@article{10272/27104,
year = {2025},
month = {1},
url = {https://hdl.handle.net/10272/27104},
abstract = {This study estimates agricultural soil variables using a non-parametric machine learning technique based on Lipschitz interpolation. This method is adapted for the first time to learn spatio-temporal dynamics, accounting for two-dimensional spatial and one temporal coordinate inputs separately. The estimator is validated on real agricultural data, addressing challenges like measurement noise and quantization. The experimental setup, including an edge layer with measurement devices and a cloud layer for data storage and processing, is detailed. Despite its simplicity, the method presents a compelling alternative to Gaussian processes and neural networks.},
organization = {This work has been partially supported by Agencia Española de Cooperación Internacional al Desarrollo, Spain (Grant 2022/ACDE/000116), Agencia Estatal de Investigación AEI, Spain (Grants PID2020-117800GB-I00 and RYC2021-032919-I) and by Junta de Andalucía, Spain (Grant PY20-RE-017-LOYOLA). The authors would like to thank Fundación Ayesa for their work involved in the development of the cloud technology, and the complete ODS Research group for their effort in designing and testing the nodes.},
publisher = {Elsevier},
title = {Data-driven spatio-temporal estimation of soil moisture and temperature based on Lipschitz interpolation},
doi = {10.1016/j.isatra.2024.11.018},
author = {Manzano, José María and Orihuela Espina, Diego Luis and Pacheco, Erid Eulogio and Pereira, Mario},
}