Key Laboratory of Environmental Engineering,Xi’an University of Architecture and Technology,Xi’an,710055,China [3]State Key Laboratory of Green Building in West China,Xi’an University of Architecture and Technology,Xi’an,710055,China

出　　处：《Frontiers of Environmental Science & Engineering》2024年第5期13-27,共15页环境科学与工程前沿（英文）

基　　金：financially supported by the National Key R&D Project(No.2022YFC3203203);the Shaanxi Province Science Fund for Distinguished Young Scholars(No.S2023-JC-JQ-0036).

摘　　要：Neural networks(NNs)have been used extensively in surface water prediction tasks due to computing algorithm improvements and data accumulation.An essential step in developing an NN is the hyperparameter selection.In practice,it is common to manually determine hyperparameters in the studies of NNs in water resources tasks.This may result in considerable randomness and require significant computation time;therefore,hyperparameter optimization(HPO)is essential.This study adopted five representatives of the HPO techniques in the surface water quality prediction tasks,including the grid sampling(GS),random search(RS),genetic algorithm(GA),Bayesian optimization(BO)based on the Gaussian process(GP),and the tree Parzen estimator(TPE).For the evaluation of these techniques,this study proposed a method:first,the optimal hyperparameter value sets achieved by GS were regarded as the benchmark;then,the other HPO techniques were evaluated and compared with the benchmark in convergence,optimization orientation,and consistency of the optimized values.The results indicated that the TPE-based BO algorithm was recommended because it yielded stable convergence,reasonable optimization orientation,and the highest consistency rates with the benchmark values.The optimization consistency rates via TPE for the hyperparameters hidden layers,hidden dimension,learning rate,and batch size were 86.7%,73.3%,73.3%,and 80.0%,respectively.Unlike the evaluation of HPO techniques directly based on the prediction performance of the optimized NN in a single HPO test,the proposed benchmark-based HPO evaluation approach is feasible and robust.

关 键 词：Neural networks Hyperparameter optimization Surface water quality prediction Bayes optimization Genetic algorithm 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]