Decentralized Weather Forecasting via Distributed Machine Learning and Blockchain-Based Model Validation

--Weather forecasting plays a vital role in disaster preparedness, agriculture, and resource management, yet current centralized forecasting systems are increasingly strained by security vulnerabilities, limited scalability, and susceptibility to single points of failure. T o address these challenges, we propose a decentralized weather forecasting framework that integrates Federated Learning (FL) with blockchain technology. FL enables collaborative model training without exposing sensitive local data, this approach enhances privacy and reduces data transfer overhead. Meanwhile, the Ethereum blockchain ensures transparent and dependable verification of model updates. T o further enhance the system's security, we introduce a reputation-based voting mechanism that assesses the trustworthiness of submitted models while utilizing the Interplanetary File System (IPFS) for efficient off-chain storage. Experimental results demonstrate that our approach not only improves forecasting accuracy but also enhances system resilience and scalability, making it a viable candidate for deployment in real-world, security-critical environments. Weather forecasting is essential for agricultural productivity, disaster preparedness, and economic stability. However, traditional forecasting methods tend to rely on centralized systems. This centralization poses significant risks, including vulnerabilities to data manipulation, privacy breaches, and single points of failure [8]. Centralized Machine Learning (ML) models, despite their high accuracy, are vulnerable to adversarial threats, such as data poisoning, where attackers introduce incorrect data to compromise forecast reliability [32]. Reliable weather forecasting systems are foundational to sectors like the insurance industry, where the integrity of environmental data directly influences risk assessment and claim processing.