A spatiotemporal ensemble machine learning framework for generating land use/land cover time-series maps for Europe (2000-2019) based on LUCAS, CORINE and GLAD Landsat.

A spatiotemporal machine learning framework for automated prediction and analysis of long-term Land Use/Land Cover dynamics is presented. The framework includes: (1) harmonization and preprocessing of spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including five million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and model variance of predicted probabilities per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model consists of a random forest, gradient boosted tree classifier, and an artificial neural network, with a logistic regressor as meta-learner. The results show that the most important variables for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, long-term surface water probability, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with overall accuracy (a weighted F1-score) of 0.49, 0.63, and 0.83 when predicting 43 (level-3), 14 (level-2), and five classes (level-1). Additional experiments show that spatiotemporal models generalize better to unknown years, outperforming single-year models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest forest loss in large parts of Sweden, the Alps, and Scotland. Positive and negative trends in NDVI in general match the land degradation and land restoration classes, with "urbanization" showing the most negative NDVI trend. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict LULC for years prior to 2000 and beyond 2020. The generated LULC time-series data stack (ODSE-LULC), including the training points, is publicly available via the ODSE Viewer. Functions used to prepare data and run modeling are available via the eumap library for Python.

Alcance total en la certificación de procesos de una unidad de atención primaria de Osakidetza-Servicio Vasco de Salud / Obtaining ISA 9001: 2000 certification for the quality management system in a primary care unit in the Osakidetza-Basque Health Service (Spain)

Objetivo: Implantar la gestión por procesos a todos los procesos en una Unidad de Atención Primaria de Osakidetza. Métodos: Durante 2002 se diseñó en la Red de Atención Primaria de Osakidetza/Servicio Vasco de Salud, a través de grupos multidisciplinarios, un mapa de procesos con 31 procesos: 15 operativos (9 asistenciales y 6 administrativos), 7 de apoyo y 9 de gestión. El diseño se implantó en 4 unidades piloto de atención primaria de Osakidetza, que participaron en el diseño de los procesos y en la definición del sistema de gestión de calidad con norma UNE-EN ISO 9001:2000. Resultados: Se consiguió la certificación de un sistema de gestión unificado, por procesos, un sistema de documentación y un cuadro de indicadores, que refleja a través de 3 años la mejora en los resultados del contrato de gestión clínica, indicadores de prescripción de calidad, percepción de la satisfacción de las personas de la Unidad de Atención Primaria (UAP) de Zumaia-Zestoa-Getaria. Conclusiones: La certificación del sistema de gestión por procesos implantado, ha contribuido a la mejora de los resultados y a una gestión descentralizada y sistematizada de las UAP donde se ha implantado, y ha servido como modelo de gestión para la atención primaria de Osakidetza

Objective: To describe our experience of implementing outcome and process assessment to all the processes in a primary care unit in Osakidetza (Basque Health Service) and to analyze the difficulties and strong points after 3 years of implementation. Methods: In 2002, the Primary Care Network of the Osakidetza/ Basque Health Service designed a process map through multidisciplinary groups. The process map contained 15 operative processes (9 clinical and 6 administrative), 7 support systems and 9 management systems. The design was implemented in 4 primary care units participating in a pilot study to create a unified health system management procedure for primary care services according to the UNE-EN ISO 9001:2000 standard. Results: The primary care service achieved certification of its quality management system to the requirements demanded by the international UNE-EN-ISO 9001-2000 standard. A documentation system was also achieved, along with a set of graphic indicators collected over a 3-year study program that demonstrated improvement in the clinical management of the primary care service, as well as satisfaction among patients treated at the primary care unit of Zumaia-Zestoa-Getaria. Conclusions: Achieving certification for outcome and process assessment has markedly contributed to better patient management outcomes and has led to greater decentralization and systematization of participating primary care units, thus serving as a model of management for primary care in the Basque health service