MYCOLab Ai Logo - gold and army green

Artificial Neural Network Prediction of Mechanical Properties in Mycelium-Based Biocomposites

Summary

Researchers used artificial intelligence to predict how strong mushroom-based materials would be. These eco-friendly composites are made from wood particles held together by fungal networks instead of synthetic glue. The AI model successfully learned to predict the strength of these materials based on which type of fungus was used and what wood particles they were grown on, potentially reducing the need for expensive testing.

Background

Mycelium-based biocomposites (MBBs) are sustainable alternatives to synthetic composites, produced from lignocellulosic substrates bonded by fungal mycelium without synthetic adhesives. Their mechanical performance depends on multiple interacting factors including substrate composition, fungal species, and processing conditions, making optimization challenging.

Objective

To develop and validate an artificial neural network (ANN) model for predicting mechanical properties of MBBs, specifically internal bonding and compressive strength, using substrate composition, fungal species, and physical properties as input variables.

Results

The ANN achieved high predictive accuracy with R² coefficients of 0.992 for internal bonding and 0.979 for compressive strength on training data. Internal bonding was predicted more precisely than compressive strength, likely due to microstructural heterogeneities. Feature importance analysis showed fungal species and substrate type were the strongest predictors.

Conclusion

ANNs can effectively predict mechanical properties of mycelium-based biocomposites, reducing the number of experimental tests needed for material characterization. The model demonstrates that fungal species and substrate choice significantly influence mechanical performance, with potential for application in sustainable composite design.
  • Published in:Polymers (Basel),
  • Study Type:Experimental Research with Machine Learning Modeling,
  • Source: 10.3390/polym17182506, PMID: 41012270
Scroll to Top