scholarly journals Drone and sensor technology for sustainable weed management: a review

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Marco Esposito ◽  
Mariano Crimaldi ◽  
Valerio Cirillo ◽  
Fabrizio Sarghini ◽  
Albino Maggio
Keyword(s):  
Weed Management ◽  
Yield Loss ◽  
Abiotic Factors ◽  
Machine Learning Techniques ◽  
Sensor Technology ◽  
Integrated Weed Management ◽  
Weed Population Dynamics ◽  
Learning Techniques ◽  
Robot Systems ◽  
Available Technology

AbstractWeeds are amongst the most impacting abiotic factors in agriculture, causing important yield loss worldwide. Integrated Weed Management coupled with the use of Unmanned Aerial Vehicles (drones), allows for Site-Specific Weed Management, which is a highly efficient methodology as well as beneficial to the environment. The identification of weed patches in a cultivated field can be achieved by combining image acquisition by drones and further processing by machine learning techniques. Specific algorithms can be trained to manage weeds removal by Autonomous Weeding Robot systems via herbicide spray or mechanical procedures. However, scientific and technical understanding of the specific goals and available technology is necessary to rapidly advance in this field. In this review, we provide an overview of precision weed control with a focus on the potential and practical use of the most advanced sensors available in the market. Much effort is needed to fully understand weed population dynamics and their competition with crops so as to implement this approach in real agricultural contexts.

scholarly journals How Can Unmanned Aerial Vehicles Be Used for Detecting Weeds in Agricultural Fields?

Agriculture ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1004
Author(s):  
Nur Adibah Mohidem ◽  
Nik Norasma Che’Ya ◽  
Abdul Shukor Juraimi ◽  
Wan Fazilah Fazlil Ilahi ◽  
Muhammad Huzaifah Mohd Roslim ◽  
...  
Keyword(s):  
Weed Management ◽  
Abiotic Factors ◽  
Scientific Information ◽  
Machine Learning Techniques ◽  
Integrated Weed Management ◽  
Weed Detection ◽  
Advantages And Disadvantages ◽  
Learning Techniques ◽  
Aerial Vehicle ◽  
Agricultural Industries

Weeds are among the most harmful abiotic factors in agriculture, triggering significant yield loss worldwide. Remote sensing can detect and map the presence of weeds in various spectral, spatial, and temporal resolutions. This review aims to show the current and future trends of UAV applications in weed detection in the crop field. This study systematically searched the original articles published from 1 January 2016 to 18 June 2021 in the databases of Scopus, ScienceDirect, Commonwealth Agricultural Bureaux (CAB) Direct, and Web of Science (WoS) using Boolean string: “weed” AND “Unmanned Aerial Vehicle” OR “UAV” OR “drone”. Out of the papers identified, 144 eligible studies did meet our inclusion criteria and were evaluated. Most of the studies (i.e., 27.42%) on weed detection were carried out during the seedling stage of the growing cycle for the crop. Most of the weed images were captured using red, green, and blue (RGB) camera, i.e., 48.28% and main classification algorithm was machine learning techniques, i.e., 47.90%. This review initially highlighted articles from the literature that includes the crops’ typical phenology stage, reference data, type of sensor/camera, classification methods, and current UAV applications in detecting and mapping weed for different types of crop. This study then provides an overview of the advantages and disadvantages of each sensor and algorithm and tries to identify research gaps by providing a brief outlook at the potential areas of research concerning the benefit of this technology in agricultural industries. Integrated weed management, coupled with UAV application improves weed monitoring in a more efficient and environmentally-friendly way. Overall, this review demonstrates the scientific information required to achieve sustainable weed management, so as to implement UAV platform in the real agricultural contexts.

scholarly journals Machine Learning and Sensor Fusion for Estimating Continuous Energy Expenditure

AI Magazine ◽  
2012 ◽  
Vol 33 (2) ◽  
pp. 55 ◽  
Author(s):  
Nisarg Vyas ◽  
Jonathan Farringdon ◽  
David Andre ◽  
John Ivo Stivoric
Keyword(s):  
Machine Learning ◽  
Energy Expenditure ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Sensor Technology ◽  
Health Goals ◽  
System A ◽  
Multi Sensor Data Fusion ◽  
Learning Techniques ◽  
Insight Into

In this article we provide insight into the BodyMedia FIT armband system — a wearable multi-sensor technology that continuously monitors physiological events related to energy expenditure for weight management using machine learning and data modeling methods. Since becoming commercially available in 2001, more than half a million users have used the system to track their physiological parameters and to achieve their individual health goals including weight-loss. We describe several challenges that arise in applying machine learning techniques to the health care domain and present various solutions utilized in the armband system. We demonstrate how machine learning and multi-sensor data fusion techniques are critical to the system’s success.

scholarly journals Response of Barley Genotypes to Weed Interference in Australia

Agronomy ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 99 ◽  
Author(s):  
Gulshan Mahajan ◽  
Lee Hickey ◽  
Bhagirath Singh Chauhan
Keyword(s):  
Negative Correlation ◽  
Weed Management ◽  
Field Experiments ◽  
Yield Loss ◽  
Production Systems ◽  
Relative Yield ◽  
Organic Production ◽  
Integrated Weed Management ◽  
Weed Interference ◽  
Barley Genotypes

Weed-competitive genotypes could be an important tool in integrated weed management (IWM) practices. However, weed competitiveness is often not considered a priority for breeding high-yielding cultivars. Weed-competitive ability is often evaluated based on weed-suppressive ability (WSA) and weed-tolerance ability (WTA) parameters; however, there is little information on these aspects for barley genotypes in Australia. In this study, the effects of weed interference on eight barley genotypes were assessed. Two years of field experiments were performed in a split-plot design with three replications. Yield loss due to weed interference ranged from 43% to 78%. The weed yield amongst genotypes varied from 0.5 to 1.7 Mg ha−1. Relative yield loss due to weed interference was negatively correlated with WTA and WSA. A negative correlation was also found between WSA and weed seed production (r = −0.72). Similarly, a negative correlation was found between WTA and barley yield in the weedy environment (r = −0.91). The results suggest that a high tillering ability and plant height are desirable attributes for weed competitiveness in the barley genotypes. These results also demonstrated that among the eight barley genotypes, Commander exhibited superior WSA and WTA parameters and therefore, could be used in both low- and high-production systems for weed management. Westminster had a superior WSA parameter. Therefore, it could be used for weed management in organic production systems. These results also implied that genotypic ranking on the basis of WSA and WTA could be used as an important tool in strengthening IWM programs for barley.

Self-reconfigurable control architecture for complex mobile robots

2015 ◽  
Vol 57 (2) ◽  
Author(s):  
Jan Frost ◽  
Walter Stechele ◽  
Erik Maehle
Keyword(s):  
Machine Learning Techniques ◽  
Reconfigurable Control ◽  
Dynamically Reconfigurable ◽  
Learning Techniques ◽  
Robot Systems ◽  
Field Programmable ◽  
Current Task ◽  
Programmable Gate Arrays ◽  
Reconfigurable Software ◽  
Task Sets

AbstractAdvanced mobile robot systems need to accomplish increasingly complex task sets. However, to solve demanding problems, they are typically optimized to a very restricted set of tasks and environments. This work will therefore propose a self-reconfigurable software and hardware architecture to allow the dynamic optimization of a robot system depending on the current situation, i. e. the current task, the robot inner state, and the environment. The proposed framework is based on organic computing principles and unsupervised machine learning techniques. It further uses dynamically reconfigurable Field Programmable Gate Arrays (FPGA) as hardware accelerators. Preliminary results will be presented, which demonstrate the feasibility of the self-reconfiguration approach.

scholarly journals Advances in Smart Environment Monitoring Systems Using IoT and Sensors

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3113 ◽  
Author(s):  
Silvia Liberata Ullo ◽  
G. R. Sinha
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Sustainable Growth ◽  
Machine Learning Techniques ◽  
Sensor Technology ◽  
Smart Environment ◽  
Environment Monitoring ◽  
Learning Techniques ◽  
Quality Water ◽  
Major Factors

Air quality, water pollution, and radiation pollution are major factors that pose genuine challenges in the environment. Suitable monitoring is necessary so that the world can achieve sustainable growth, by maintaining a healthy society. In recent years, the environment monitoring has turned into a smart environment monitoring (SEM) system, with the advances in the internet of things (IoT) and the development of modern sensors. Under this scenario, the present manuscript aims to accomplish a critical review of noteworthy contributions and research studies on SEM, that involve monitoring of air quality, water quality, radiation pollution, and agriculture systems. The review is divided on the basis of the purposes where SEM methods are applied, and then each purpose is further analyzed in terms of the sensors used, machine learning techniques involved, and classification methods used. The detailed analysis follows the extensive review which has suggested major recommendations and impacts of SEM research on the basis of discussion results and research trends analyzed. The authors have critically studied how the advances in sensor technology, IoT and machine learning methods make environment monitoring a truly smart monitoring system. Finally, the framework of robust methods of machine learning; denoising methods and development of suitable standards for wireless sensor networks (WSNs), has been suggested.

scholarly journals Defining Integrated Weed Management: A Novel Conceptual Framework for Models

Agronomy ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 747
Author(s):  
Jonathan Storkey ◽  
Joseph Helps ◽  
Richard Hull ◽  
Alice E. Milne ◽  
Helen Metcalfe
Keyword(s):  
Population Dynamics ◽  
Conceptual Framework ◽  
Herbicide Resistance ◽  
Weed Management ◽  
Integrated Weed Management ◽  
Management Options ◽  
Weed Population ◽  
Weed Population Dynamics ◽  
Population Dynamics Models ◽  
Dynamics Models

Weed population dynamics models are an important tool for predicting the outcome of alternative Integrated Weed Management (IWM) scenarios. The growing problem of herbicide resistance has increased the urgency for these tools in the design of sustainable IWM solutions. We developed a conceptual framework for defining IWM as a standardised input template to allow output from different models to be compared and to design IWM scenarios. The framework could also be used as a quantitative metric to determine whether more diverse systems are more sustainable and less vulnerable to herbicide resistance using empirical data. Using the logic of object-oriented programming, we defined four classes of weed management options based on the stage in the weed life cycle that they impact and processes that mediate their effects. Objects in the same class share a common set of properties that determine their behaviour in weed population dynamics models. Any weed control “event” in a system is associated with an object, meaning alternative management scenarios can be built by systematically adding events to a model either to compare existing systems or design novel approaches. Our framework is designed to be generic, allowing IWM systems from different cropping systems and countries to be compared.

scholarly journals Abiotic Factors Affecting Seed Germination and Early Seedling Emergence of Large Crabgrass (Digitaria sanguinalis)

2018 ◽  
Vol 36 (0) ◽  
Author(s):  
Y.H. WANG ◽  
Y.L. MA ◽  
G.J. FENG ◽  
H.H. LI
Keyword(s):  
Seed Germination ◽  
Weed Management ◽  
Light Exposure ◽  
Soil Depth ◽  
Abiotic Factors ◽  
Seedling Emergence ◽  
Integrated Weed Management ◽  
Factors Affecting ◽  
Early Seedling ◽  
Large Crabgrass

ABSTRACT: Large crabgrass is one of the worst exotic weed in tropical, subtropical, and temperate regions of the world. In this study, the abiotic factors affecting seed germination and early seedling emergence of large crabgrass were investigated under laboratory conditions. The optimum temperatures of germination occurred at the range from 25 to 35 oC under 12 h light/12 h dark condition. Some seeds could germinate in the dark, but light exposure significantly stimulated the germination. Large crabgrass seed was tolerant to salinity level range of 0 to 160 and low water potential (11% germination at -0.8 MPa). Medium pH had no significant effect on seed germination and more than 90% seeds germination was obtained over a broad pH range from 4.0 to 10.0. Seed germination was significantly influenced by heat-shock and completely inhibited at 140 oC for 5 min. The greatest seedling emergence rate was 96% when seeds were planted at a soil depth of 1 cm. Knowledge of germination biology obtained from this study will be useful in the development of the integrated weed management strategies for this species, and to avoid its establishment as a troublesome weed in economically important cropping regions.

Tolerance and Suppression of Weeds Varies among Carrot Varieties

2017 ◽  
Vol 31 (6) ◽  
pp. 897-902 ◽  
Author(s):  
Jed B. Colquhoun ◽  
Richard A. Rittmeyer ◽  
Daniel J. Heider
Keyword(s):  
Weed Management ◽  
Yield Loss ◽  
Plant Density ◽  
Control Measures ◽  
Integrated Weed Management ◽  
Future Research ◽  
Canopy Development ◽  
Stand Establishment ◽  
Carrot Plant ◽  
Vegetative Canopy

Slow carrot emergence and canopy development render the crop a poor competitor with weeds. In this study, the ability to suppress weeds and maintain yield in the presence of weeds was compared among nine carrot varieties that included those selected by plant breeders for rapid vegetative canopy development compared to traditional varieties. Two weed management treatments were compared: handweeding for 21 d after carrot seeding versus handweeding for the entire carrot season. In years and locations with low to moderate weed pressure, such as in the 2014 study, differences among carrot varieties in weed competitiveness or tolerance were less apparent and therefore less relevant. Maximum carrot yield loss to weed competition among varieties was 28% in 2014. Yield loss in the presence of weeds was 15% or less with six of the nine carrot varieties. However, when weed pressure was intense in the 2015 study, both carrot plant density and carrot canopy development were inversely related to weed biomass. Carrot yield loss in the presence of weeds ranged from 38 to 87%. Despite correcting seeding populations for differences in germination among carrot varieties, carrot stand establishment varied greatly and would likely affect subsequent weed control measures such as timely cultivation or herbicide application. Future research efforts are warranted that consider carrot stand establishment factors and their relationship with integrated weed management programs.

Weed Science Beyond the Weeds: The Role of Integrated Weed Management (IWM) in Agroecosystem Health

Weed Science ◽  
1996 ◽  
Vol 44 (2) ◽  
pp. 437-445 ◽  
Author(s):  
Clarence J. Swanton ◽  
Stephen D. Murphy
Keyword(s):  
Cover Crops ◽  
Weed Management ◽  
Crop Yields ◽  
Crop Productivity ◽  
Integrated Weed Management ◽  
Spatial And Temporal Scales ◽  
Weed Population Dynamics ◽  
Environmental Goals ◽  
Predictive Approaches

Integrated weed management (IWM) research has focused on how crop yields and weed interference are affected by changes in management, e.g., tillage, herbicide application timing and rates, cover crops, and planting patterns. Acceptance of IWM will depend on recommendation of specific strategies that manage weeds and maintain crop productivity; such research will and should continue. However, IWM needs to move from a descriptive to a predictive phase if long-term strategies are to be adopted. Linking management changes with crop-weed modeling that includes such components as weed population dynamics and the ecophysiological basis of competition will help predict future weed problems and solutions and the economic risks and benefits of intervention. Predictive approaches would help incorporate IWM into models of the processes that occur in agricultural systems at wider spatial and temporal scales, i.e., in agroecosystems comprised of the interactions among organisms (including humans) and the environment. It is at these larger scales that decisions about management are initiated and where questions about the long-term consequences and constraints of IWM and agriculture are often asked. These questions can be addressed by agroecosystem health, an approach that integrates biophysical, social, and economic concerns and recognizes that agriculture is part of a world with many complex subsystems and interactions. Indicators are used to examine the status of an agroecosystem, e.g., whether or not it contains all that is necessary to continue functioning. Indicators include soil quality, crop productivity, and water quality; all of these are related to the rationale of IWM, hence IWM can be linked to agroecosystem health. Ancillary effects of using IWM relate to other indicators such as diversity and energy efficiency. Linking IWM to agroecosystem health has at least two benefits: (1) predictive models within IWM can be incorporated into larger agroecosystem models to explore hitherto unforseen problems or benefits of IWM, and (2) the relevance and benefits of IWM should become clearer to the public and government agencies who otherwise might not examine how IWM promotes many of the larger social, economic and environmental goals being promulgated.

Weed seed return as influenced by the critical weed-free period in corn (Zea mays L.)

1999 ◽  
Vol 79 (1) ◽  
pp. 165-167 ◽  
Author(s):  
Clarence J. Swanton ◽  
Kevin Chandler ◽  
Anil Shrestha
Keyword(s):  
Weed Management ◽  
Zea Mays L ◽  
Soil Surface ◽  
Management Systems ◽  
Integrated Weed Management ◽  
Critical Periods ◽  
Weed Seed ◽  
Weed Population ◽  
Weed Population Dynamics ◽  
Total Seed

Seed return from later emerging weeds is a concern in weed management systems based on critical periods of control. A study in Ontario found that estimated weed seed return to the soil surface was influenced by the duration of weed control in corn and the prevailing environmental conditions. Weeds emerging after the 8- to 11-leaf stage of corn growth did not cause an increase in total seed number compared to the residual seed bank in the weed-free control. Key words: Seedbank, weed population dynamics, integrated weed management

Sign in / Sign up

Export Citation Format

Share Document