scholarly journals UAV-Assisted Thermal Infrared and Multispectral Imaging of Weed Canopies for Glyphosate Resistance Detection

2021 ◽  
Vol 13 (22) ◽  
pp. 4606
Author(s):  
Austin Eide ◽  
Cengiz Koparan ◽  
Yu Zhang ◽  
Michael Ostlie ◽  
Kirk Howatt ◽  
...  
Keyword(s):  
Maximum Likelihood ◽  
Weed Management ◽  
Management Practices ◽  
Multispectral Imaging ◽  
Glyphosate Resistance ◽  
Random Trees ◽  
Field Conditions ◽  
Support Vector ◽  
Classification Methods ◽  
Continuous Growth

The foundation of contemporary weed management practices in many parts of the world is glyphosate. However, dependency on the effectiveness of herbicide practices has led to overuse through continuous growth of crops resistant to a single mode of action. In order to provide a cost-effective weed management strategy that does not promote glyphosate-resistant weed biotypes, differences between resistant and susceptible biotypes have to be identified accurately in the field conditions. Unmanned Aerial Vehicle (UAV)-assisted thermal and multispectral remote sensing has potential for detecting biophysical characteristics of weed biotypes during the growing season, which includes distinguishing glyphosate-susceptible and glyphosate-resistant weed populations based on canopy temperature and deep learning driven weed identification algorithms. The objective of this study was to identify herbicide resistance after glyphosate application in true field conditions by analyzing the UAV-acquired thermal and multispectral response of kochia, waterhemp, redroot pigweed, and common ragweed. The data were processed in ArcGIS for raster classification as well as spectral comparison of glyphosate-resistant and glyphosate-susceptible weeds. The classification accuracy between the sensors and classification methods of maximum likelihood, random trees, and Support Vector Machine (SVM) were compared. The random trees classifier performed the best at 4 days after application (DAA) for kochia with 62.9% accuracy. The maximum likelihood classifier provided the highest performing result out of all classification methods with an accuracy of 75.2%. A commendable classification was made at 8 DAA where the random trees classifier attained an accuracy of 87.2%. However, thermal reflectance measurements as a predictor for glyphosate resistance within weed populations in field condition was unreliable due to its susceptibility to environmental conditions. Normalized Difference Vegetation Index (NDVI) and a composite reflectance of 842 nm, 705 nm, and 740 nm wavelength managed to provide better classification results than thermal in most cases.

scholarly journals Weed Mapping in Vineyards Using RGB-D Perception

2021 ◽  
Vol 9 (1) ◽  
pp. 30
Author(s):  
Dimitrios Kateris ◽  
Damianos Kalaitzidis ◽  
Vasileios Moysiadis ◽  
Aristotelis C. Tagarakis ◽  
Dionysis Bochtis
Keyword(s):  
Weed Management ◽  
Management Practices ◽  
Field Conditions ◽  
Yield Losses ◽  
Weed Mapping ◽  
Significant Yield ◽  
Different Levels

Weed management is one of the major challenges in viticulture, as long as weeds can cause significant yield losses and severe competition to the cultivations. In this direction, the development of an automated procedure for weed monitoring will provide useful data for understanding their management practices. In this work, a new image-based technique was developed in order to provide maps based on weeds’ height at the inter-row path of the vineyards. The developed algorithms were tested in many datasets from vineyards with different levels of weed development. The results show that the proposed technique gives promising results in various field conditions.

scholarly journals Assessing weeds at risk of evolving glyphosate resistance in Australian sub-tropical glyphosate-resistant cotton systems

2011 ◽  
Vol 62 (11) ◽  
pp. 1002 ◽  
Author(s):  
Jeff Werth ◽  
David Thornby ◽  
Steve Walker
Keyword(s):  
High Risk ◽  
Weed Management ◽  
Management Practices ◽  
Cropping Systems ◽  
Cropping System ◽  
Glyphosate Resistance ◽  
Management Approach ◽  
Weed Species ◽  
Summer Fallow ◽  
Very High

Glyphosate resistance will have a major impact on current cropping practices in glyphosate-resistant cotton systems. A framework for a risk assessment for weed species and management practices used in cropping systems with glyphosate-resistant cotton will aid decision making for resistance management. We developed this framework and then assessed the biological characteristics of 65 species and management practices from 50 cotton growers. This enabled us to predict the species most likely to evolve resistance, and the situations in which resistance is most likely to occur. Species with the highest resistance risk were Brachiaria eruciformis, Conyza bonariensis, Urochloa panicoides, Chloris virgata, Sonchus oleraceus and Echinochloa colona. The summer fallow and non-irrigated glyphosate-resistant cotton were the highest risk phases in the cropping system. When weed species and management practices were combined, C. bonariensis in summer fallow and other winter crops were at very high risk. S. oleraceus had very high risk in summer and winter fallow, as did C. virgata and E. colona in summer fallow. This study enables growers to identify potential resistance risks in the species present and management practices used on their farm, which will to facilitate a more targeted weed management approach to prevent development of glyphosate resistance.

scholarly journals Evaluación de cuatro algoritmos de clasificación de imágenes satelitales Landsat-8 y Sentinel-2 para la identificación de cobertura boscosa en paisajes altamente fragmentados en Costa Rica

2020 ◽  
pp. 37
Author(s):  
I.D. Ávila-Pérez ◽  
E. Ortiz-Malavassi ◽  
C. Soto-Montoya ◽  
Y. Vargas-Solano ◽  
H. Aguilar-Arias ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Costa Rica ◽  
Maximum Likelihood ◽  
Forest Cover ◽  
Support Vector ◽  
Classification Algorithms ◽  
Landsat 8 ◽  
Classification Methods ◽  
Global Accuracy ◽  
Sentinel 2

<p>Mapping of land use and forest cover and assessing their changes is essential in the design of strategies to manage and preserve the natural resources of a country, and remote sensing have been extensively used with this purpose. By comparing four classification algorithms and two types of satellite images, the objective of the research was to identify the type of algorithm and satellite image that allows higher global accuracy in the identification of forest cover in highly fragmented landscapes. The study included a treatment arrangement with three factors and six randomly selected blocks within the Huetar Norte Zone in Costa Rica. More accurate results were obtained for classifications based on Sentinel-2 images compared to Landsat-8 images. The best classification algorithms were Maximum Likelihood, Support Vector Machine or Neural Networks, and they yield better results than Minimum Distance Classification. There was no interaction among image type and classification methods, therefore, Sentinel-2 images can be used with any of the three best algorithms, but the best result was the combination of Sentinel-2 and Support Vector Machine. An additional factor included in the study was the image acquisition date. There were significant differences among months during which the image was acquired and an interaction between the classification algorithm and this factor was detected. The best results correspond to images obtained in April, and the lower to September, month that corresponds with the period of higher rainfall in the region studied. The higher global accuracy identifying forest cover is obtained with Sentinel-2 images from the dry season in combination with Maximum Likelihood, Support Vector Machine, and Neural Network image classification methods.</p>

Consultant's Perspective on the Evolution and Management of Glyphosate-Resistant Kochia (Kochia scoparia) in Western Kansas

2015 ◽  
Vol 29 (2) ◽  
pp. 318-328 ◽  
Author(s):  
Amar S. Godar ◽  
Phillip W. Stahlman
Keyword(s):  
Weed Management ◽  
Online Survey ◽  
Management Practices ◽  
Production Systems ◽  
Glyphosate Resistance ◽  
Kochia Scoparia ◽  
Survey Period ◽  
Crop Fields ◽  
No Till

Glyphosate is the leading herbicide used in glyphosate-resistant (GR) crops and no-till production systems. Evolved resistance to glyphosate in kochia was first reported in Kansas in 2007. Shortly thereafter, GR kochia became prevalent in western Kansas. An online survey of crop consultants was conducted in fall 2012 to gain their perspectives on evolving glyphosate resistance in kochia in western Kansas, to gather information on how grower weed management practices have changed from before to after occurrence of GR kochia, and to assess the effectiveness of management practices used during 2011 to 2012. Results of the survey indicated increasing infestation of kochia from prior to 2007 (present in 47% of fields) through 2012 (present in 70% of fields). It was estimated that greater than one-third of the cropland in western Kansas was thought to be infested with GR kochia by 2012. Growers increased glyphosate use rates from an average of 0.8 to 1.22 kg ae ha−1and application frequencies from 2.0 to 2.9 from the period before 2007 to 2012. The spread of GR kochia has resulted in changing weed management practices. During the survey period, growers reduced the exclusive use of glyphosate from 49 to 15% for GR crop fields and diversified weed management practices. Though other herbicides in addition to or in place of glyphosate were often applied prior to kochia emergence and were effective in more than half the fields, at least one-fourth of respondents reported inconsistent results with alternative kochia control practices other than tillage. These results are educational and helpful in developing both proactive and reactive tactics to manage GR kochia.

Benchmark Study: II. A 2010 Survey to Assess Grower Awareness of and Attitudes toward Glyphosate Resistance

2012 ◽  
Vol 26 (3) ◽  
pp. 531-535 ◽  
Author(s):  
Joby M. Prince ◽  
David R. Shaw ◽  
Wade A. Givens ◽  
Michael E. Newman ◽  
Micheal D. K. Owen ◽  
...  
Keyword(s):  
Weed Management ◽  
Management Practices ◽  
Glyphosate Resistance ◽  
The South ◽  
Cross Sectional ◽  
Benchmark Study ◽  
Geographic Regions ◽  
On Farm

A 2010 survey of 1,299 corn, cotton, and soybean growers was conducted to determine their attitudes and awareness regarding glyphosate-resistant (GR) weeds and resultant implications on weed management practices. An additional 350 growers included in the current study participated in a 2005 survey, and these answers were compared across time so that cross-sectional and longitudinal comparisons of responses could be made. Most growers surveyed in 2010 were aware of the potential for weeds to evolve resistance to glyphosate; however, many growers were not aware of glyphosate resistance in specific weeds in their county or state. Growers in the South were different from growers in other geographic regions and were significantly more aware of local cases of GR weeds. Awareness of GR weeds did not increase appreciably from 2005 to 2010, but the percentage who reported GR weeds as problematic was significantly higher. Grower reports of GR weeds on-farm in 2010 were up considerably from 2005, with growers in the South reporting significantly more instances than growers in other regions. Growers in the South were also more likely to consider glyphosate resistance a serious problem. Overall, 30% of growers did not consider GR weeds to be a problem. It appears that most growers received information about glyphosate resistance from farm publications, although in the South this percentage was less than for other geographic regions. Growers in the South received more information from universities and extension sources.

scholarly journals WorldView-2 Satellite Image Classification using U-Net Deep Learning Model

2021 ◽  
Vol 5 (2) ◽  
pp. 502-509
Author(s):  
Ilyas Ilyas ◽  
Lalu Muhamad Jaelani ◽  
Muhammad Aldila Syariz ◽  
Husnul Hidayat
Keyword(s):  
Support Vector Machine ◽  
Deep Learning ◽  
Maximum Likelihood ◽  
Random Forest ◽  
Land Cover ◽  
Satellite Image ◽  
Support Vector ◽  
Classification Methods ◽  
Land Cover Map ◽  
Land Cover Maps

Land cover maps are important documents for local governments to perform urban planning and management. A field survey using measuring instruments can produce an accurate land cover map. However, this method is time-consuming, expensive, and labor-intensive. A number of researchers have proposed using remote sensing, which generates land cover maps using an optical satellite image with various statistical classification procedures. Recently, artificial intelligence (AI) technology, such as deep learning, has been used in multiple fields, including satellite image classification, with satisfactory results. In this study, a WorldView-2 image of Terangun in Aceh Province, which was acquired on Aug 2, 2016, was classified using a commonly used deep-learning-based classification, namely, U-net. There were eight classes used in the experiment: building, road, open land (such as green open space, bare land, grass, or low vegetation), river, farm, field, aquaculture pond, and garden. For comparison, three classification methods: maximum-likelihood, random forest, and support vector machine, were performed compared to U-Net. A land cover map provided by the government was used as a reference to evaluate the accuracy of land cover maps generated using two classification methods. The results with 100 randomly selected pixels revealed that U-Net was able to obtain a 72% and 0.585 for overall and kappa accuracy, respectively; whereas, overall accuracy and kappa accuracy for the maximum likelihood, random forest and support vector machine methods were  49% and 0.148; 59% and 0.392; and 67% and 0. 511; respectively. Therefore, U-Net outperformed those three of classification methods in classifying the image.  

Using a Grower Survey to Assess the Benefits and Challenges of Glyphosate-Resistant Cropping Systems for Weed Management in U.S. Corn, Cotton, and Soybean

2009 ◽  
Vol 23 (1) ◽  
pp. 134-149 ◽  
Author(s):  
David R. Shaw ◽  
Wade A. Givens ◽  
Luke A. Farno ◽  
Patrick D. Gerard ◽  
David Jordan ◽  
...  
Keyword(s):  
North Carolina ◽  
Crop Rotation ◽  
Best Management Practices ◽  
Weed Management ◽  
Crop Production ◽  
Management Practices ◽  
Glyphosate Resistance ◽  
Farm Size ◽  
Rotation System ◽  
Crop Rotation System

Over 175 growers in each of six states (Illinois, Indiana, Iowa, Mississippi, Nebraska, and North Carolina) were surveyed by telephone to assess their perceptions of the benefits of utilizing the glyphosate-resistant (GR) crop trait in corn, cotton, and soybean. The survey was also used to determine the weed management challenges growers were facing after using this trait for a minimum of 4 yr. This survey allowed the development of baseline information on how weed management and crop production practices have changed since the introduction of the trait. It provided useful information on common weed management issues that should be addressed through applied research and extension efforts. The survey also allowed an assessment of the perceived levels of concern among growers about glyphosate resistance in weeds and whether they believed they had experienced glyphosate resistance on their farms. Across the six states surveyed, producers reported 38, 97, and 96% of their corn, cotton, and soybean hectarage planted in a GR cultivar. The most widely adopted GR cropping system was a GR soybean/non-GR crop rotation system; second most common was a GR soybean/GR corn crop rotation system. The non-GR crop component varied widely, with the most common crops being non-GR corn or rice. A large range in farm size for the respondents was observed, with North Carolina having the smallest farms in all three crops. A large majority of corn and soybean growers reported using some type of crop rotation system, whereas very few cotton growers rotated out of cotton. Overall, rotations were much more common in Midwestern states than in Southern states. This is important information as weed scientists assist growers in developing and using best management practices to minimize the development of glyphosate resistance.

Weed Management in Small Grains Harvested for Grain

EDIS ◽  
2020 ◽  
Vol 2020 (3) ◽  
Author(s):  
Jason Ferrell ◽  
Gregory MacDonald ◽  
Pratap Devkota
Keyword(s):  
Weed Control ◽  
Weed Management ◽  
Chemical Control ◽  
Management Practices ◽  
Good Management ◽  
Small Grains ◽  
Crop Competition

Successful weed control in small grains involves using good management practices in all phases of production. In Florida, winter weeds compete with small grains for moisture, nutrients, and light, with the greatest amount of competition occurring during the first six to eight weeks after planting. Weeds also cause harvest problems the following spring when the small grain is mature. This 4-page publication discusses crop competition, knowing your weeds, and chemical control. Written by J. A. Ferrell, G. E. MacDonald, and P. Devkota, and published by the UF/IFAS Agronomy Department, revised May 2020.

Weed Management in Peanuts

EDIS ◽  
2020 ◽  
Vol 2020 (3) ◽  
Author(s):  
Pratap Devkota
Keyword(s):  
Weed Control ◽  
Weed Management ◽  
Management Practices ◽  
Application Rate ◽  
Good Management ◽  
Peanut Production

Successful weed control in peanuts involves use of good management practices in all phases of peanut production. This 11-page document lists herbicide products registered for use in Florida peanut production, their mode of actions group, application rate per acre and per season, and reentry interval. It also discusses the performance of these herbicides on several weeds under Florida conditions. Written by J. A. Ferrell, G. E. MacDonald, and P. Devkota, and published by the UF/IFAS Agronomy Department, revised May 2020.

Sign in / Sign up

Export Citation Format

Share Document