Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.2
3.7
Journals
Agronomy
Special Issues
Current and Future Technologies for Improving and Re-establishing Mechanical and...
share announcement

Current and Future Technologies for Improving and Re-establishing Mechanical and Low-Input Weed Control

A special issue of Agronomy (ISSN 2073-4395). This special issue belongs to the section "Weed Science and Weed Management".

Deadline for manuscript submissions: closed (20 December 2022) | Viewed by 4312

Special Issue Editors

Dr. Gerassimos Peteinatos

E-Mail
Guest Editor
Institute of Soil & Water Resources, Department of Agricultural Engineering, Hellenic Agricultural Organization - Demeter, 11145 Athens, Greece
Interests: precision farming; sensors in agriculture; robotics; mechanical weed management; AI; hyperspecral data; innovation technologies
Special Issues, Collections and Topics in MDPI journals
Dr. Dionisio Andújar

E-Mail Website
Guest Editor
CSIC-UPM - Centro de Automatica y Robotica (CAR), 28500 Madrid, Spain
Interests: robotics; artificial perception; plant crop monitoring; agricultural machinery
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Mechanical weed control has been used for centuries. Its labor intensity, combined with its small application window, has decreased its benefits compared with other methods such as herbicides. Nowadays, interest in mechanical weed control has been re-established. It can be used as an alternative to reduce the in-field chemical inputs and residues in the food chain, which are demanded by both society and legislation. It can also be a tool for reducing herbicide resistance weed populations and, under the proper usage, improve the soil characteristics during the cultivation period. New technologies, such as sensor information, advanced recognition systems, big data, and neural networks also have applications in mechanical weed control. Robotic implements and swarms of robots can also be used for that purpose. These tools can improve the various aspects of mechanical weeding, improve its applicability, increase the labor efficiency, reduce its adverse effects (e.g., corrosion, CO2 exchange), increase the biodiversity, form part of an integrated weed management approach, and re-establish it as a competitive option and solution. In the current Special Issue, we invite the submission of current and novel work which presents the utilization of novel methodologies and new technologies for mechanical weed control and other purposes related to decreasing the use of chemicals. The usage of different perception and actuation technologies for improving mechanical weed control and its integration into farm management, such as, for example, precision harrowing and hoeing, are welcome.

Dr. Gerassimos Peteinatos
Dr. Dionisio Andújar
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Agronomy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • sensors
  • neural networks
  • harrowing
  • howing
  • big data
  • automation
  • site-specific field management
  • robotic

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 2989 KiB  
Article
Intelligent Weed Management Based on Object Detection Neural Networks in Tomato Crops
by Juan Manuel López-Correa, Hugo Moreno, Angela Ribeiro and Dionisio Andújar
Agronomy 2022, 12(12), 2953; https://doi.org/10.3390/agronomy12122953 - 24 Nov 2022
Cited by 8 | Viewed by 2636
Abstract
As the tomato (Solanum lycopersicum L.) is one of the most important crops worldwide, and the conventional approach for weed control compromises its potential productivity. Thus, the automatic detection of the most aggressive weed species is necessary to carry out selective control [...] Read more.
As the tomato (Solanum lycopersicum L.) is one of the most important crops worldwide, and the conventional approach for weed control compromises its potential productivity. Thus, the automatic detection of the most aggressive weed species is necessary to carry out selective control of them. Precision agriculture associated with computer vision is a powerful tool to deal with this issue. In recent years, advances in digital cameras and neural networks have led to novel approaches and technologies in PA. Convolutional neural networks (CNNs) have significantly improved the precision and accuracy of the process of weed detection. In order to apply on-the-spot herbicide spraying, robotic weeding, or precise mechanical weed control, it is necessary to identify crop plants and weeds. This work evaluates a novel method to automatically detect and classify, in one step, the most problematic weed species of tomato crops. The procedure is based on object detection neural networks called RetinaNet. Moreover, two current mainstream object detection models, namelyYOLOv7 and Faster-RCNN, as a one and two-step NN, respectively, were also assessed in comparison to RetinaNet. CNNs model were trained on RGB images monocotyledonous (Cyperus rotundus L., Echinochloa crus galli L., Setaria verticillata L.) and dicotyledonous (Portulaca oleracea L., Solanum nigrum L.) weeds. The prediction model was validated with images not used during the training under the mean average precision (mAP) metric. RetinaNet performed best with an AP ranging from 0.900 to 0.977, depending on the weed species. Faster-RCNN and YOLOv7 also achieved satisfactory results, in terms of mAP, particularly through data augmentation. In contrast to Faster CNN, YOLOv7 was less precise when discriminating monocot weed species. The results provide a better insight on how weed identification methods based on CNN can be made more broadly applicable for real-time applications. Full article
(This article belongs to the Special Issue Current and Future Technologies for Improving and Re-establishing Mechanical and Low-Input Weed Control)
►▼ Show Figures

Figure 1

13 pages, 682 KiB  
Article
A New Approach for Timing Post-Emergence Weed Control Measures in Crops: The Use of the Differential Form of the Emergence Model
by Jordi Izquierdo, Clara Prats, Montserrat Gallart and Daniel López
Agronomy 2022, 12(11), 2896; https://doi.org/10.3390/agronomy12112896 - 19 Nov 2022
Viewed by 1161
Abstract
Models based on thermal or hydrothermal time are used to predict the seedling emergence pattern of weeds. These models rely on sigmoidal functions such as Gompertz, Weibull or logistic, in which daily soil temperature and moisture data are inputs and the percentage of [...] Read more.
Models based on thermal or hydrothermal time are used to predict the seedling emergence pattern of weeds. These models rely on sigmoidal functions such as Gompertz, Weibull or logistic, in which daily soil temperature and moisture data are inputs and the percentage of total expected emergences is the output. The models give good predictions at local and regional scales but they lose accuracy when extrapolated to different geographic areas from where the equations were developed. They also must be validated prior to their release and have subjectivity of the date to start the accumulation of the degree-days. We propose the use of the differential form of the function rather than the integrated form. Under this approach, the starting date to accumulate degree-days is set to the week before the first weed emergence is recorded (if recorded on a weekly basis) and emergence predictions only rely on the current sigmoidal relationship between data recordings. When the weed emergence rate in the field decreases, the relationship between data recordings and time, measured either as thermal or hydrothermal degrees, starts to decrease. When the derivative of the emergence over time falls below a threshold that should be set up based on our knowledge of the economic threshold of the species, a post-emergence weed control measure should be carried out. Under this approach, weekly counts of weeds must be recorded until the derivative reaches the threshold. This approach has been checked on 39 data sets of different weeds in different crops and seasons by applying the differential form of the Gompertz function, obtaining a correlation of 0.99 between the predicted and the observed emergence. The methodology could be particularly useful when timing control measures in cropping areas with unknown or very little knowledge of the species and their emergence pattern. Full article
(This article belongs to the Special Issue Current and Future Technologies for Improving and Re-establishing Mechanical and Low-Input Weed Control)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop