Symbolically Regressing Fish Biomass Spectral Data: A Linear Genetic Programming Method with Tunable Primitives

2025-05-28

AI Summary

Fish biomass spectral data suffer from high noise levels and limited sample sizes, hindering effective pattern discovery. Method: We formulate the modeling task as symbolic regression and propose a linear genetic programming approach with tunable basis elements. By dynamically optimizing intrinsic coefficients within each basis element, our method significantly enhances pattern mining capability and generalization performance under small-sample conditions; the resulting models are compact and physically interpretable. Contribution/Results: Integrated with spectral preprocessing and feature interpretability analysis, our method outperforms all baselines across ten fish biomass component prediction tasks: average prediction error decreases by 12.7%, model size shrinks by 68%, inference speed increases 3.2×, and biologically meaningful key spectral bands—such as 420–450 nm and 670–690 nm—are successfully identified.

Technology Category

• Machine Learning: Bio-inspired Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Machine learning techniques play an important role in analyzing spectral data. The spectral data of fish biomass is useful in fish production, as it carries many important chemistry properties of fish meat. However, it is challenging for existing machine learning techniques to comprehensively discover hidden patterns from fish biomass spectral data since the spectral data often have a lot of noises while the training data are quite limited. To better analyze fish biomass spectral data, this paper models it as a symbolic regression problem and solves it by a linear genetic programming method with newly proposed tunable primitives. In the symbolic regression problem, linear genetic programming automatically synthesizes regression models based on the given primitives and training data. The tunable primitives further improve the approximation ability of the regression models by tuning their inherent coefficients. Our empirical results over ten fish biomass targets show that the proposed method improves the overall performance of fish biomass composition prediction. The synthesized regression models are compact and have good interpretability, which allow us to highlight useful features over the spectrum. Our further investigation also verifies the good generality of the proposed method across various spectral data treatments and other symbolic regression problems.

Problem

• Analyzing noisy fish biomass spectral data with limited samples
• Improving prediction of fish biomass composition via symbolic regression
• Enhancing model interpretability and generality for spectral data analysis

Innovation

• Linear genetic programming for symbolic regression
• Tunable primitives enhance model approximation
• Compact interpretable models for spectral data