Evaluating the accuracy of mapping weeds in fallow fields using airborne digital imaging: Panicumeffusum in oilseed rape stubble

The potential accuracy of using airborne multispectral imaging to map weed patches rapidly in a fallow field has been evaluated. An image of a field of oilseed rape ( Brassica napus L.) stubble interspersed with Panicum effusum R. Br. was acquired using a four-camera airborne digital imaging system; recording in the infrared, red, green and blue wavebands. The image was converted into georectified weed maps using supervised and unsupervised classification procedures. Comparison of the airborne-derived maps with an accurate weed map compiled from a detailed ground survey demonstrated that weed:non-weed classification and mapping accuracies of better than 87% are possible. The limitations of assessing the accuracy of classified imagery using ground-truth data of similar spatial resolution are discussed.     

Plant classification for weed detection using hyperspectral imaging with wavelet analysis

The goal of this study is to develop a new weed detection method that can be applied for automatic mechanical weed control. For successful weed detection, plants must be classified into crops and weeds according to their species. In this study, we employed a portable hyperspectral imaging system. The hyperspectral camera can capture landscape images that include crops, weeds, and the soil surface, and can provide more extensive information than conventional red, green, and blue (RGB) images. Although RGB images consist of red, green, and blue wavebands, the obtained hyperspectral images consist of 240 wavebands of spectral information. Hyperspectral imaging is expected to provide powerful technology for agricultural sensing. In the initial step of this study, the image pixels of the plants (crop or weeds) were segmented from the background soil surface using Euclidean distance as the discriminant function. In the next step, the image pixels of the crop (sugarbeet) and weeds (four species) were classified using the difference in the spectral characteristics of the plant species. In this process, classification variables were generated using wavelet transformation for data compression, noise reduction, and feature extraction, and then stepwise linear discriminant analysis was applied. The validation results indicate that the developed classification method has potential for practical use.     

Evaluating the potential of Unmanned Aerial Systems for mapping weeds at field scales: a case study with Alopecurus myosuroides

Mapping weed densities within crops has conventionally been achieved either by detailed ecological monitoring or by field walking, both of which are time‐consuming and expensive. Recent advances have resulted in increased interest in using Unmanned Aerial Systems (UAS ) to map fields, aiming to reduce labour costs and increase the spatial extent of coverage. However, adoption of this technology ideally requires that mapping can be undertaken automatically and without the need for extensive ground‐truthing. This approach has not been validated at large scale using UAS ‐derived imagery in combination with extensive ground‐truth data. We tested the capability of UAS for mapping a grass weed, Alopecurus myosuroides , in wheat crops. We addressed two questions: (i) can imagery accurately measure densities of weeds within fields and (ii) can aerial imagery of a field be used to estimate the densities of weeds based on statistical models developed in other locations? We recorded aerial imagery from 26 fields using a UAS . Images were generated using both RGB and R_mod (R_mod 670–750 nm) spectral bands. Ground‐truth data on weed densities were collected simultaneously with the aerial imagery. We combined these data to produce statistical models that (i) correlated ground‐truth weed densities with image intensity and (ii) forecast weed densities in other fields. We show that weed densities correlated with image intensity, particularly R_mod image data. However, results were mixed in terms of out of sample prediction from field‐to‐field. We highlight the difficulties with transferring models and we discuss the challenges for automated weed mapping using UAS technology.     

Mapping Ridolfia segetum patches in sunflower crop using remote sensing

Ridolfia segetum is a frequent umbelliferous weed in sunflower crops in the Mediterranean basin. Field and remote sensing research was conducted in 2003 and 2004 over two naturally infested fields to determine the potential of multispectral imagery for discrimination and mapping of R. segetum patches in sunflower crops. The efficiency of the four wavebands blue (B), green (G), red (R) and near‐infrared (NIR), selected vegetation indices and the spectral angle mapper (SAM) classification method were studied using aerial photographs taken in the late vegetative (mid‐May), flowering (mid‐June) and senescence (mid‐July) crop growth stages. Discrimination efficiency of R. segetum patches in sunflower crops is consistently affected by their phenological stages, in this order: flowering > senescence > vegetative. In both fields, R. segetum patches were efficiently discriminated in mid‐June, corresponding to the flowering phase, by using the waveband G, the ratio R/B or SAM with overall accuracies ranging from 85% to 98%. The application of the median‐filtering algorithm to any of the classified images improved the accuracy. Our results suggest that mapping R. segetum weed patches in sunflower to implement site‐specific weed management techniques is feasible with aerial photography when images are taken from 8 to 10 weeks before harvesting.     

Does kriging predict weed distributions accurately enough for site‐specific weed control?

Numerous studies have demonstrated the patchy distribution of weeds within fields. The majority of these studies have used discrete sampling, recording weed densities at the intersections of regular grids. In this study, Avena spp. seedlings were recorded on square grids at four sites. The data were then divided into test and real data sets using the whole, two-thirds and one-half of the data to evaluate the consistency of global variogram models and accuracy of ordinary kriging estimates. Kriging provided poor weed density estimates at both very low and high densities, i.e. data were smoothed when compared with true values. Grid sampling took considerable time and, therefore, money to complete, whereas continuous sampling with multispectral imagery (performed at one site) was much quicker and at a finer resolution. It is suggested that sampling systems that collect continuous rather than discrete data are currently more appropriate for site-specific weed management.     

Spectral discrimination of Ridolfia segetum and sunflower as affected by phenological stage

Ridolfia segetum is an umbelliferous weed frequent and abundant in sunflower crops in the Mediterranean basin. Field research was conducted to evaluate the potential of hyperspectral and multispectral reflectance and five vegetation indices in the visible to near infrared spectral range, for discriminating bare soil, sunflower and R. segetum at different phenological stages. This was a preliminary step for mapping R. segetum patches in sunflower using remote sensing for herbicide application decisions. Reflectance data were collected at three sampling dates (mid‐May, mid‐June and mid‐July, corresponding to vegetative‐early reproductive, flowering and senescent phenological stages respectively) using a handheld field spectroradiometer. Differences observed in hyperspectral reflectance curves were statistically significant within and between crop and weed phenological stages depending on sampling date, which facilitates their discrimination. Statistically significant differences in the multispectral and vegetation indices analysis showed that it is also possible to distinguish any of the classes studied. Our study provides some information for constructing the spectral libraries of sunflower and R. segetum in which the different phenological stages co‐existing in the field were considered. Hyperspectral and multispectral results suggest that mapping R. segetum patches in sunflower is feasible using airborne hyperspectral sensors, and high‐resolution satellite imagery or aerial photography, respectively, taking into account specific timeframes.     

Multispectral classification of grass weeds and wheat (Triticum durum) using linear and nonparametric functional discriminant analysis and neural networks

Field studies were conducted to determine the potential of multispectral classification of late‐season grass weeds in wheat. Several classification techniques have been used to discriminate differences in reflectance between wheat and Avena sterilis, Phalaris brachystachys, Lolium rigidum and Polypogon monspeliensis in the 400–900 nm spectrum, and to evaluate the accuracy of performance for a spectral signature classification into the plant species or group to which it belongs. Fisher’s linear discriminant analysis, nonparametric functional discriminant analysis and several neural networks have been applied, either with a preliminary principal component analysis (PCA) or not and in different scenarios. Fisher’s linear discriminant analysis, feedforward neural networks and one‐layer neural network, all showed classification percentages between 90% and 100% with PCA. Generally, a preliminary computation of the most relevant principal components considerably improves the correct classification percentage. These results are promising because A. sterilis and L. rigidum, two of the most problematic, clearly patchy and expensive‐to‐control weeds in wheat, could be successfully discriminated from wheat in the 400–900 nm range. Our results suggest that mapping grass weed patches in wheat could be feasible with analysis of real‐time and high‐resolution satellite imagery acquired in mid‐May under these conditions.     

Evaluating the accuracy of mapping weeds in seedling crops using airborne digital imaging: Avena spp. in seedling triticale

Airborne multispectral imaging has been used to map patches of Avena spp. (wild-oats) in a field of seedling triticale (X Triticosecale , Wittmack). Images of the target field were acquired using a four-camera airborne digital imaging system, recording in the infrared, red, green and blue wave-bands. Spectral information derived from images of 0.5-, 1.0-, 1.5- and 2.0-m spatial resolution were correlated with detailed on-ground weed density measurements to investigate the effect of image resolution on mapping accuracy. Comparisons between normalized-difference vegetation index (NDVI) or soil-adjusted vegetation index (SAVI) images and weed data achieved correlations of up to 71%. The highest correlation was achieved with the 0.5-m-resolution images and the lowest with the 2.0-m-resolution images. At 0.5-m resolution, NDVI images could not reliably discriminate weed populations of less than 28 weeds m^–2 from weed-free regions, while SAVI images could not discriminate populations of less than 17 weeds m^–2. At 1.0-, 1.5- and 2.0-m resolution, SAVI images could not discriminate populations of less than 23 weeds m^–2, while NDVI images again demonstrated a higher discrimination threshold. Results suggest that airborne multispectral imaging could be used as part of a stratified weed sampling system.     

国内外有机果园杂草管理技术研究综述

在有机果园的日常管理中,应摈弃传统农业"根除杂草"的观念,建立"杂草管理"的可持续发展理念。杂草管理对建立和维持一个良好的有机果园尤为重要。本文主要围绕杂草对果园的影响以及如何有效地进行杂草管理展开综述,重点介绍了国内外有机果园普遍采用的杂草管理技术(包括耕作除草、果园覆草、生草覆盖、地膜覆盖、有机除草剂和火焰除草),旨在为有机果农实施杂草管理提供有益借鉴。     

Potential uses of small unmanned aircraft systems (UAS) in weed research

Small unmanned aerial systems (UAS) with cameras have not been adopted in weed research, but offer low‐cost sensing with high flexibility in terms of spatial resolution. A small rotary‐wing UAS was tested as part of a search for an inexpensive, user‐friendly and reliable aircraft for practical applications in UAS imagery weed research. In two experiments with post‐emergence weed harrowing in barley, the crop resistance parameter, which reflects the crop response to harrowing, was unaffected by image capture altitude in the range from 1 to 50 m. This corresponded to image spatial resolution in the range from 0.3 to 17.1 mm per pixel. This finding is important because spatial resolution is inversely related to sensing capacity. We captured 20 plots comprising a total of about 0.2 ha in one image at 50 m altitude without losing information about the cultivation impacts on vegetation compared with ground truth data. UAS imagery also gave excellent results in logarithmic sprayer experiments in oilseed rape, where we captured 37 m long plots in each image from an altitude of 35 m. Furthermore, perennial weeds could be mapped from UAS images. These first experiences with a small rotary‐wing UAS show that it is relatively easy to integrate as a tool in weed research and offers great potential for site‐specific weed management.     

BP神经网络的沙漠化土地信息提取研究

以塔克拉玛干沙漠南缘策勒绿洲为例,探讨了基于主成分融合的沙漠化信息的提取方法.由于Landsat-7 ETM 的全色波段与多光谱波段有相同成像条件,影像获取时间一致,两种不同分辨率的数据可以不经配准而实现高精度融合.首先,对Landsat-7ETM 的全色图像与多光谱图像进行主成分融合处理,再利用BP神经网络模型,以相同的训练样本分别对融合前后的影像进行分类,在此基础上进行沙漠化信息的提取.结果表明:主成分变换融合图像的光谱信息保持性、信息量以及空间分解力都较高,且分类精度比Landsat-7ETM 多光谱图像有较大提高,是监测沙漠化土地变化的有效手段.     

A method for mapping the distribution of willow at a catchment scale using bi-seasonal SPOT5 imagery

This study showed that seasonal imagery acquired at specific stages of phenology can be used to improve the mapping accuracy of invasive willow at a catchment scale. SPOT5 XI (10 m) satellite imagery was acquired for early autumn and winter to represent the phenological stages of leaf cover and leaf fall respectively. Four classification regimes were evaluated using single‐ and bi‐seasonal composite imagery to determine the most accurate method. Significant spectral noise was found in willow populations, especially in the winter image, due to the effects of undergrowth exposure, shadowing, topography and boundary‐mixed pixels. Two noise reduction techniques were applied to the bi‐seasonal composite image to improve the classification results. The noise‐reduced bi‐seasonal composite image was classified using the spectral angle mapper (SAM) algorithm before importation into a geographical information system. Aerial photography was used to reduce the errors of commission associated with misclassification of pastures. The class accuracy achieved for willow using the method described in this study was 77.5% (Kappa =0.87). The high cost of eradicating willow means that managers must establish priorities for control; this technique can provide a powerful tool for prioritizing control programmes and for monitoring results at a catchment scale.     

United States Department of Agriculture-Agricultural Research Service research on pest biology: weeds

Over 125 permanent full-time scientists conduct research within the USDA Agricultural Research Service (ARS) on issues related to weeds. The research emphasis of most of these scientists involves ecology and management or biological control of weeds. Many scientists perform research on weed biology as components of their primary projects on weed control and integrated crop and soil management. Describing all ARS projects involved with weed biology is impossible, and consequently only research that falls within the following arbitrarily chosen topics is highlighted in this article: dormancy mechanisms; cell division; diversity of rangeland weeds; soil resources and rangeland weeds; poisonous rangeland plants; horticultural weeds; weed traits limiting chemical control; aquatic and semi-aquatic weeds; weed/transgenic wheat hybrids; seedbanks, seedling emergence and seedling populations; and weed seed production. Within these topics, and others not highlighted, the desire of ARS is that good information on weed biology currently translates or eventually will translate into practical advice for those who must manage weeds.     

Herbicide‐resistant weed management: focus on glyphosate

This review focuses on proactive and reactive management of glyphosate‐resistant (GR) weeds. Glyphosate resistance in weeds has evolved under recurrent glyphosate usage, with little or no diversity in weed management practices. The main herbicide strategy for proactively or reactively managing GR weeds is to supplement glyphosate with herbicides of alternative modes of action and with soil‐residual activity. These herbicides can be applied in sequences or mixtures. Proactive or reactive GR weed management can be aided by crop cultivars with alternative single or stacked herbicide‐resistance traits, which will become increasingly available to growers in the future. Many growers with GR weeds continue to use glyphosate because of its economical broad‐spectrum weed control. Government farm policies, pesticide regulatory policies and industry actions should encourage growers to adopt a more proactive approach to GR weed management by providing the best information and training on management practices, information on the benefits of proactive management and voluntary incentives, as appropriate. Results from recent surveys in the United States indicate that such a change in grower attitudes may be occurring because of enhanced awareness of the benefits of proactive management and the relative cost of the reactive management of GR weeds. Copyright © 2011 Society of Chemical Industry     

Use of perennial cover crops to suppress weeds in Nicaraguan coffee orchards

Both uncontrolled weed growth and vegetation‐free orchard floors have been shown to affect coffee (Coflea arabica L.) negatively, but using cover crops as a solution has yielded conflicting results in different studies. In this study we tested the establishment success of three cover crop species under different management intensities and planting densities, as well as their long term weed‐controlling abilities and effects on weed community composition. Monthly manual weedings during the first 12 weeks after planting resulted in more rapid and extensive cover crop development compared with less intensive management. Transplanted Commelina diffusa Burm. f. grew most rapidly and controlled weeds by limiting light availability, but disappeared during the dry season and failed to establish at all on one of the farms. Arachis pintoi established and persisted for over 2 years, providing excellent weed control by outcompeting weeds for water and/or nutrient resources. Desmodium ovalifolium Wall required the longest time to establish and controlled weeds by an undetermined competitive mechanism. The sowing method of Desmodium led to intense intraspecific competition which probably decreased its effectiveness. Both Arachis and Desmodium led to lower relative abundances of grassy weeds and more perennial forbs, but total weed biomass was so low that these differences have no practical implications.     

Practical experiences with a system for site-specific weed control in arable crops using real-time image analysis and GPS-controlled patch spraying

Information on temporal and spatial variation in weed seedling populations within agricultural fields is very important for weed population assessment and management. Primarily, spatial information allows a potential reduction in herbicide use, when post‐emergent herbicides are only applied to field sections with high weed infestation levels. This paper presents a system for site‐specific weed control in sugar beet, maize, winter wheat, winter barley, winter rape and spring barley. The system includes on‐line weed detection using digital image analysis, computer‐based decision making and Global Positioning System‐controlled patch spraying. In a 2‐year study, herbicide use with this map‐based approach was reduced in winter cereals by 6–81% for herbicides against broad leaved weeds and 20–79% for grass weed herbicides. Highest savings were achieved in cereals followed by sugar beet, maize and winter rape. The efficacy of weed control varied from 85% to 98%, indicating that site‐specific weed management will not result in higher infestation levels in the following crops.     

Image‐based thresholds for weeds in maize fields

Recent development of site‐specific weed management strategies suggests patch application of herbicides to avoid their excessive use in crops. The estimation of infestation of weeds and control thresholds are important components for taking spray decisions. If weed pressure is below a certain level in some parts of the field and if late germinating weeds do not affect yield, it may not be necessary the spray such places from an economic point of view. Consequently, it makes sense to develop weed control thresholds for patch spraying, based on weed cover early in the growing season. In Danish maize field experiments conducted from 2010 to 2012, we estimated competitive ability parameters and control thresholds of naturally established weed populations in the context of decision‐making for patch spraying. The most frequent weed was Chenopodium album, accompanied by Capsella bursa‐pastoris, Cirsium arvense, Lamium amplexicaule, Tripleurospermum inodorum, Poa annua, Polygonum aviculare, Polygonum persicaria, Stellaria media and Veronica persica. Relative leaf cover of weeds was estimated using an image analysis method. The relation between relative weed leaf cover and yield loss was analysed by nonlinear regression models. The competitive ability parameters and economic thresholds were estimated from the regression models. The competitive ability of weed mixtures was influenced by the increasing proportion of large size weeds in the mixtures. There was no significant effect of weeds which survived or established after the first herbicide application, indicating that early image analysis was robust for use under these conditions.     

A call for weed research in industrial hemp (Cannabis sativa L)

Industrial hemp (Cannabis sativa L.) is grown in more than 30 countries for fibre, seed and flowers, and acreage of cultivation is increasing globally. Hemp has long been promoted as a crop that competes well with weeds and requires little intervention to prevent yield losses. We conducted a literature review and found little peer‐reviewed research to support this claim. We identified only three articles that specifically addressed weed management under field conditions and none provided information on hemp yield losses from weeds. These findings highlight a clear need for research‐based information on interactions between weeds and hemp to address potential yield losses under various production conditions and provide a research‐based framework for weed management in industrial hemp.     

基于无人机多光谱影像的完熟期玉米倒伏信息提取

以吉林省梨树县的玉米试验田为研究区，按受灾后完熟期玉米的状态将研究区分为倒伏、半倒伏和未倒伏3种类型。基于无人机采集的多光谱影像提取15种光谱指数和8种纹理特征，采用面向对象法、最大似然法和多元Logistic回归模型进行玉米倒伏信息的提取；而后通过目视方法选取400个样本点进行玉米倒伏信息提取结果的精度验证。结果表明：面向对象法精度最高，对玉米3种倒伏状态信息识别的总体精度为88.13%,Kappa系数为0.83。研究用于区分倒伏与未倒伏玉米的最佳光谱指数是归一化差异植被指数，对区分倒伏与半倒伏、半倒伏与未倒伏玉米贡献最大的特征均为对比度纹理特征。研究表明基于无人机多光谱影像的面向对象方法在对田块尺度玉米倒伏信息的精准识别中具有较大潜力。