Latest SCI publications
Research project (§ 26 & § 27)
Duration : 2021-01-01 - 2022-06-30
The aim of this project is the development of methods for satellite, model and AI-based yield forecasting of agricultural crops in the context of Austrian agriculture. In order to achieve the project goal, the following technologies and methods will be combined or further developed: - Sentinel 2 spectral data (satellite images) will be used as input for the AI component, the reflection model PROSAIL and the crop growth model iCrop. - The AI component will be trained to recognize agricultural crops with manually marked and already available training data from the Austria and USA. The trained model should be able to correctly classify the crop plants visible on the satellite images to 90%. With the reflection model PROSAIL, possible reflection values are calculated by discrete variation of the input values and stored in a database. The reflection values shown in the satellite images are then compared with the values in the database in order to be able to draw conclusions about possible input value combinations and crop plants. - The results of the AI component and the reflection model will be transferred to the fuzzy logic classifier in order to finally determine the crop species. - The identified crop species and growth parameters derived from the spectral data (e.g. Leaf Area Index) are used to calibrate the iCrop model to generate yield forecasts (as well as harvest time, phenology, fertilizer and water requirements).
Basic research on the management of giant hogweed, knotgrass and narrow-leaved ragwort along the Bavarian road system
Research project (§ 26 & § 27)
Duration : 2020-06-30 - 2023-06-29
Giant hogweed (Heracleum mantegazzianum), japanese knotweed (Fallopia japonicum) and narrow-leaved ragwort (Senecio inaequidens) are nowadays three of the economically and ecologically most important invasive alien species in Middle Europe. Conventional methods to eradicate the plants like mowing, mechanical excavation or herbicide application have not proofed to be sufficient to effecitvely contain the further spread of these perennial plant species. Thus, during this three-years-project the effectiveness of two new physical methods of weed management should be tested on four sites in Bavaria (Ampfing, Munich, Gersthofen, Nuremberg). The first system works with hot foam, consisting of sugar tensides and fatty acids (no herbicides!) that forms an isolating layer over the plants, which should secure a longer heat-exposure. Due to this enhanced dwell time, aboveground parts of the plant, paricularly leaves should not only be devitalised but primary should transfer the heat also to belowground parts like rhizoms (japanese knotweed) or storage roots (giant hogweed and narrow-leaved ragwort), which should weeken the plants ability to resprout. In contrast to that, the second system called “rootwave” introduces an electric shock into the plant when touching it. This electric shock goes straight into the xylem of the plants and is therefore transported through the entire plant. Due to the heat, caused by the electric shock plant cells should burst open from leaves and stem down to the roots which should cause a complete mortification of the plant. The aim of the project is therefore to test the optimum application time of these means of weed management in these four different climatic regions in Bavaria. Additionally, it should be revealed how many numbers of annual applications are necessary to achieve not only a significant reduction in population size but also to prohibit the flowering and seed formation, particularly with giant hogweed and narrow-leaved ragwort. A continuous monitoring of the essential development and growth parameters of these plants should provide steady information on the management success.
Research project (§ 26 & § 27)
Duration : 2020-04-01 - 2023-03-31
Climate change poses a major threat to ecosystems all over the globe. Rainfall variability results in more frequently occurring drought events and large yield losses. However, current crop management practices are largely based on empirical approaches representing crop demands in “average seasons” under “average price and market conditions”. While these “average” management practices have been relatively successful in the past, rapidly changing production conditions demand a more tailored, site- and season-specific crop management. This project focuses on the development and evaluation of support tools for decision makers of the Austrian agricultural sector through the integration of site-specific crop modelling, spectral sensing and weather forecasting. First, crop models offer cost-efficient tools to generate temporally-dense data on crop growth and yield, soil water and nutrient content as well as crop demand for inputs such as fertilizers. This provides information not only to practitioners on how to best manage crops in the field, but also to researchers to gain a more detailed understanding of the processes that are responsible for e.g. yield formation, crop nutritional status and water demand. Second, spectral sensing via satellites, drones or ground sampling facilitates the collection of data on crop growth and nutritional status at large to very large scales. This data can be used for improving crop management such as N fertilization and irrigation schemes. And third, since decisions and measures taken in crop management are guided by the prevailing weather conditions, accurate weather forecasts can support a more reliable agronomic planning. The combination of all three can be used to provide pre- and in-season crop management support based on projections at field, farm or regional level for a couple of days, weeks or even months in advance. However, there is still a gap between what scientists consider as “useable” information and what users recognise as “useful” in their decision-making processes. This gap prevents the provided support being suitable for actual climate change adaptation in practical terms. Given that agricultural decision/making is a complex and context-specific process, identifying the perceptions and needs of end-users in regard to decision support and how such tools can be tailored to provide “useful” information to end-users will be the second part of this project. The outcomes of this project will be beneficial to different stakeholders, be it farmers, decision makers from the processing industry, policymakers or researchers: farmers can get specific information on optimal soil management, crop selection, sowing date, plant protection, irrigation and fertilization for individual crops at each site. Accurate yield estimations come with major economic advances for the processing industry and agricultural stock trade. Policymakers will be able to take evidence-based decisions when it comes to agricultural compensation payments or spatial planning. And finally research will benefit from an increased accuracy of crop model simulation to draw precise conclusions upon potential agricultural management improvements.