Exportar Publicação

Mateus, C. A. G., Noetzold, D., Skolik, J. M. B., Leithardt, V. R. Q. & de Paz, J. F. (2026). A low-cost IoT architecture for micro-zone climate prediction and meteorological forecasting. Electronics. 15 (14)

C. A. Mateus et al.,  "A low-cost IoT architecture for micro-zone climate prediction and meteorological forecasting", in Electronics, vol. 15, no. 14, 2026

@article{mateus2026_1788117430984,
	author = "Mateus, C. A. G. and Noetzold, D. and Skolik, J. M. B. and Leithardt, V. R. Q. and de Paz, J. F.",
	title = "A low-cost IoT architecture for micro-zone climate prediction and meteorological forecasting",
	journal = "Electronics",
	year = "2026",
	volume = "15",
	number = "14",
	doi = "10.3390/electronics15143102",
	url = "https://www.mdpi.com/journal/electronics"
}

TY  - JOUR
TI  - A low-cost IoT architecture for micro-zone climate prediction and meteorological forecasting
T2  - Electronics
VL  - 15
IS  - 14
AU  - Mateus, C. A. G.
AU  - Noetzold, D.
AU  - Skolik, J. M. B.
AU  - Leithardt, V. R. Q.
AU  - de Paz, J. F.
PY  - 2026
SN  - 2079-9292
DO  - 10.3390/electronics15143102
UR  - https://www.mdpi.com/journal/electronics
AB  - This article presents the design and deployment of ClimaBogotá v1.2, a climate prediction system tailored for high-altitude urban micro-zones in Bogotá, Colombia. The system combines low-cost IoT sensing, machine learning modeling, and cloud-based orchestration to enable scalable and affordable meteorological forecasting. Its architecture comprises Raspberry Pi-based weather stations, a Random Forest model trained on engineered temporal features, and an n8n-driven automation pipeline for real-time inference and dissemination via Telegram, PostgreSQL, and Grafana. With a Mean Absolute Error of 2.59 °C and an R2 of 0.6286 on a 30 min forecast horizon, the system demonstrates both predictive reliability and operational feasibility using free-tier cloud resources. Unlike traditional weather systems, ClimaBogotá emphasizes modularity, adaptability, and cost-efficiency, offering a replicable framework for decentralized climate monitoring in data-scarce urban environments. Temporal misalignment between sensor nodes was identified as the primary constraint, informing future enhancements toward distributed learning strategies.
ER  -