Opportunities from Unmanned Aerial Vehicles to Identify Differences in Weed Spatial Distribution between Conventional and Conservation Agriculture

Nebojša Nikolić, Pietro Mattivi, Salvatore Eugenio Pappalardo, Cristiano Miele, Massimo De Marchi and Roberta Masin
Additional contact information
Nebojša Nikolić: Department of Agronomy, Food, Natural Resources, Animals and Environment—DAFNAE, University of Padua, 35020 Legnaro, Italy
Pietro Mattivi: Advanced Master in GIScience and UAV for the Integrated Management of Territory and Natural Resources, Department of Civil, Environmental and Architectural Engineering––ICEA, University of Padua, 35100 Padova, Italy
Salvatore Eugenio Pappalardo: Laboratory GIScience and Drones for Good, Department of Civil, Environmental and Architectural Engineering—ICEA, University of Padua, 35100 Padova, Italy
Cristiano Miele: Archetipo s.r.l., 35129 Padova, Italy
Massimo De Marchi: Advanced Master in GIScience and UAV for the Integrated Management of Territory and Natural Resources, Department of Civil, Environmental and Architectural Engineering––ICEA, University of Padua, 35100 Padova, Italy
Roberta Masin: Department of Agronomy, Food, Natural Resources, Animals and Environment—DAFNAE, University of Padua, 35020 Legnaro, Italy

Sustainability, 2022, vol. 14, issue 10, 1-15

Abstract: Weeds are one of the major issues in agricultural production and they are present in most agricultural systems. Due to the heterogeneity of weed distribution, understanding spatial patterns is paramount for precision farming and improving sustainability in crop management. Nevertheless, limited information is currently available about the differences between conventional agricultural (CV) weed spatial patterns and weed spatial patterns in conservation agricultural systems (CA); moreover, opportunities to use unmanned aerial vehicles (UAV) and recognition algorithms to monitor these differences are still being explored and tested. In this work, the opportunity to use UAVs to detect changes in spatial distribution over time between CA and CV fields was assessed for data acquisition. Acquired data were processed using maximum likelihood classification to discriminate between weeds and surrounding elements; then, a similarity assessment was performed using the ‘equal to’ function of the raster calculator. The results show important differences in spatial distribution over time between CA and CV fields. In the CA field 56.18% of the area was infested in both years when the field margin effect was included, and 22.53% when this effect was excluded; on the other hand, in the CV field only 11.50% of the area was infested in both years. The results illustrate that there are important differences in the spatial distribution of weeds between CA and CV fields; such differences can be easily detected using UAVs and identification algorithms combined.

Keywords: plant infestation; remote sensing technology; no-till system; UAV; CA; CV (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/14/10/6324/pdf (application/pdf)
https://www.mdpi.com/2071-1050/14/10/6324/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:14:y:2022:i:10:p:6324-:d:821351

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().