https://paglab.org/tag/crop-monitoring/Crop MonitoringHugo Blox Builder (https://hugoblox.com)en-usSun, 01 May 2022 00:00:00 +0000https://paglab.org/media/logo_hu_32055a858e223df5.pnghttps://paglab.org/tag/crop-monitoring/https://paglab.org/project/digicrop-farm-data/Sun, 01 May 2022 00:00:00 +0000https://paglab.org/project/digicrop-farm-data/<h2 id="overview">Overview</h2> <p><strong>DigiCrop Farm Data</strong> is a collaborative project funded through the <strong>Hans Eisenmann-Forum für Agrarwissenschaften (HEF)</strong> at TUM, jointly led by <strong>Prof. Kang Yu</strong> (Precision Agriculture), <strong>Prof. Heinz Bernhardt</strong> (Agricultural Systems Engineering), and <strong>Prof. Timo Oksanen</strong> (Agricultural Robotics and Automation). The project develops <strong>precision farming data analytics</strong> workflows using multi-sensor UAV and field datasets collected at the <strong>TUM Dürnast research farm</strong>, bridging agronomy, sensing, robotics, and data science.</p> <h2 id="objectives">Objectives</h2> <ul> <li><strong>Integrate multi-sensor UAV data</strong> (multispectral, RGB, LiDAR) with ground-based farm records for comprehensive field-scale crop monitoring.</li> <li><strong>Develop data analytics pipelines</strong> for extracting agronomically meaningful insights from heterogeneous precision farming datasets.</li> <li><strong>Assess crop nitrogen status and NUE</strong> using drone remote sensing and field measurements at TUM&rsquo;s experimental farm.</li> <li><strong>Support farm management decisions</strong> by linking remote sensing outputs to fertilization and yield outcomes.</li> </ul> <h2 id="methodology">Methodology</h2> <p>The project combines:</p> <ul> <li> <p><strong>Cross-disciplinary collaboration</strong> between precision agriculture, agricultural engineering, agrimechatronics and robotics groups at TUM</p> </li> <li> <p><strong>Digitize Field experiment data</strong> to enalbe reuse of historical farming data e.g., for enhancing variable nitrogen fertilization applications</p> </li> <li> <p><strong>Data analytics and machine learning</strong> for trait retrieval, canopy characterization, and NUE assessment</p> </li> <li> <p><strong>Mobile sensing and remote sensing data calibration</strong> at TUM&rsquo;s Dürnast research farm for spatial crop monitoring</p> </li> <li> <p><strong>Funded by:</strong> Hans Eisenmann-Forum für Agrarwissenschaften (HEF) Seed Fund 2022</p> </li> </ul> <p><strong>Duration:</strong> 5/2022 – 5/2023</p> <h2 id="related-publications">Related Publications</h2> <ul> <li>Wang et al. (2025). <em>Drone multispectral imaging captures the effects of soil mineral nitrogen on canopy structure and nitrogen use efficiency in wheat.</em> <strong>Computers and Electronics in Agriculture</strong>. <a href="../../publication/wang-2025-cea-drone/">View</a></li> </ul>https://paglab.org/project/greenwindows4_0/Tue, 01 Jan 2019 00:00:00 +0000https://paglab.org/project/greenwindows4_0/<h2 id="overview">Overview</h2> <p><strong>GreenWindows4_0</strong> is a research project funded by the <strong>Federal Ministry of Food and Agriculture (BMEL)</strong>, jointly led by <strong>Prof. Urs Schmidhalter</strong> and <strong>Prof. Kang Yu</strong> at the Technical University of Munich (TUM). The project develops precision tools and workflows for <strong>optimizing nitrogen (N) fertilization</strong> in arable farming, with the dual goal of reducing <strong>greenhouse gas (GHG) emissions</strong> (e.g., N₂O) and <strong>ammonia (NH₃) volatilization</strong> while maintaining crop productivity and N use efficiency.</p> <h2 id="objectives">Objectives</h2> <ul> <li><strong>Optimize N application timing and rates</strong> using satellite and UAV remote sensing to identify application windows that minimize emissions.</li> <li><strong>Monitor crop N status</strong> across field-scale experiments using hyperspectral and multispectral sensors.</li> <li><strong>Develop emissions-aware decision support</strong> linking remote sensing outputs to N management recommendations.</li> <li><strong>Improve N use efficiency (NUE)</strong> at the farm scale through data-driven approaches combining biophysical modelling and machine learning.</li> </ul> <h2 id="methodology">Methodology</h2> <p>The project integrates:</p> <ul> <li><strong>Satellite remote sensing</strong> (e.g., Sentinel-2) for large-area crop N status monitoring and yield estimation</li> <li><strong>UAV-based multispectral and hyperspectral imaging</strong> for high-resolution field phenotyping</li> <li><strong>Radiative transfer modelling</strong> and <strong>machine learning</strong> for robust trait retrieval</li> <li><strong>Field experiments</strong> with variable N fertilization treatments across multiple sites and seasons in Bavaria</li> </ul> <h2 id="project-partners">Project Partners</h2> <ul> <li><strong>Technical University of Munich (TUM)</strong></li> <li><strong>AGRAVIS NetFarming GmbH</strong></li> <li>Funded by: <strong>Federal Ministry of Food and Agriculture (BMEL)</strong></li> </ul> <p><strong>Duration:</strong> 01.01.2019 – 31.12.2022</p> <h2 id="related-publications">Related Publications</h2> <ul> <li>Mokhtari et al. (2025). <em>Satellite-based winter wheat yield estimation with a newly parameterized LUE model based on crop water status and leaf chlorophyll content.</em> <strong>Field Crops Research</strong>. <a href="../../publication/mokhtari-2025-fcr-satellitebased/">View</a></li> </ul>