Institut für Kulturpflanzenwissenschaften

Permanent URI for this collectionhttps://hohpublica.uni-hohenheim.de/handle/123456789/12

Browse

Browsing Institut für Kulturpflanzenwissenschaften by Person "Abdipourchenarestansofla, Morteza"

Type the first few letters and click on the Browse button
Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    In season estimation of economic optimum nitrogen rate with remote sensing multispectral indices and historical telematics field-operation data
    (2025) Abdipourchenarestansofla, Morteza; Piepho, Hans-Peter
    Accurate estimation and spatial allocation of economic optimum nitrogen (N) rates (EONR) can support sustainable crop production systems by reducing chemical compounds to be applied to the ground while preserving the optimum yield and profitability Smart Farming (SF) techniques such as historical precision agriculture (PA) machinery data, satellite multispectral imagery, and on-machine nitrogen adjustment sensors can bring together state-of-the-art precision in determining EONR. The novelty of this study is in introducing an efficient optimization framework using SF technology to enable real-time and prescription based EONR application execution. An optimization strategy called response surface modelling (RSM) was implemented to support decision making by fusing multiple sources of information while keeping the underlying computation simple and interpretable. Here, a field of winter wheat with an area of 7 ha was used to prove the proposed concept of determining EONR for each location in the field using auxiliary variables called multispectral indices (MSIs) derived from Sentinel 2. Three different image acquisition dates before the actual N application were considered to find the best time combination of MSIs along with the best MSIs to model yield. The best MSIs were filtered out through three phases of feature selection using analysis of variance (ANOVA), Lasso regression, and model reduction of RSM. For the date 2020.03.25, 14 out of 21 MSIs exhibited a significant interaction with the N applied as determined through an on-machine N sensor. For dates 2020.03.30 and 2020.04.04, the numbers of significant indices were identified as 6 and 10, respectively. Some of the MSIs were no longer significant after five days of the growth period (5-day interval between Sentinel 2 revisits). The best model demonstrated an average prediction error of 14.5%. Utilizing the model’s coefficients, the EONR was computed to be between 43 kg/ha and 75 kg/ha for the target field. By incorporating MSIs into the fitted model for a given N range, it was demonstrated that the shape of the yield-N relation (RSM) varied due to field heterogeneity. The proposed analytical approach integrates farmer engagement by participatory annual post-mortem analysis. Using the determined RSM approach, retrospective assessment compares economically optimal N input, based on observed MSIs values to each location, with the actual applied rates.
  • Thumbnail Image
    Publication
    Mapping knowledge domains of regenerative agriculture with a focus on on-farm nitrogen fertilization experimentation and response surface regression
    (2025) Abdipourchenarestansofla, Morteza; Piepho, Hans-Peter
    In the face of growing environmental concerns and the global demand for sustainable agriculture, achieving balanced nitrogen (N) management is critical for both maximizing crop productivity and maintaining environmental health. This dissertation proposes an innovative framework to address this challenge within the scope of regenerative agriculture, which emphasizes sustainable farming practices. Regenerative agriculture aims to reduce chemical inputs while maintaining yield levels yet implementing these practices at scale is complex due to the intricate interactions between biological, environmental, and technological factors on farms. This research tackles these challenges by introducing a Knowledge Domain Mapping (KDM)-based framework, integrating advanced technologies—including remote sensing, Internet of Things (IoT) telemetry, geospatial sciences, statistical modeling, machine learning, and cloud computing—to create a holistic and scalable system for optimizing nitrogen applications. Central to this research is the accurate estimation and spatial allocation of the Economic Optimum Nitrogen Rate (EONR), a crucial element for reducing nitrogen use and enhancing yield. A key contribution of this study is the development of a robust Response Surface Model (RSM) that leverages multispectral indices (MSIs) from Sentinel-2 imagery, historical IoT telemetry data, and on-machine nitrogen sensors. This RSM approach allows for precise EONR predictions tailored to field-specific conditions, reducing the need for traditional plot-based trials and achieving an average prediction error of just 14.5%. Applied to a 7-hectare winter wheat field, the model successfully predicted EONR values ranging from 43 kg/ha to 75 kg/ha across zones, showcasing the adaptability and accuracy of RSM for field-specific nitrogen recommendations. This precisionfocused approach exemplifies the study’s goal of minimizing environmental impacts while ensuring sustainable yield improvements. Beyond the initial field-level implementation, this research examines the generalizability of the RSM framework using two modeling strategies: a single RSM across fields and a weighted average model that aggregates individual field-specific RSMs. The weighted model demonstrated superior adaptability and high prediction accuracy, with a root mean square error (RMSE) of 11 kg N/ha for the EONR, highlighting the framework’s potential for broader application across different agricultural settings. Such generalizability supports the framework’s adoption in diverse farming environments, enabling precise and informed nitrogen management at scale. To facilitate widespread adoption and practical application, the dissertation also introduces a cloud-based infrastructure that integrates the KDM framework with real-time IoT data and satellite imagery. Leveraging cloud services like Amazon Web Services (AWS) Batch for job orchestration, Amazon S3 for scalable data storage, and RDS Postgres for structured data management, this8 infrastructure allows for seamless handling of both real-time and historical data. Spatial interpolation techniques, such as Kriging, enhance the model’s capability to generate real-time nitrogen prescription maps, enabling precise nutrient management for large-scale agricultural operations. Automated data quality control and data harmonization embedded within this cloud architecture provide a strong foundation for managing increasing data volumes and diverse field conditions, making the system cost-effective, adaptable, and efficient for modern agriculture. In summary, this dissertation maps regenerative agriculture via a comprehensive roadmap for translating regenerative agriculture principles into practical, operational nitrogen management practices. Through KDM an interdisciplinary approach is mapped by the integration of advanced modeling, data processing, and cloud technologies. This framework enables sustainable crop management and aligns with global goals for environmentally responsible food production. The innovations introduced here support a scalable, data-driven approach to agricultural sustainability, bridging scientific research with real-world applications to meet the evolving demands of modern agriculture.