# Evaluation of Multiple Influences on the Unconfined Compressive Strength of Fibre-Reinforced Backfill Using a GWO–LGBM Model

## TL;DR

A new model accurately predicts the strength of fiber-reinforced backfill used in mining, showing that cement content and fiber properties are key factors.

## Contribution

The novel GWO–LGBM model improves prediction accuracy of unconfined compressive strength in fiber-reinforced cemented paste backfill.

## Key findings

- The GWO–LGBM model achieved high accuracy in predicting UCS with R2 = 0.949 on the testing set.
- Cement content and curvature coefficient are primary factors affecting UCS of CPB.
- Fibers enhance structural bonding, while tailings' chemical composition has an inert role.

## Abstract

What are the main findings?
A GWO–LGBM model is proposed for the high-accuracy prediction of UCS in fibre-reinforced CPB.Multi-factor analysis is applied to evaluate the coupled effects of mixture proportions, the tailings’ physical/chemical characteristics, and fibre properties on UCS.

A GWO–LGBM model is proposed for the high-accuracy prediction of UCS in fibre-reinforced CPB.

Multi-factor analysis is applied to evaluate the coupled effects of mixture proportions, the tailings’ physical/chemical characteristics, and fibre properties on UCS.

What are the implications of the main findings?
Cement content and curvature coefficient are identified as the primary factors affecting the UCS of CPB.Fibres are found to enhance structural bonding, whereas the chemical composition of tailings plays an inert role.

Cement content and curvature coefficient are identified as the primary factors affecting the UCS of CPB.

Fibres are found to enhance structural bonding, whereas the chemical composition of tailings plays an inert role.

Fibres can markedly enhance the uniaxial compressive strength (UCS) of cemented paste backfill (CPB). However, previous studies have mainly verified the effectiveness of polypropylene and straw fibres in improving the UCS of CPB experimentally, while systematic multi-factor evaluation remains limited. In this study, laboratory experiments were conducted on polypropylene- and straw fibre-reinforced CPB to construct a reliable dataset. The factors influencing the intensity of uniaxial compressive strength were divided into four aspects (mixture proportions, physical properties of the cement–tailings mixture, chemical characteristics of tailings, and fibre properties), and four intelligent models were developed for effectiveness analysis and UCS prediction. SHapley Additive exPlanations (SHAP) were employed to quantify the contributions of individual features, and the findings were experimentally validated. The GWO–LGBM model outperformed the SVR, ANN, and LGBM models, achieving R2 = 0.907, RMSE = 0.78, MAE = 0.515, and MAPE = 0.157 for the training set, and R2 = 0.949, RMSE = 0.627, MAE = 0.38, and MAPE = 0.115 for the testing set, respectively. Feature analysis reveals that mixture proportions contribute the most to UCS, followed by the tailings’ physical properties, the fibre properties, and the tailings’ chemical characteristics. This study found that cement content and tailings gradation control CPB structural compactness and fibres enhance bonding between hydration products and tailings aggregates, while the chemical composition of the tailings plays an inert role, functioning mainly as an aggregate.