Intra-row Weed Research Articles

Use of an organic mulching film for intra-row weed management in a young high-density olive orchard

Use of an organic mulching film for intra-row weed management in a young high-density olive orchard

Ammonia Emissions, Exposed Surface Area, and Crop and Weed Responses Resulting from Three Post-Emergence Slurry Application Strategies in Cereals

Ammonia (NH3) emissions resulting from the field application of livestock slurry has both negative human health and environmental impacts. However, decreasing the exposed surface area (ESA) of slurry upon application can reduce NH3 volatilization by limiting its atmospheric exposure. In the present study, three strategies for depositing slurry within a growing crop were studied, including: 1. standard trailing hoses (SAhose), 2. trailing shoes (SAshoes), and 3. the combination of rigid tines and trailing shoes (SAtines+shoes). Application methods interact with the soil to varying degrees and were evaluated within the context of contemporary weed management practices, namely in cereals receiving inter-row hoeing. SAhose, SAshoes, and SAtines+shoes were compared in three coinciding experiments that assessed slurry ESA, NH3 emissions, and crop and weed effects. SAtines+shoes resulted in smallest ESA, 70–72% and 61–66% less than SAhose and SAshoes, respectively. However, in only one of three site–years did SAshoes and SAtines+shoes reduce NH3 emissions compared to SAhose, by 46% and 29%, respectively. Crop yields, nitrogen (N) accumulation in crop biomass, and intra-row weed biomass were unaffected by the placement method. In heavily crusted soils, the SAtines+shoes prototype worked well; however, the functional differences among placement strategies were not great enough to detect crop and NH3 effects.

Deep learning-based early weed segmentation using motion blurred UAV images of sorghum fields

Weeds are undesired plants in agricultural fields that affect crop yield and quality by competing for nutrients, water, sunlight and space. For centuries, farmers have used several strategies and resources to remove weeds. The use of herbicide is still the most common control strategy. To reduce the amount of herbicide and impact caused by uniform spraying, site-specific weed management (SSWM) through variable rate herbicide application and mechanical weed control have long been recommended. To implement such precise strategies, accurate detection and classification of weeds in crop fields is a crucial first step. Due to the phenotypic similarity between some weeds and crops as well as changing weather conditions, it is challenging to design an automated system for general weed detection. For efficiency, unmanned aerial vehicles (UAV) are commonly used for image capturing. However, high wind pressure and different drone settings have a severe effect on the capturing quality, what potentially results in degraded images, e.g., due to motion blur. In this paper, we investigate the generalization capabilities of Deep Learning methods for early weed detection in sorghum fields under such challenging capturing conditions. For this purpose, we developed weed segmentation models using three different state-of-the-art Deep Learning architectures in combination with residual neural networks as feature extractors.We further publish a manually annotated and expert-curated UAV imagery dataset for weed detection in sorghum fields under challenging conditions. Our results show that our trained models generalize well regarding the detection of weeds, even for degraded captures due to motion blur. An UNet-like architecture with a ResNet-34 feature extractor achieved an F1-score of over 89% on a hold-out test-set. Further analysis indicate that the trained model performed well in predicting the general plant shape, while most misclassifications appeared at borders of the plants. Beyond that, our approach can detect intra-row weeds without additional information as well as partly occluded plants in contrast to existing research.All data, including the newly generated and annotated UAV imagery dataset, and code is publicly available on GitHub: https://github.com/grimmlab/UAVWeedSegmentation and Mendeley Data: https://doi.org/10.17632/4hh45vkp38.4.

SE-YOLOv5x: An Optimized Model Based on Transfer Learning and Visual Attention Mechanism for Identifying and Localizing Weeds and Vegetables

Weeds in the field affect the normal growth of lettuce crops by competing with them for resources such as water and sunlight. The increasing costs of weed management and limited herbicide choices are threatening the profitability, yield, and quality of lettuce. The application of intelligent weeding robots is an alternative to control intra-row weeds. The prerequisite for automatic weeding is accurate differentiation and rapid localization of different plants. In this study, a squeeze-and-excitation (SE) network combined with You Only Look Once v5 (SE-YOLOv5x) is proposed for weed-crop classification and lettuce localization in the field. Compared with models including classical support vector machines (SVM), YOLOv5x, single-shot multibox detector (SSD), and faster-RCNN, the SE-YOLOv5x exhibited the highest performance in weed and lettuce plant identifications, with precision, recall, mean average precision (mAP), and F1-score values of 97.6%, 95.6%, 97.1%, and 97.3%, respectively. Based on plant morphological characteristics, the SE-YOLOv5x model detected the location of lettuce stem emerging points in the field with an accuracy of 97.14%. This study demonstrates the capability of SE-YOLOv5x for the classification of lettuce and weeds and the localization of lettuce, which provides theoretical and technical support for automated weed control.

Improving upon the interrow hoed cereal system: the effects of crop density and row spacing on intrarow weeds and crop parameters in spring barley

AbstractAutomated guidance systems have advanced precise interrow hoeing in narrowly spaced cereals. Compared with other direct mechanical strategies, hoeing provides superior weed control and improved yields. However, weeds in the uncultivated intrarow zone may survive and compete intensely with the crop, causing yield loss. Therefore, improved intrarow weed management strategies in hoed cereals must be investigated. In spring barley (Hordeum vulgare L.), the effect of crop density was assessed at four levels (200, 300, 400, and 500 plants m−2); interrow spacing at two levels (15 and 20 cm), relevant to the abilities of current automated equipment to hoe between narrowly spaced rows; and weed management treatment at three levels (no additional controls, herbicide, and preemergence tine harrowing). All treatments received interrow hoeing, and a surrogate weed (white mustard, Sinapis alba L.) was sown and monitored throughout experiments. The manipulation of crop density was a reliable method for suppressing the growth of intrarow weeds. As barley density increased from the target 200 to 500 plants m−2, percent reduction in intrarow surrogate and ambient weed biomass (g m−2) increased from 49% to 82% and 53% to 99%, respectively. Increasing crop density caused a decrease in grain bulk density (kg hl−1) both years, and grain protein (%) and 1,000-kernel weight (g) in one year; whether these changes constitute a loss in grain quality depends upon end use. While row spacing had no effect on intrarow weeds, crop yields were 7% to 8% lower at 20 cm compared with 15 cm, incentivizing narrow row sowing. Barley yields were unaffected by increasing crop density, and the effect of preemergence tine harrowing was inconsistent. In one year, harrowing reduced surrogate and ambient weed biomass and increased barley yield; however, in another year, ambient weed biomass increased, and harrowing did not affect yield or surrogate weed biomass.

Maize weed control and yield using different applications of tembotrione

Present study employed different methods of tembotrione applications for weed management in maize and investigated if integration of a herbicide in intra-row and hand weeding in inter-row could provide similar level of weed control to blanket application of a herbicide. The field study was conducted in 2018 and 2019 on loamy sand soil at Ludhiana and on a clay loam soil in 2018 at Langroya, in India. At Ludhiana, Cyperus rotundus L., Dactyloctenium aegyptium (L.) Willd., Acrachne racemosa Ohwi and Trianthema portulacastrum L. and, at Langroya, C. rotundus, D. aegyptium, Echinochloa colonum L. and T. portulacastrum were major weeds. Integrated use of tembotrione at 36.7 g ha−1 alone or its tank mixture with atrazine 208 g ha−1 as band application (intra-row) with manual weeding (inter-row) provided similar level of weed control and maize grain yield to blanket application of tembotrione 110 g ha−1 alone or its tank mixture with atrazine 625 g ha−1. The study concluded that integration of herbicide application on crop rows and hand weeding in inter rows could be adopted in maize.

Intelligent intra-row robotic weeding system combining deep learning technology with a targeted weeding mode

Mechanical weed control is the most promising weed control method for weed management in organic agriculture. Among the various available methods, inter-row weeding technology is relatively mature, and researchers have focused on intra-row weeding technology. The objective of this study was to develop a new intelligent intra-row mechanical robotic weeding system based on deep learning for crop and weed detection. The system consists of a mobile robot platform and two intelligent weeding units. The mobile robot platform provides power support as well as operating conditions for the weeding units. A targeted weeding pattern was proposed based on the deep learning detection results, and protected and targeted weeding zones were established by strict criteria to reduce crop injury rates. In addition, three weed control knives were designed according to different field environments. Field trials showed that among the three weed knives, the plough-surface weeding knife was the most effective and most suitable knife for flat cultivation, and the wedge weeding knife was most suitable for ridge planting. Based on the obtained results, the best weeding method was determined, and the experiment was repeated using a wedge weeding knife under ridge planting conditions. The final weed removal rate was 85.91%, and the crop injury rate was 1.17%. The results demonstrated the feasibility of the proposed intra-row weed control method.

Intra-row weed density evaluation in rice field using tactile method

• The first attempt to evaluate the density of intra-row weeds in a paddy field based on tactile perception. • A variety of tactile expressions of weed density were obtained. • A novel feature extraction scheme based on the Hilbert-Huang Transform was proposed. • The weed density evaluation model was established based on the feature scheme. Accurate evaluation of weed density is crucial for effective utilization of herbicides, improvement of rice quality, and reduction of herbicide dosages. The application of visual methods is disadvantageous because intra-row weeds are blocked by the canopies of adjacent rice plants. Therefore, an innovative tactile sensing method is proposed. A flexible gasbag filled with special microstructures distributed over its surface was developed. The tactile data of weed density were generated through contact between the microstructures and weeds, and the data were measured using the voltage value of a barometric sensor mounted inside the gasbag. The tactile time series was processed using fractal theory and Hilbert–Huang transform (HHT), and the discriminating features of the weed density were acquired. The discriminating features were input into a neural network to train a weed density classifier to evaluate the weed density. The results of the feasibility experiment demonstrated that the evaluation accuracies for high-density, medium-density, and low-density weeds were 95.4%, 91.8%, and 87.9%, respectively, with an average accuracy of 91.7%. The field validation test demonstrated that the visual-based method had an average classification accuracy of 64.17%, whereas the proposed method had an average accuracy of 77.04%, experimentally demonstrating superior accuracy over the image-based method.

Development of a Three-Dimensional Plant Localization Technique for Automatic Differentiation of Soybean from Intra-Row Weeds

Soybean is a legume that is grown worldwide for its edible bean. Intra-row weeds greatly hinder the normal growth of soybeans. The continuous emergence of herbicide-resistant weeds and the increasing labor costs of weed control are affecting the profitability of growers. The existing cultivation technology cannot control the weeds in the crop row which are highly competitive with the soybean in early growth stages. There is an urgent need to develop an automated weeding technology for intra-row weed control. The prerequisite for performing weeding operations is to accurately determine the plant location in the field. The purpose of this study is to develop a plant localization technique based on systemic crop signalling to automatically detect the appearance of soybean. Rhodamine B (Rh-B) is a signalling compound with a unique fluorescent appearance. Different concentrations of Rh-B were applied to soybean based on seed treatment for various durations prior to planting. The potential impact of Rh-B on seedling growth in the outdoor environment was evaluated. Both 60 and 120 ppm of Rh-B were safe for soybean plants. Higher doses of Rh-B resulted in greater absorption. A three-dimensional plant localization algorithm was developed by analyzing the fluorescence images of multiple views of plants. The soybean location was successfully determined with the accuracy of 97%. The Rh-B in soybean plants successfully created a machine-sensible signal that can be used to enhance weed/crop differentiation, which is helpful for performing automatic weeding tasks in weeders.

Simulation modelling of mechanical systems for intra-row weeding in a precision farming approach

Aim of study: To test new approaches to perform mechanical weeding inside the row in horticulture and tree fruit fields. The idea is to weed the row by skipping the crop by means of a rotating system instead of a traditional crosswise one. Area of study: North of Italy. Material and methods: Numerical models have been developed to simulate mechanical weeding over time by generating numerical maps to quantify the different kind of worked areas. Main results: Considering the efficiency of weed control on the row, the rotating plant-skipping system with vertical axis (RPSS-VA model) with two working tools gives the best performance index (1.1.RWA% = 95.9%). A similar performance can be obtained by the crosswise displacement plant-skipping system, but with very high crosswise translation velocity (with va/vr ratio = 1/5, 1.1.RWA% = 94.5%). With regard to the outwards worked area the RPSS-VA models give the best performances (2.2.%OWAR index from 127.2% up to 282.3%). To reduce the worked area outside the row, the FBTS models give lower index (2.1.OWAR%), while the RPSS-HA works only on the row, but with the lower 1.1.RWA% index among all tested models (55.8%). Research highlights: Rotating systems resulted more efficient than traditional ones, and provide considerations on the use of electric drive power instead of hydraulic one. This study highlights also the need of new approaches in designing lighter working tools. Lastly, the proposed classification of the worked areas could be used as reference standard.

Mechanical weed management technology to manage inter- and intra-row weeds in agroecosystems - A review

Traditional manual weed management is one of the tedious and costly operations in the complete cycle of crop production, reasons being high labor costs, time and tedium. The herbicide use contributes to environmental pollution in addition to other disadvantages of concern. The increasing demand for toxicant free food has become a challenge for weed control. Hence, the mechanical weeding is gaining importance. Automation in agriculture has also improved the mechanization input in weed management. The rapid entry of sensors, microcontroller and computing technologies in the field has formed a foundation of agricultural autonomous guidance systems. An automated system is time effective for field operations, avoids huge labor requirement and health drudgery issues to provide an efficient farm operation. Generally manual tools such as khurpi (hand operated small hoe), grubber, spade, wheel hoe, push pull type of weeder are used by farmers for the removal of inter- and intra-row weeds with higher weeding efficiency in the range of 72 to 99% but field capacity is very low in the range of 0.001 to 0.033 ha/h. This review deliberates on the latest work being done on mechanical weed management such as tractor operated finger weeder, torsion weeder, ECO weeder, flame weeder, harrow and sensor-based technologies for management of inter- and intra-row weeds in crops with wider rows.

Development of intra-row weeding robot equipped with pull-out weeding mechanism and image recognition system

Development of intra-row weeding robot equipped with pull-out weeding mechanism and image recognition system

Study on Comparative Performances of Selected Paddy Weeders Developed in India

Various types of paddy weeders, for dry as well as wet-land conditions, have been developed and used in India. The commonly used wetland paddy weeders under Indian conditions are rotary power weeder, cono-weeder, and Ambika weeder; whereas, hoe-type weeders are mostly used under dry-land conditions. The common and effective type of weeder is two-row power-operated rotary type of 0.0793 ha.h-1 field capacity. The average cost of operation and weeding efficiency of existing paddy weeder is 1,169.59 `.ha-1 and 79.92%, respectively. A review undertaken on different types of paddy weeders developed by researchers in India indicated that most of the developed weeders are designed for the use in inter-row cultivation, and limited research has been conducted for intra-row weeding. Thus, research should focus on developing inter-cum-intra-row weeders which could increase weeding efficiency and crop yield.

DESIGN AND EXPERIMENT OF KEY COMPONENTS OF PADDY FIELD WEEDING DEVICE

A type of weeding device was designed to solve the problems of weeders in paddy fields, such as high rice seedling damage and low weeding rate. The structure of the weeding machine and the working principle are illustrated. The seedling avoiding and weeding mechanism of the weeding device were analyzed. The parts of the weeder that contacted the soil were designed. The contact process between the spring tine and soil in paddy was simulated using the discrete element method to study the change in mechanical behavior during the working process. To verify the performance of the weeding machine, the forward speed and hoeing depth were taken as experimental factors, and weeding rate and rice seedling damage rate were selected as test indices. Field experiments were conducted to study the effects of each factor on weeding operations. The results of the experiment were evaluated by multi-index comprehensive weighting. The test results showed that, when the forward speed was 0.30 m/s and hoeing depth was 40 mm, rice seedling damage rate was 3.4%, weeding rate was 85%. The weeding machine satisfies the requirements of weeding in paddy. This research can provide a reference for the design of intra-row weeding devices in paddy.

Weeding Frequency Effects on Growth and Yield of Dry Bean Intercropped with Sweet Sorghum and Cowpea under a Dryland Area

A better understanding of the dry bean (Phaseolus vulgaris L.) growth and yield response to weed competition under the intercropping system is critical for improving sustainable weed management strategies. A two-year trial was conducted with three types of crop arrangement (sole cropping, inter-row, and intra-row intercropping) combined with weeding frequency (no weeding, weeding over the first 50 days of crop growth, and weed-free). Effects of the treatments were tested on dry bean agronomic indicators in terms of the following: 100-grain weight, dry biomass, grain yield, grains per pod, pods per plant, plant height, number of leaves per plant, and chlorophyll content. The intercropping pattern significantly affected dry bean pods per plant, height, and chlorophyll content, while weeding frequency significantly affected all measured agronomic indicators for dry bean, except for chlorophyll content, during the 2017/18 growing season. The results showed that the significant measured agronomic indicators were the lowest under no weed control; however, they increased as weeding frequency increased. The 2018/19 growing season followed a similar trend; however, the interaction effect significantly affected dry bean 100-grain weight, dry biomass, and number of leaves per plant at 40 days after emergence. The dry bean/sweet sorghum or cowpea intra-row intercropping and intermediate weeding frequency displayed optimum productivity.

Development and evaluation of a seed position mapping system

With the development of precision agriculture, individual plant care systems have become an important research topic. These systems require accurate and reliable information about the position of individual plants. Seed position mapping, an important method of accurate plant positioning techniques, can obtain seed location data directly in planting stage. The utilization of seed location data is maximized by providing references for the field managements such as intra-row weeding, fertilizer and pesticide application. This study presented the design of a seed mapping system for corn planters in high-position seeding method (HSM). An experimental study of the designed mapping system was performed to evaluate its performance with a four-row planter. The seed firmer (SF) which can reduce seed bouncing and the limiting plate (LP) which can disable the parallel four-bar linkage (PFL) are used to modify the four-row planter. Each planter unit had been modified differently (with SF and LP added, without SF and LP added, with only LP added, with only SF added). The accuracy of the seed position mapping system was evaluated for different operation speed (3, 5, and 7 km/h), seed spacing (20, 30, and 40 cm), and the global positing system (GPS) frequency (1, 5, and 10 Hz) by the distance deviation (DD) and the location quality index (LQI), where DD is the distance deviation between the predicted and actual seed locations, while LQI is defined as the percentage of seeds with a DD < 5 cm. Field tests show that the application of SF can decrease DD and increase LQI immensely: the average decrease of DD is 19.85 mm in the row with SF compared with that without SF, while the average increase of LQI is 29.4%. The application of LP has no significant impact on DD and LQI under experimental conditions. The DD was highly significant influenced by operation speed and seed spacing (p < 0.01), but significant influenced by GPS frequency (p < 0.05). The LQI was highly significant influenced by operation speed (p < 0.01), significant influenced by seed spacing (p < 0.05), but not significant influenced by GPS frequency (p > 0.05). Slower operation speed and larger seed spacing help to improve the mapping accuracy, achieving lower DD and higher LQI. The maximum operating speed of proposed mapping system is 3 km/h, the average DD and LQI in the presence of SF under this condition were 24.4 mm and 91.3%. The mapping accuracy under such conditions is satisfactory.

Sensor-Based Intrarow Mechanical Weed Control in Sugar Beets with Motorized Finger Weeders

The need for herbicide usage reduction and the increased interest in mechanical weed control has prompted greater attention to the development of agricultural robots for autonomous weeding in the past years. This also requires the development of suitable mechanical weeding tools. Therefore, we devised a new weeding tool for agricultural robots to perform intrarow mechanical weed control in sugar beets. A conventional finger weeder was modified and equipped with an electric motor. This allowed the rotational movement of the finger weeders independent of the forward travel speed of the tool carrier. The new tool was tested in combination with a bi-spectral camera in a two-year field trial. The camera was used to identify crop plants in the intrarow area. A controller regulated the speed of the motorized finger weeders, realizing two different setups. At the location of a sugar beet plant, the rotational speed was equal to the driving speed of the tractor. Between two sugar beet plants, the rotational speed was either increased by 40% or decreased by 40%. The intrarow weed control efficacy of this new system ranged from 87 to 91% in 2017 and from 91 to 94% in 2018. The sugar beet yields were not adversely affected by the mechanical treatments compared to the conventional herbicide application. The motorized finger weeders present an effective system for selective intrarow mechanical weeding. Certainly, mechanical weeding involves the risk of high weed infestations if the treatments are not applied properly and in a timely manner regardless of whether sensor technology is used or not. However, due to the increasing herbicide resistances and the continuing bans on herbicides, mechanical weeding strategies must be investigated further. The mechanical weeding system of the present study can contribute to the reduction of herbicide use in sugar beets and other wide row crops.

Sweet Sorghum (Sorghum bicolor) Performance in a Legume Intercropping System under Weed Interference

Sweet sorghum (Sorghum bicolor L. Moench) is highly susceptible to weed competition during the early growth stages; hence, intercropping is considered to overcome the weed competition challenge. This study was conducted to determine the performance of sweet sorghum in legume intercropping systems under different weed management pressures. Three cropping systems (sole crop, inter-row, and intra-row intercropping) and three weed management levels (no weeding after crop emergency, ceasing weeding 50 days after crop emergency, and weeding throughout) were tested. Intercropping pattern had a significant (p &lt; 0.05) impact on the plant and the number of leaves per plant, while other treatments remained insignificant during the 2017/18 growing season. During the 2018/19 growing season, the intercropping pattern had a significant (p &lt; 0.05) effect on dry and fresh biomass and plant height at 60 days after emergence. An increase in weeding frequencies reduced Brix (◦Bx). Uncontrolled weed plots had the lowest sweet sorghum dry biomass accumulation, whereas the biomass increased as weeding frequencies increased but remained insignificant as weeding frequencies further increased from 50% to 100% in both seasons. Consequently, SS/DB intra-row intercropping and intermediate weeding are sufficient for optimum SS biomass production and sugar levels.

An integrated inter- and intra-row weeding system for row crops

Weeding is critical to eliminate non-native plants that compete with main crops and adversely affect their production quality and quantity. Numerous prototypes exist for inter-row weeding but very limited for intra-row weed eradication. This study developed a tractor drawn integrated inter- and intra-row weeding (IIIRW) system for field crops. Active rotary tines were used for intra-row weeding and passive tines for inter-row weeding. Optimum operational configurations were obtained with rigorous repeated soil bin experiments, and developed system was evaluated for three growing seasons (2017–19) in field grown maize (Zea mays L.) and pigeon pea (Cajanus cajan (L.) Millsp.) crops. Optimum ratios of intra-row tine rotary speed to forward speed (u/v) were in the ranges of 0.8–1.3 that lead to weed mortality of 88.4 % (Buried: 8.5 %, Uprooted: 79.9 %), negligible intact weeds, and plant damage (Pd) within 6 %. Sole inter-row weeding operation resulted up to 78.1 % of weed mortality (Buried: 18.1 %, Uprooted: 60.0 %) and negligible Pd. Overall weed mortality with the IIIRW system was 92.8 % (Buried: 9.5 %, Uprooted: 83.3 %) in maize and 84.1 % (Buried: 7.6 %, Uprooted: 76.5 %) in pigeon pea crops. Results suggest suitability of the IIIRW system for a range of similar crops for field capacity in ranges of 0.22–0.26 ha/h at recommended operating speeds within 0.50–0.56 m/s. The IIIRW system requires a single prime mover and could be potentially economical and efficient technology for field weeding operations.

Development of a Mechatronic System for Plant Recognition and Intra-row Weeding With Machine Vision

In this paper, an electro-mechanical integrated weed management system was designed, constructed, and tested. This laboratory-scale solution integrated elements of machine vision, controls, and mechanical actuation to selectively remove weeds from within a crop row. The device was validated in a controlled environment using corn crops. Various crop conditions were considered to ensure the robustness of the design. Though some design aspects should be reworked for improved results, the device can effectively be used to facilitate small-scale research for automated weeding strategies.