Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems

TL;DR

This work tackles crop yield forecasting under data heterogeneity, privacy constraints, and uneven connectivity in smart agriculture. It introduces a hierarchical federated learning framework with a seasonal crop-type subscription and a three-layer architecture, comprising client farms, crop-specific aggregators, and a global model aggregator. The approach yields cluster models $\theta_k$ that are integrated into a global model $w_{global}$ via $w_{global} = \sum_{k=1}^K \alpha_k \theta_k$ with $\alpha_k = \frac{N_k}{\sum_j N_j}$, enabling both crop-level personalization and cross-crop knowledge sharing. Experiments on synthetic, multi-crop data demonstrate that local and crop-layer models closely track yield patterns and outperform a standalone global model and standard baselines, while reducing communication and preserving data privacy.

Abstract

In this paper, we presents a novel hierarchical federated learning architecture specifically designed for smart agricultural production systems and crop yield prediction. Our approach introduces a seasonal subscription mechanism where farms join crop-specific clusters at the beginning of each agricultural season. The proposed three-layer architecture consists of individual smart farms at the client level, crop-specific aggregators at the middle layer, and a global model aggregator at the top level. Within each crop cluster, clients collaboratively train specialized models tailored to specific crop types, which are then aggregated to produce a higher-level global model that integrates knowledge across multiple crops. This hierarchical design enables both local specialization for individual crop types and global generalization across diverse agricultural contexts while preserving data privacy and reducing communication overhead. Experiments demonstrate the effectiveness of the proposed system, showing that local and crop-layer models closely follow actual yield patterns with consistent alignment, significantly outperforming standard machine learning models. The results validate the advantages of hierarchical federated learning in the agricultural context, particularly for scenarios involving heterogeneous farming environments and privacy-sensitive agricultural data.

Figures (3)

• Figure 1: The architecture of the hierarchical federated learning model
• Figure 2: Number of clients per crop type
• Figure 3: Comparison between the different models for 3 chosen crops (Corn, Wheat, and Cotton)