Research

The aim of this project is to evaluate whether conservation agriculture can increase soil health compared to conventional agriculture while maintaining the same yield level and stability, or whether there are trade-offs between these effect sizes. A field experiment established at UFT Tulln in 2015 is used for this purpose. The following two systems are compared: (i) a system with local conventional crop rotation (sugar beet-winter wheat-maize-winter wheat) and turning tillage and (ii) a conservation system with an eight-crop rotation (sugar beet-winter wheat-maize-soybean-winter wheat-sunflower-winter legume-winter wheat), reduced tillage and extended intercropping. The trial will be in its ninth harvest year in 2023; system effects can therefore be expected in the meantime. The following soil health parameters will be evaluated at two soil depths: (i) total soil carbon and nitrogen pools, (ii) microbial biomass, (iii) available organic carbon and nitrogen, (iv) nitrogen mineralization potential, (v) potential enzyme activity and (vi) aggregate stability. In addition, the two systems are evaluated with regard to their humus balance and nitrogen use efficiency. Furthermore, yield data for all crops over the entire trial period can be used; this allows a pairwise comparison of the yields of sugar beet, winter wheat and maize, which are grown in both systems after the same previous crops.

As part of the Green Deal, agriculture faces the challenge of climate neutrality by reducing emissions and sequestering carbon in soils. Within the EU Soil Strategy ecosystem functions of healthy soils contributing to climate change mitigation and adaptation should be achieved. However, currently there are hardly any realistic implementation strategies for these goals within crop production. As a new approach, the EU “Mission Soil Health” defines lighthouse farms as innovation drivers for achieving the climate and soil goals of the Green Deal. In the project SoilPioneers 2050, a national network of lighthouse farms is being set up at 60 locations, covering the most important soil and climate types as well as farming types in Austria. Modern scientific instruments are established on-farm to specifically monitor the soil functions of climate protection, nutrient efficiency, erosion protection and climate change adaptation. The potential for optimizing soil health through regenerative and agroecological practices compared to current agricultural state-of-the art systems, particularly with regard to efficient carbon, nitrogen and water cycles, is recorded through comprehensive soil indicator assessment. Based on the measured indicators, a soil quality model is developed that quantifies the management advance achieved for the individual soil functions and supports the farmers in further management optimization. A new platform will be used to process satellite data for soil organic matter balancing and assessment of crop resilience to heat/drought stress. By integrating crop-based remote sensing data into the soil quality model, the soil function assessment is improved and linked to progress made in climate change adaptation of crop production within the lighthouse farm network. Based on the improvements recorded in soil organic matter formation, nutrient and water efficiency as well as crop resilience achieved by the lighthouse farms, new simulation models will be used to develop improved estimates of climate and soil protection potentials through management innovation in arable farming within the framework of the Green Deal goals and future climate scenarios. By integrating innovative agricultural practice and research in a lighthouse farmer network, the project offers practical management solutions for the national implementation of the Green Deal goals, thereby also providing an important Europe-wide exemple for future-oriented climate action in agriculture.

The world faces a growing risk of food shortages due to climate change and the increasing global population. Digital transformation of agriculture holds the potential for creating efficient, resilient and eco-friendly crop production systems. In recent years, automatic monitoring methods based on different imaging technologies (e.g., hyperspectral, thermal imaging) have been successfully applied to identify drought in plants, detect decay in fruits and other tasks. As such, they have proven to be valuable tools for achieving sustainability in agricultural systems. Established methods, however, mostly rely on using a single imaging technology at once. This neglects the potential of complementary information that could be obtained with multiple cameras and could lead to improved monitoring accuracy. Thus, the goal of this dissertation project is to utilize multiple camera technologies simultaneously for the monitoring of crop production processes and to develop powerful multimodal machine learning techniques to precisely predict relevant target traits. In this project, the input modalities are represented by different imaging technologies (e.g., thermal camera for temperature, hyperspectral camera for waveband information (incl. visible light), lidar camera for depth information). To demonstrate that the developed machine learning methods are generalizable, they will be evaluated in three real-world use cases, which represent the entire spectrum of the “One Health” concept: 1) health/fertility assessment of soil, 2) detection of nutrient deficiency in plants, 3) early detection of decay in fruits and vegetables. Contributions of this thesis will be 1) the design of novel multimodal machine learning techniques for the prediction of biological traits from multiple camera modalities based on deep learning methodology, 2) the development of modality fusion methods that enable robustness to missing modalities and allow for the joint prediction of multiple traits, 3) the detailed evaluation of practical feasibility and level of improvement over unimodal methods in real-world use cases. With the developed methods, this dissertation aims to make a contribution to a more secure global food supply.