Description: In this article, we propose a deep learning-based algorithm for the classification of crop types from Sentinel-1 and Sentinel-2 time series data which is based on the celebrated transformer architecture. Crucially, we enable our algorithm to do early classification, i.e., predict crop types at arbitrary time points early in the year with a single trained model (progressive intra-season classification). Such early season predictions are of practical relevance for instance for yield forecasts or the modeling of agricultural water balances, therefore being important for the public as well as the private sector. Furthermore, we improve the mechanism of combining different data sources for the prediction task, allowing for both optical and radar data as inputs (multi-modal data fusion) without the need for temporal interpolation. We can demonstrate the effectiveness of our approach on an extensive data set from three federal states of Germany reaching an average F1 score of 0.92 using data of a complete growing season to predict the eight most important crop types and an F1 score above 0.8 when doing early classification at least one month before harvest time. In carefully chosen experiments, we can show that our model generalizes well in time and space.

Description: In the view of increasing water demands in agriculture, efficient water use is a key factor in potato production. The aim of this study was to compare two deficit (80% and 90%) and one abundant (120%) gun sprinkler irrigation levels with the longtime used irrigation level of a farmer (100%). Irrigation was supplied during the 2021 growing season on a loamy sand site in Mecklenburg–Western Pomerania, Germany. Yield and tuber quality of the high-amylopectin potato (HAPP) variety “Waxy/Henriette” were assessed in a three-grade tuber size distribution. Five economic indicators were used to assess the suitability of the investigated irrigation levels to secure economic responses. Yield and starch yield did not significantly differ between the 90% (561.1 dt ha−1 and 102.0 dt ha−1) and the 100% irrigation levels (559.1 dt ha−1 and 102.3 dt ha−1), with total production increasing by 2.0 dt ha−1 and starch production decreasing by 0.4 dt ha−1 at the 90% irrigation level. Tuber lesions decreased the economic responses at all irrigation levels. Potentially, 87,469 m3 of irrigation water (125.8 m3 ha−1) could have been saved on the loamy sand starch potato sites of the local farm (695.3 ha) in 2021.

Description: The Environmental Mapping and Analysis Program (EnMAP) is a spaceborne German hyperspectral satellite mission that aims at monitoring and characterizing the Earth’s environment on a global scale. EnMAP core themes are environmental changes, ecosystem responses to human activities, and management of natural resources. In 2021 major milestones were achieved in the sensor and satellite preparation which is by end-2021 in the final acceptance review and pre-launch phase, with a launch window opening April 2022 (Fischer et al., ESA LPS 2022). Accordingly, the mission science support shifted from science development to pre-launch and launch support. The EnMAP science preparation program has been run for more than a decade to support industrial and mission development, and scientific exploitation of the data by the user community. The program is led by the German Research Center for Geosciences (GFZ) Potsdam supported by several partners and is funded within the German Earth observation program by the DLR Space Agency with resources from the German Federal Ministry for Economic Affairs and Energy (BMWi). In 2020 a new 3+1-year project phase started during which specific activities are performed at the GFZ Potsdam together with the four project partners Humboldt-University (HU) Berlin, Alfred-Wegener Institute (AWI) Bremerhaven, Ludwig Maximilian University (LMU) Munich, and University Greifswald. These activities focus on the preparation for the scientific exploitation of the data by the user community as well as mission support during the commissioning phase and the start of the nominal phase, supported by the EnMAP Science Advisory Group. In this presentation, we aim at providing an update of the current science preparation activities performed at GFZ. This includes an update of the data product validation activities focusing on an independent validation of the EnMAP radiance and reflectance products. For smooth and efficient validation especially during the commissioning phase, a semi-automatic processing chain is being developed (EnVAL), which streamlines the validation sites and in-situ data management as well as the validation tasks and report generation. Also, an update on new resources in the online learning initiative HYPERedu will be presented. In particular, the first Massive Open Online Course (MOOC) on the basics of imaging spectroscopy titled ‘Beyond the Visible – Introduction to Hyperspectral Remote Sensing’ was successfully opened in November 2021. An update will be further provided on the status of algorithms included in the EnMAP-Box related to data pre-processing and derivation of geological and soil mapping. It includes the EnMAP processing tool (EnPT) that is developed as an alternative to the processing chain of the EnMAP ground segment and provides free and open-source features to process EnMAP Level-1B data to Level-2A bottom-of-atmosphere (BOA) reflectance, and the EnMAP geological Mapper (EnGeoMap) and Soil Mapper (EnSoMap) for users in bare Earth and Geosciences applications. Finally, a background mission plan is developed as mission internal to fully exploit the resources of the satellite in terms of functionalities and/or capacities when there are resources available after all user requests have been processed. It can be used to generate time series databases interesting for the user community and anticipate future user needs, or to prototype and validate new mission strategies, such as large mosaicking demonstrations and/or synergies with other hyperspectral missions.

Description: WRaINfo is a software for real-time weather radar data processing developed by the Helmholtz Innovation Lab FERN.Lab, a technology and innovation platform of the German Research Centre for Geosciences Potsdam (GFZ). WRaINfo is specifically designed for processing X-band weather radar data of FURUNO devices. The modules of the package allow to read and process raw data of the WR2120 and WR2100. For this purpose, many functions of the library wradlib are used and adapted. The processing is controlled by a configuration file, main functionalities include formatting, attenuation correction, clutter detection, georeferencing and gridding of the data. This allows the construction of reproducible, automatic data processing chains. The package is written in the Python programming language. The source code is publicly available on GitLab. Compiled versions are also available on PyPi. The package is distributed under the Apache 2.0 license.