Can Commercial Low-Cost Drones and Open-Source GIS Technologies Be Suitable for Semi-Automatic Weed Mapping for Smart Farming? A Case Study in NE Italy

Weed management is a crucial issue in agriculture, resulting environmental in-field and off-field impacts. Within Agriculture 4.0, adoption of UASs combined with spatially explicit approaches may drastically reduce doses herbicides, increasing sustainability weed management. However, 4.0 technologies are barely adopted small-medium size farms. Recently, small low-cost UASs, together open-source software packages, represent system to map distribution crop fields. The general aim by replicable workflow, completely based on open GIS algorithms: OpenDroneMap, QGIS, SAGA OpenCV classification algorithms. Specific objectives are: (i) testing UAS for mapping; (ii) assessing packages semi-automatic classification; (iii) performing sustainable scenario prescription maps. Results showed high performances along the whole process: orthomosaic generation at very spatial resolution (0.01 m/pixel), detection (Matthews Correlation Coefficient: 0.67–0.74), production maps, reducing herbicide treatment only 3.47% entire field. This study reveals feasibility software, enabling approach farmlands.