On the Impact of Data Heterogeneity in Federated Learning: A Case Study on Air Quality Prediction

An Investigation of Federated Learning for Air Quality Forecasting and Monitoring

There are significant gaps that remain in terms of model interpretability and the ability to generalize across climate variations, so this article provides a relatively comprehensive overview of the application of federated learning in air quality forecasting and monitoring.

Implementation and Validation of an Air Quality Prediction Model Based on Federated Learning

This study confirms that FL is a feasible method for distributed air quality prediction, and the key point is to establish a prediction model, not to change the algorithm.

The Impact of Data Preprocessing on Federated Learning for Air Quality Prediction: A Comparative Study of Imputation Methods

Data preprocessing plays a foundational role in machine learning, but it receives limited systematic attention in federated learning (FL) environments. This study empirically compares four missing value strategies using the UCI dataset: direct deletion, mean imputation, K-Nearest Neighbors (KNN) imputation, and Random Forest (RF) imputation. The setup uses a federated framework with five clients, each running a multi layer perceptron model. The findings show direct deletion achieves the strongest performance, with a mean absolute error of 0.173 and an  of 0.966, clearly exceeding imputation methods (the errors around 0.25). The NMHC(GT) feature has an 88.4% missing rate, making imputation unreliable and introducing noise. Although direct deletion reduces the sample from 7,674 to 827 observations, it safeguards data integrity. This research shows that preserving data quality should take priority over quantity when the missing rates are exceptionally high, providing the practical guidance for robust preprocessing design in federated learning systems.

Privacy-Preserving Crop Disease Prediction using Federated Meta-Learning and Climate Intelligence

The growing diversity of climate conditions and the scale effects of agricultural data pose serious problems for the accuracy and scalability of crop disease prediction. The drawbacks of traditional centralized machine learning methods include limitations caused by data privacy, low generalization, and high communication overheads. To overcome these challenges, in this study, we propose a new federated meta-learning with climate-driven personalization (FML-CDP) system that incorporates federated learning, meta-learning, and climate-sensitive modelling in a single architecture. The suggested system allows decentralized and distributed training to several farms without losing data privacy and addresses non-identically distributed (non-IID) data. The framework is more accurate in terms of predictions and more context-aware by using multimodal inputs, such as leaf images, IoT sensor data, and climate variables. The meta-learning aspect allows for quick local farm adjustments and individual predictions. The proposed model outperformed the baseline approach, achieving an accuracy of 97.3% and an F1-score of 0.96, surpassing the performance of centralised convolutional neural networks (CNN), FedAvg, and meta-learning models. Another benefit of climate intelligence is that it enhances resilience and flexibility of the system. The proposed framework offers privacy-saving, scalable, and efficient next-generation smart agricultural systems.

Exploring aggregation strategies for federated learning in national statistics 1

Privacy-preserving load forecasting in smart grids using federated learning: a comparative analysis of aggregation strategies

Experimental results on real-world energy consumption datasets demonstrate that the proposed FL framework achieves competitive forecasting accuracy while preserving client data privacy, and a rigorous comparative analysis reveals that FedProx and FedTrimmedAvg consistently outperform FedAvg under non-IID conditions.