Privacy-Preserving Federated Learning for Artificial Intelligence Agriculture Crop Disease Detection Under Non-IID Farm Data: A Computer Differential-Privacy Utility Evaluation

Federated learning allows crop-disease classifiers to be trained across farms without centralising leaf imagery, but the non-IID structure of farm data and the noise added for differential privacy interact in ways that are poorly characterised for agricultural deployment. The analysis characterises the operating characteristics of the design under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, using 2000 replications per design cell across cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The results show that 54 clusters are required to detect a 5 percentage point effect at 80 percent power under this variance structure, and that the minimum detectable effect falls steeply as clusters increase from 8 to 32. The contribution is a design-level account of when differential-privacy noise overwhelms the between-farm signal that federated crop-disease detection depends on, together with a cluster-count rule that practitioners can apply before committing to a federation.