Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis

PurposeWe propose an accelerated Bayesian optimization framework for tuning the learning rate of CNN+LSTM models in soil analysis, addressing the computational inefficiency of traditional Gaussian Process (GP)-based methods. This work bridges the gap between computational efficiency and probabilisti...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaolong Chen, Hongfeng Zhang, Cora Un In Wong, Zhengchun Song
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Environmental Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fenvs.2025.1633046/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413424363077632
author Xiaolong Chen
Hongfeng Zhang
Cora Un In Wong
Zhengchun Song
author_facet Xiaolong Chen
Hongfeng Zhang
Cora Un In Wong
Zhengchun Song
author_sort Xiaolong Chen
collection DOAJ
description PurposeWe propose an accelerated Bayesian optimization framework for tuning the learning rate of CNN+LSTM models in soil analysis, addressing the computational inefficiency of traditional Gaussian Process (GP)-based methods. This work bridges the gap between computational efficiency and probabilistic robustness, with broader implications for automated machine learning in geoscientific applications.MethodThe key innovation lies in a subspace-accelerated GP surrogate model that precomputes low-rank approximations of covariance matrices offline, thereby decoupling the costly hyperparameter tuning from the online acquisition function evaluations. By projecting the hyperparameter search space onto a dominant subspace derived from Nyström approximations, our method reduces the computational complexity from cubic to linear in the number of observations. The proposed system integrates seamlessly with existing CNN+LSTM pipelines, where the offline phase constructs the GP subspace using historical or synthetic data, while the online phase iteratively updates the subspace with rank-1 modifications. Moreover, the method’s adaptability to non-stationary response surfaces, facilitated by a Matérn-5/2 kernel with automatic relevance determination, makes it particularly suitable for soil data exhibiting multi-scale features.ResultsEmpirical validation on soil spectral datasets demonstrates a 3–5× speedup in convergence compared to standard Bayesian optimization, with no loss in model accuracy. Experiments on soil spectral datasets show convergence in 23.4 min (3.8× faster than standard Bayesian optimization) with a test RMSE of 0.142, while maintaining equivalent accuracy across diverse CNN+LSTM architectures.ConclusionThe reformulated approach not only overcomes the scalability limitations of conventional GP-based optimization but also preserves its theoretical guarantees, offering a practical solution for hyperparameter tuning in resource-constrained environments.
format Article
id doaj-art-47e706c7733745c1beb980321cb36ced
institution Kabale University
issn 2296-665X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Environmental Science
spelling doaj-art-47e706c7733745c1beb980321cb36ced2025-08-20T03:34:08ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2025-08-011310.3389/fenvs.2025.16330461633046Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysisXiaolong ChenHongfeng ZhangCora Un In WongZhengchun SongPurposeWe propose an accelerated Bayesian optimization framework for tuning the learning rate of CNN+LSTM models in soil analysis, addressing the computational inefficiency of traditional Gaussian Process (GP)-based methods. This work bridges the gap between computational efficiency and probabilistic robustness, with broader implications for automated machine learning in geoscientific applications.MethodThe key innovation lies in a subspace-accelerated GP surrogate model that precomputes low-rank approximations of covariance matrices offline, thereby decoupling the costly hyperparameter tuning from the online acquisition function evaluations. By projecting the hyperparameter search space onto a dominant subspace derived from Nyström approximations, our method reduces the computational complexity from cubic to linear in the number of observations. The proposed system integrates seamlessly with existing CNN+LSTM pipelines, where the offline phase constructs the GP subspace using historical or synthetic data, while the online phase iteratively updates the subspace with rank-1 modifications. Moreover, the method’s adaptability to non-stationary response surfaces, facilitated by a Matérn-5/2 kernel with automatic relevance determination, makes it particularly suitable for soil data exhibiting multi-scale features.ResultsEmpirical validation on soil spectral datasets demonstrates a 3–5× speedup in convergence compared to standard Bayesian optimization, with no loss in model accuracy. Experiments on soil spectral datasets show convergence in 23.4 min (3.8× faster than standard Bayesian optimization) with a test RMSE of 0.142, while maintaining equivalent accuracy across diverse CNN+LSTM architectures.ConclusionThe reformulated approach not only overcomes the scalability limitations of conventional GP-based optimization but also preserves its theoretical guarantees, offering a practical solution for hyperparameter tuning in resource-constrained environments.https://www.frontiersin.org/articles/10.3389/fenvs.2025.1633046/fullBayesian optimizationCNN+LSTMsoil analysisGaussian processcomputational efficiencyhyperparameter tuning
spellingShingle Xiaolong Chen
Hongfeng Zhang
Cora Un In Wong
Zhengchun Song
Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis
Frontiers in Environmental Science
Bayesian optimization
CNN+LSTM
soil analysis
Gaussian process
computational efficiency
hyperparameter tuning
title Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis
title_full Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis
title_fullStr Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis
title_full_unstemmed Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis
title_short Accelerated Bayesian optimization for CNN+LSTM learning rate tuning via precomputed Gaussian process subspaces in soil analysis
title_sort accelerated bayesian optimization for cnn lstm learning rate tuning via precomputed gaussian process subspaces in soil analysis
topic Bayesian optimization
CNN+LSTM
soil analysis
Gaussian process
computational efficiency
hyperparameter tuning
url https://www.frontiersin.org/articles/10.3389/fenvs.2025.1633046/full
work_keys_str_mv AT xiaolongchen acceleratedbayesianoptimizationforcnnlstmlearningratetuningviaprecomputedgaussianprocesssubspacesinsoilanalysis
AT hongfengzhang acceleratedbayesianoptimizationforcnnlstmlearningratetuningviaprecomputedgaussianprocesssubspacesinsoilanalysis
AT corauninwong acceleratedbayesianoptimizationforcnnlstmlearningratetuningviaprecomputedgaussianprocesssubspacesinsoilanalysis
AT zhengchunsong acceleratedbayesianoptimizationforcnnlstmlearningratetuningviaprecomputedgaussianprocesssubspacesinsoilanalysis