The objective of the study was to estimate soil moisture (SM) from Sentinel-1 (S-1) satellite images acquired over wetlands. The study was carried out during the years 2015–2017 in the Biebrza Wetlands, situated in north-eastern Poland. At the Biebrza Wetlands, two Sentinel-1 validation sites were established, covering grassland and marshland biomes, where a network of 18 stations for soil moisture measurement was deployed. The sites were funded by the European Space Agency (ESA), and the collected measurements are available through the International Soil Moisture Network (ISMN). The SAR data of the Sentinel-1 satellite with VH (vertical transmit and horizontal receive) and VV (vertical transmit and vertical receive) polarization were applied to SM retrieval for a broad range of vegetation and soil moisture conditions. The methodology is based on research into the effect of vegetation on backscatter (σ°) changes under different soil moisture and Normalized Difference Vegetation Index (NDVI) values. The NDVI was derived from the optical imagery of a MODIS (Moderate Resolution Imaging Spectroradiometer) sensor onboard the Terra satellite. It was found that the state of the vegetation expressed by NDVI can be described by the indices such as the difference between σ° VH and VV, or the ratio of σ° VV/VH, as calculated from the Sentinel-1 images in the logarithmic domain. The most significant correlation coefficient for soil moisture was found for data that was acquired from the ascending tracks of the Sentinel-1 satellite, characterized by the lowest incidence angle, and SM at a depth of 5 cm. The study demonstrated that the use of the inversion approach, which was applied to the newly developed models using Water Cloud Model (WCM) that includes the derived indices based on S-1, allowed the estimation of SM for wetlands with reasonable accuracy (10 vol. %). The developed soil moisture retrieval algorithms based on S-1 data are suited for wetland ecosystems, where soil moisture values are several times higher than in agricultural areas.

The main objective of the presented study was to verify the potential of the Sentinel-5 Precursor (S-5P) Tropospheric NO₂ Column Number Density (NO₂ TVCD) to support air pollution monitoring in Poland. The secondary objective of this project was to establish a relationship between air pollution and meteorological conditions. The ERA-5 data together with the NO₂ TVCD product and auxiliary data were further assimilated into an artificial intelligence model in order to estimate surface NO₂ concentrations. The results revealed that the random forest method was the most accurate method for estimating the surface NO₂. The random forest model demonstrated MAE values of 3.4 μg/m³ (MAPE~37%) and 3.2 μg/m³ (MAPE~31%) for the hourly and weekly estimates, respectively. It was observed that the proposed model could be used for at least 120 days per year due to the cloud-free conditions. Further, it was found that the S-5P NO₂ TVCD was the most important variable, which explained more than 50% of the predictions. Other important variables were the nightlights, solar radiation flux, road density, population, and planetary boundary layer height. The predictions obtained with the proposed model were better fitted to the actual surface NO₂ concentrations than the CAMS median ensemble estimations (~15% better accuracy).

Timely crop yield forecasts at a national level are substantial to support food policies, to assess agricultural production, and to subsidize regions affected by food shortage. This study presents an operational crop yield forecasting system for Poland that employs freely available satellite and agro-meteorological products provided by the Copernicus programme. The crop yield predictors consist of: (1) Vegetation condition indicators provided daily by Sentinel-3 OLCI (optical) and SLSTR (thermal) imagery, (2) a backward extension of Sentinel-3 data (before 2018) derived from cross-calibrated MODIS data, and (3) air temperature, total precipitation, surface radiation, and soil moisture derived from ERA-5 climate reanalysis generated by the European Centre for Medium-Range Weather Forecasts. The crop yield forecasting algorithm is based on thermal time (growing degree days derived from ERA-5 data) to better follow the crop development stage. The recursive feature elimination is used to derive an optimal set of predictors for each administrative unit, which are ultimately employed by the Extreme Gradient Boosting regressor to forecast yields using official yield statistics as a reference. According to intensive leave-one-year-out cross validation for the 2000–2019 period, the relative RMSE for voivodships (NUTS-2) are: 8% for winter wheat, and 13% for winter rapeseed and maize. Respectively, for municipalities (LAU) it equals 14% for winter wheat, 19% for winter rapeseed, and 27% for maize. The system is designed to be easily applicable in other regions and to be easily adaptable to cloud computing environments such as Data and Information Access Services (DIAS) or Amazon AWS, where data sets from the Copernicus programme are directly accessible.

The COVID-19 pandemic has affected many aspects of human well-being including air quality. The present study aims at quantifying this effect by means of ground-level concentrations of NO₂, PM_2.5, as well as aerosol optical depth (AOD) measurements and tropospheric NO₂ column number density (NO₂ TVCD), during the imposed governmental restrictions in spring 2020. The analyses were performed for both urban and non-built-up areas across the whole of Poland accompanied by Warsaw (urban site) and Strzyzow (a background site). The results revealed that mean PM_2.5 concentrations in spring 2020 for urban and non-built-up areas across Poland and for Warsaw were 20%, 23%, 15% lower than the 10-year average, respectively. Analogous mean NO₂ concentrations were lower by 20%, 18%, 30% and NO₂ TVCD revealed 9%, 4%, 9% reductions in 2020 as compared to 2019. Regarding mean AOD, retrieved from MERRA-2 reanalysis, it was found that for the whole of Poland during spring 2020 the reduction in AOD as compared to the 10-year average was 15%. The contribution of the lockdown within total air pollution reduction is not easily assessable due to anomalous weather conditions in 2020 which resulted in advection of clean air masses identified from MERRA-2 reanalysis and Strzyzow observatory.

The Vectorized Earth Observation Retrieval (VEOR) algorithm is a novel algorithm suited to the efficient supervised classification of large Earth Observation (EO) datasets. VEOR addresses shortcomings in well-established machine learning methods with an emphasis on numerical performance. Its characteristics include (1) derivation of classification probability; (2) objective selection of classification features that maximize Cohen’s kappa coefficient ($\kappa$) derived from iterative “leave-one-out” cross-validation; (3) reduced sensitivity of the classification results to imbalanced classes; (4) smoothing of the classification probability field to reduce noise/mislabeling; (5) numerically efficient retrieval based on a pre-computed look-up vector (LUV); and (6) separate parametrization of the algorithm for each discrete feature class (e.g., land cover). Within this study, the performance of the VEOR classifier was compared to other commonly used machine learning algorithms: K-nearest neighbors, support vector machines, Gaussian process, decision trees, random forest, artificial neural networks, AdaBoost, Naive Bayes and Quadratic Discriminant Analysis. Firstly, the comparison was performed using synthetic 2D (two-dimensional) datasets featuring different sample sizes, levels of noise (i.e., mislabeling) and class imbalance. Secondly, the same experiments were repeated for 7D datasets consisting of informative, redundant and insignificant features. Ultimately, the benchmarking of the classifiers involved cloud discrimination using MODIS satellite spectral measurements and a reference cloud mask derived from combined CALIOP lidar and CPR radar data. The results revealed that the proposed VEOR algorithm accurately discriminated cloud cover using MODIS data and accurately classified large synthetic datasets with low or moderate levels of noise and class imbalance. On the contrary, VEOR did not feature good classification skills for significantly distorted or for small datasets. Nevertheless, the comparisons performed proved that VEOR was within the 3–4 most accurate classifiers and that it can be applied to large Earth Observation datasets.

The Copernicus Data Space Ecosystem introduces an innovative approach to accessing large Earth Observation (EO) data through streaming services and APIs. This study elaborates on advantages of the novel data discovery, streaming and access APIs within the Data Space, emphasizing key components such as: STAC catalog, OData and OpenSearch querying APIs, Browser, S3 interface, Jupyter Hub, openEO, and Sentinel Hub’s APIs.The OData (Open Data Protocol) stands as the ISO/IEC approved standard, outlining best practices for designing and utilizing REST APIs. It harmonizes various elements such as request and response headers, status codes, HTTP methods, URL conventions, media types, payload formats, and query options. The OpenSearch catalogue enables the search for Copernicus data through a standardized web service. For technical details, the OpenSearch specification serves as a reference. The results from this web service are delivered as GeoJSON feature collections, with each feature representing an Earth observation 'product' and referencing the location of the actual data.STAC (Spatio-Temporal Asset Catalog) emerges as a cutting-edge EO data management standard with robust data discovery and access capabilities. Built on simple JSON entries with resource-pointing URLs, it boasts flexibility in the types of data stored and accommodates new extensions and capabilities seamlessly. The hierarchical structure includes collections (e.g., Sentinel-2 L2A), subdivided into items representing satellite products. These items further break down into assets corresponding to spectral bands. This detailed STAC catalogue facilitates user searches for specific spectral bands and enables streaming of spatial data subsets using HTTP range requests.JupyterHub is a central platform for managing Jupyter Notebooks, simplifying tasks like resource allocation and user authentication. Copernicus Data Space Ecosystem users get free access, but with limited resources. Jupyter Notebooks offer a user-friendly interface for EO data prototyping, integrating with Python SDKs like Sentinel Hub and OpenEO. They grant direct access to the EO data repository, eliminating dependency hassles with pre-configured kernels for immediate prototyping. Sentinel Hub, a satellite imagery processing service, that excels in on-the-fly actions like gridding, re-projection, mosaicking, etc. It efficiently fetches data for web applications or analytical processes like ML, based on satellite data without replication or pre-processing. Several APIs, including OGC services, contribute to the Data Space Browser for advanced data visualization. Key APIs within the Copernicus Data Space Ecosystem include: BYOC (Bring Your Own COG) API, (Batch) Processing API, (Batch) Statistical API. These APIs empower users to perform diverse tasks, from data ingestion to advanced statistical analyses.OpenEO, revolutionizes geospatial data processing and analysis by offering a unified, interoperable platform for developers, researchers, and scientists. This framework empowers users to address complex geospatial challenges collaboratively, leveraging distributed computing environments and cloud-based resources. The collaborative nature of openEO enables seamless sharing of code, workflows, and data processing methods across platforms, advancing the accessibility, scalability, and reproducibility of Earth Observation (EO) data. OpenEO's intuitive libraries in Python, R, and JavaScript simplify the analysis of diverse datasets. In addition to the SDK, openEO features the Web Editor - an online tool for visually constructing workflows.