Search

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

The assessment of the potential use of renewable energy resources requires reliable and precise data inputs for sustainable energy planning on a regional, national and local scale. In this study, we examine high spatial resolution grids of potential insolation and solar duration in order to determine the location of potential solar power plants in Montenegro. Grids with a 25-m spatial resolution of potential solar radiation and duration were produced based on observational records and publicly available high-resolution digital elevation model provided by the European Environment Agency. These results could be further used for the estimation and selection of a specific location for solar panels. With an average annual potential insolation of 1800 kWh/m² and solar duration of over 2000 h per year for most of its territory, Montenegro is one of the European countries with the highest potential for the development, production, and consumption of solar energy.

During the establishment of first order trigonometric network in Serbia, the influence of Earth’s gravitational field on measurements was not considered. As a consequence, all points have position errors. With additional measurements and calculations, these errors were later determined for X and Y coordinates of each point. This paper uses geostatistical methods (regression kriging) to estimate error prediction model for any location in Serbia.