A Novel Self-Attention Mechanism-Based Dynamic Ensemble Model for Soil Hyperspectral Prediction
Open Access
Abstract
Visible–near-infrared spectroscopy enables rapid, non-destructive soil organic matter (SOM) detection, yet its prediction accuracy relies heavily on the effectiveness of the chosen algorithmic models. Weighted Averaging Ensemble Models (WAEM) are robust but face a key challenge: their performance depends on optimal base learner weight allocation, which standard evaluation indices often fail to achieve, risking biased weights and local optima. This study significantly enhances WAEM by determining optimal weights using information extracted from the model training process via seven methods, including reinforcement learning and a self-attention mechanism (Sam). Experiments on 704 soil samples from China’s Tarim River Basin employed a dynamic data structure for real-time weight updating. Results show that six WAEM methods utilizing training process information outperformed conventional evaluation index approaches. Improvements reduced WAEM root mean square error (RMSE) by 0.028–1.279 g kg−1 and increased the correlation coefficient (R2) by up to 0.06. Sam achieved the highest performance, with R2 and RMSE reaching 0.927 and 2.325 g kg−1, respectively. Furthermore, model R2 began converging at 26 base learners, indicating diminishing returns from adding more. This research confirms that dynamic WAEM weight allocation via Sam significantly boosts SOM prediction accuracy, providing a scientific foundation for infrared-based soil monitoring.Keywords
Funding Information
- Natural Science Support Program of XPCC (2025DA002)
- Tarim University President’s Fund (TDZKSS202404)
- Tarim University President’s Fund (TDZKCX202205)
- Tarim University President’s Fund (TDZKSS202227)
- Tarim University Graduate Research and Innovation Project (TDGRI202319)
- the National Science Foundation of China (42201073)
- the National Science Foundation of China (42201058)
- the National Science Foundation of China (42201054)
This publication has 72 references indexed in Scilit:
- Reduced Bayesian Optimized Stacked Regressor (RBOSR): A highly efficient stacked approach for improved air pollution predictionApplied Soft Computing, 2023
- An adaptive learning approach for customer churn prediction in the telecommunication industry using evolutionary computation and Naïve BayesApplied Soft Computing, 2023
- Software defect prediction ensemble learning algorithm based on adaptive variable sparrow search algorithmInternational Journal of Machine Learning and Cybernetics, 2023
- A Weighted Average Ensemble Technique to Predict Heart Disease2022
- A review on extreme learning machineMultimedia Tools and Applications, 2021
- pXRF in tropical soils: Methodology, applications, achievements and challenges2021
- Linear regressionWIREs Computational Statistics, 2012
- Genetic algorithms (GA) applied to the orthogonal projection approach (OPA) for variable selectionAnalytica Chimica Acta, 2004
- Q-learningMachine Learning, 1992
- A linked list data structure for a simple linear regression algorithmComputers & Operations Research, 1984