RT Journal Article
T1 ⁠Big Data-driven MLOps workflow for annual high-resolution land cover classification models
A1 Burgueño Romero, Antonio Manuel
A1 Barba-González, Cristóbal
A1 Aldana-Montes, José Francisco
K1 Datos masivos
K1 Teledetección
AB Developing an annual and global high-resolution land cover map is one of the most ambitious tasks in remotesensing, with increasing importance due to the continual rise in validated data and satellite imagery. Thesuccess of land cover classification models largely hinges on the data quality, coupled with the application ofBig Data techniques and distributed computing. This is essential for efficiently processing the extensive volumeof available satellite data. However, maintaining the lifecycle of several annual Machine Learning modelspresents a complex challenge. The rise of Machine Learning Operations offers an opportunity to automate themaintenance of these models, a feature particularly beneficial in systems that require generating new modelseach year alongside the continuous integration of validated data. This article details the development of anend-to-end MLOps workflow, meticulously integrating land cover classification models that employ Big Datastrategies for processing large-scale, high-resolution spatial data. The workflow is designed within a Kubernetesenvironment, achieving on-demand auto-scaling, distributed computing, and load balancing. This integrationdemonstrates the practicality and efficiency of managing and deploying models that treat satellite imagery inan automated, scalable framework, thus marking a significant advancement in remote sensing and MLOps.
PB Elsevier
YR 2024
FD 2024-08
LK https://hdl.handle.net/10630/32514
UL https://hdl.handle.net/10630/32514
LA eng
NO Antonio M. Burgueño-Romero, Cristóbal Barba-González, José F. Aldana-Montes, Big Data-driven MLOps workflow for annual high-resolution land cover classification odels,Future Generation Computer Systems, Volume 163, 2025, 107499, ISSN 0167-739X
NO Funding for open access charge: Universidad de Málaga / CBUA
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026