Combined interaction of fungicides binary mixtures: experimental study and machine learning-driven QSAR modeling
2024

Fungicide Mixtures and Machine Learning Models

Sample size: 50 publication 10 minutes Evidence: high

Author Information

Author(s): Abbod Mohsen, Mohammad Ahmad

Primary Institution: Department of Plant Protection, Faculty of Agriculture, Al-Baath University, Homs, Syria

Hypothesis

Can machine learning models accurately predict the fungicidal activity of binary mixtures of fungicides?

Conclusion

The study found that machine learning models, particularly ANN and SVM, are effective in predicting the fungicidal activity of mixtures, outperforming traditional methods.

Supporting Evidence

  • Machine learning models showed better predictive performance than traditional methods.
  • Most fungicide mixtures exhibited additive interactions.
  • The ANN model had a higher accuracy than the SVM model.

Takeaway

Mixing different fungicides can help fight plant diseases better, and using computers to analyze these mixtures can make predictions about their effectiveness.

Methodology

The study used a fixed ratio ray design to create binary mixtures of fungicides and analyzed their interactions using machine learning models.

Potential Biases

Potential biases in the selection of fungicides and their concentrations could affect the results.

Limitations

The study may not account for all environmental factors affecting fungicide efficacy.

Statistical Information

P-Value

p<0.001

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1038/s41598-024-63708-2

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication