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

2025-10-14

AI Summary

To address data privacy sensitivity, high communication overhead, and strong farm heterogeneity in intelligent agriculture yield forecasting, this paper proposes a hierarchical federated learning framework tailored for smart agriculture. The framework introduces a seasonal crop-cluster dynamic clustering mechanism to enable adaptive farm grouping based on crop type and growth stage; designs a three-tier federated architecture (device–farm–crop layers) with cross-layer model aggregation to balance local specialized modeling and global knowledge sharing; and integrates temporal modeling to enhance trend prediction capability. Experiments demonstrate that the method preserves data locality while significantly reducing communication costs. Both local and crop-layer models achieve superior yield trend fitting accuracy compared to conventional centralized and standard federated learning baselines, validating the framework’s effectiveness and practicality in heterogeneous agricultural settings.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Developing hierarchical federated learning for crop yield prediction in agriculture
• Enabling local crop specialization while maintaining data privacy protection
• Addressing heterogeneous farming environments with reduced communication overhead

Innovation

• Hierarchical federated learning for crop yield prediction
• Three-layer architecture with crop-specific aggregators
• Seasonal subscription mechanism for farm clusters