scholarly journals Digging roots is easier with AI

2021 ◽  
Author(s):  
Eusun Han ◽  
Abraham George Smith ◽  
Roman Kemper ◽  
Rosemary White ◽  
John Kirkegaard ◽  
...  
Keyword(s):  
Root Length Density ◽  
Automatic Segmentation ◽  
Soil Core ◽  
Significant Relationships ◽  
Root Sample ◽  
Root Measurement ◽  
Rooting Density ◽  
Recent Developments ◽  
Plant Image ◽  
Time Required

Abstract The scale of root quantification in research is often limited by the time required for sampling, measurement and processing samples. Recent developments in Convolutional Neural Networks (CNN) have made faster and more accurate plant image analysis possible which may significantly reduce the time required for root measurement, but challenges remain in making these methods accessible to researchers without an in-depth knowledge of Machine Learning. We analyzed root images acquired from three destructive root samplings using the RootPainter CNN-software that features an interface for corrective annotation for easier use. Root scans with and without non-root debris were used to test if training a model, i.e., learning from labeled examples, can effectively exclude the debris by comparing the end-results with measurements from clean images. Root images acquired from soil profile walls and the cross-section of soil cores were also used for training and the derived measurements were compared with manual measurements. After 200 minutes of training on each dataset, significant relationships between manual measurements and RootPainter-derived data were noted for monolith (R 2=0.99), profile wall (R 2=0.76) and core-break (R 2=0.57). The rooting density derived from images with debris was not significantly different from that derived from clean images after processing with RootPainter. Rooting density was also successfully calculated from both profile wall and soil core images, and in each case the gradient of root density with depth was not significantly different from manual counts. Differences in root-length density (RLD: cm cm -3) between crops with contrasting root systems were captured using automatic segmentation at soil profiles with high RLD (1 to 5 cm cm -3) as well as at low RLD (0.1 to 0.3 cm cm -3). Our results demonstrate that the proposed approach using CNN can lead to substantial reductions in root sample processing workloads, increasing the potential scale of future root investigations.

scholarly journals Digging roots is easier with AI

2020 ◽  
Author(s):  
Eusun Han ◽  
Abraham George Smith ◽  
Roman Kemper ◽  
Rosemary White ◽  
John Kirkegaard ◽  
...  
Keyword(s):  
Soil Core ◽  
Significant Relationships ◽  
Root Sample ◽  
Root Measurement ◽  
Rooting Density ◽  
Potential Scale ◽  
Recent Developments ◽  
Plant Image ◽  
Time Required ◽  
Derived Data

AbstractThe scale of root quantification in research is often limited by the time required for sampling, measurement and processing samples. Recent developments in Convolutional Neural Networks (CNN) have made faster and more accurate plant image analysis possible which may significantly reduce the time required for root measurement, but challenges remain in making these methods accessible to researchers without an in-depth knowledge of Machine Learning. We analyzed root images acquired from three destructive root samplings using the RootPainter CNN-software that features an interface for corrective annotation for easier use. Root scans with and without non-root debris were used to test if training a model, i.e., learning from labeled examples, can effectively exclude the debris by comparing the end-results with measurements from clean images. Root images acquired from soil profile walls and the cross-section of soil cores were also used for training and the derived measurements were compared with manual measurements. After 200 minutes of training on each dataset, significant relationships between manual measurements and RootPainter-derived data were noted for monolith (R2=0.99), profile wall (R2=0.76) and core-break (R2=0.57). The rooting density derived from images with debris was not significantly different from that derived from clean images after processing with RootPainter. Rooting density was also successfully calculated from both profile wall and soil core images, and in each case the gradient of root density with depth was not significantly different from manual counts. Our results demonstrate that the proposed approach using CNN can lead to substantial reductions in root sample processing workloads, increasing the potential scale of future root investigations.

Soil core and minirhizotron comparison for the determination of root length density

1994 ◽  
Vol 161 (2) ◽  
pp. 225-232 ◽  
Author(s):  
Benjamin K. Samson ◽  
Thomas R. Sinclair
Keyword(s):  
Root Length ◽  
Root Length Density ◽  
Soil Core

scholarly journals Developing a 3- to 6-state EEG-based brain-computer interface for a robotic manipulator control

2017 ◽  
Author(s):  
Yuriy Mishchenko ◽  
Murat Kaya ◽  
Erkan Ozbay ◽  
Hilmi Yanar
Keyword(s):  
Error Rate ◽  
High Performance ◽  
Processing System ◽  
Robotic Control ◽  
Signal Processing System ◽  
Eeg Data ◽  
Recent Developments ◽  
Assistive Systems ◽  
Time Required ◽  
Bci System

AbstractRecent developments in BCI techniques have demonstrated high-performance control of robotic prosthetic systems primarily via invasive methods. In this work we develop an electroencephalography (EEG) based noninvasive BCI system that can be used for a similar, albeit lower-speed robotic control, and a signal processing system for detecting user’s mental intent from EEG data based on up to 6-state motor-imagery BCI communication paradigm. We examine the performance of that system on experimental data collected from 12 healthy participants and analyzed offline. We show that our EEG BCI system can correctly identify different motor imageries in EEG data with high accuracy: 3 out of 12 participants achieved accuracy of 6-state communication in 80-90% range, while 2 participants could not achieve a satisfactory accuracy. We further implement an online BCI system for control of a virtual 3 degree-of-freedom prosthetic manipulator and test it with our 3 best participants. The participants’ ability to control the BCI is quantified by using the percentage of successfully completed BCI tasks, the time required to complete a task, and the error rate. 2 participants were able to successfully complete 100% of the test tasks, demonstrating on average the error rate of 80% and requiring 5-10 seconds to execute a manipulator move. 1 participant failed to demonstrate a satisfactory performance in online trials. Our results lay a foundation for further development of EEG BCI-based robotic assistive systems and demonstrate that EEG-based BCI may be feasible for robotic control by paralyzed and immobilized individuals.

scholarly journals MEASUREMENT OF ROOT LENGTH DENSITY IN INTACT SAMPLES USING X-RADIOGRAPHY AND IMAGE ANALYSIS

2011 ◽  
Vol 19 (2) ◽  
pp. 145 ◽  
Author(s):  
Alain Pierret ◽  
Chris J Moran ◽  
Colin B Mclachlan ◽  
John M Kirby
Keyword(s):  
Image Analysis ◽  
Root Length ◽  
Root Length Density ◽  
Spatial Arrangement ◽  
Plant Performance ◽  
Non Invasive ◽  
Root Sample ◽  
Measuring Techniques ◽  
Measurement Algorithm ◽  
Invasive Measurement

Measurement of root system attributes is of critical importance to understand and model plant growth. Root length density, the length of roots per unit volume of soil, is one of the important parameters required to understand plant performance. Measuring techniques currently in use to assess this parameter, such as for example core washing, are notoriously imprecise and labour-intensive. Roots and soil being inextricably linked, it is virtually impossible to separate them without loosing a significant amount of the root sample to be measured. This noticeably compromises the accuracy of washing techniques. For this reason, non-invasive measurement approaches are highly desirable. Here, a method based on the combination of X-radiography and image analysis is proposed as a new alternative for the measurement of root length density from intact samples. The successive steps of the method, from sampling to image acquisition are briefly described. A specific measurement algorithm, designed to account for the complex spatial arrangement of the roots within the samples is then presented and discussed in detail.

Interatomic Potentials for Atomistic Simulations

MRS Bulletin ◽  
1996 ◽  
Vol 21 (2) ◽  
pp. 17-19 ◽  
Author(s):  
Arthur F. Voter
Keyword(s):  
Atomistic Simulation ◽  
Large Scale ◽  
Materials Science ◽  
Interatomic Potential ◽  
Computer Time ◽  
Atomistic Simulations ◽  
Interatomic Potentials ◽  
Materials Research ◽  
Recent Developments ◽  
Time Required

Atomistic simulations are playing an increasingly prominent role in materials science. From relatively conventional studies of point and planar defects to large-scale simulations of fracture and machining, atomistic simulations offer a microscopic view of the physics that cannot be obtained from experiment. Predictions resulting from this atomic-level understanding are proving increasingly accurate and useful. Consequently, the field of atomistic simulation is gaining ground as an indispensable partner in materials research, a trend that can only continue. Each year, computers gain roughly a factor of two in speed. With the same effort one can then simulate a system with twice as many atoms or integrate a molecular-dynamics trajectory for twice as long. Perhaps even more important, however, are the theoretical advances occurring in the description of the atomic interactions, the so-called “interatomic potential” function.The interatomic potential underpins any atomistic simulation. The accuracy of the potential dictates the quality of the simulation results, and its functional complexity determines the amount of computer time required. Recent developments that fit more physics into a compact potential form are increasing the accuracy available per simulation dollar.This issue of MRS Bulletin offers an introductory survey of interatomic potentials in use today, as well as the types of problems to which they can be applied. This is by no means a comprehensive review. It would be impractical here to attempt to present all the potentials that have been developed in recent years. Rather, this collection of articles focuses on a few important forms of potential spanning the major classes of materials bonding: covalent, metallic, and ionic.

scholarly journals Root system architecture in winter varieties of spelt (TriticumspeltaL.)

2018 ◽  
Vol 10 ◽  
pp. 01019
Author(s):  
Andrzej Żabiński ◽  
Urszula Sadowska
Keyword(s):  
Root System ◽  
Root Length ◽  
Root Length Density ◽  
Computer Software ◽  
Morphological Structure ◽  
Specific Root Length ◽  
Dry Mass ◽  
Root System Architecture ◽  
Root Diameter ◽  
Soil Core

The objective of the study was determination of the variability of morphometry and comparison of the morphological structure of the root system in winter cultivars of spelt. Four spelt cultivars were used in the study: Frankencorn, Oberkulmer Rotkorn, Schwabenkorn and Ostro. The material for the study originated from a field experiment. The roots were collected using the soil core method to the depth of 30 cm, from the rows and inter-rows, then the roots were separated using a semi-automatic hydropneumatic scrubber. The cleaned roots were manually separated and scanned, obtaining their digital images. Image analysis was performed using the Aphelion computer software. In order to characterize the root system of the spelt cultivars included in the study, values of the following indexes were determined: root dry mass (RDM), root length density (RLD), specific root length (SRL), mean root diameter (MD). Based on the obtained results it was determined that the RDM, MD and RLD indexes in all spelt cultivars attain the highest values in the row, at the depth 0–5 cm.The highest value of the RDM and MD indexes characterized the root system of the Ostro cultivar at the depth 0–5 cm. The Oberkulmerrotkorn spelt cultivar was distinguished among the tested objects by the highest value of the SRL index.

scholarly journals Semiautomatic, Quantitative Measurement of Aortic Valve Area Using CTA: Validation and Comparison with Transthoracic Echocardiography

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
V. Tuncay ◽  
N. Prakken ◽  
P. M. A. van Ooijen ◽  
R. P. J. Budde ◽  
T. Leiner ◽  
...  
Keyword(s):  
Aortic Valve ◽  
Transthoracic Echocardiography ◽  
Interobserver Variability ◽  
Automatic Segmentation ◽  
Initial Contour ◽  
Aortic Valve Area ◽  
Semiautomatic Segmentation ◽  
Mean Differences ◽  
Time Required ◽  
Valve Area

Objective. The aim of this work was to develop a fast and robust (semi)automatic segmentation technique of the aortic valve area (AVA) MDCT datasets.Methods. The algorithm starts with detection and cropping of Sinus of Valsalva on MPR image. The cropped image is then binarized and seed points are manually selected to create an initial contour. The contour moves automatically towards the edge of aortic AVA to obtain a segmentation of the AVA. AVA was segmented semiautomatically and manually by two observers in multiphase cardiac CT scans of 25 patients. Validation of the algorithm was obtained by comparing to Transthoracic Echocardiography (TTE). Intra- and interobserver variability were calculated by relative differences. Differences between TTE and MDCT manual and semiautomatic measurements were assessed by Bland-Altman analysis. Time required for manual and semiautomatic segmentations was recorded.Results. Mean differences from TTE were −0.19 (95% CI: −0.74 to 0.34) cm2for manual and −0.10 (95% CI: −0.45 to 0.25) cm2for semiautomatic measurements. Intra- and interobserver variability were 8.4 ± 7.1% and 27.6 ± 16.0% for manual, and 5.8 ± 4.5% and 16.8 ± 12.7% for semiautomatic measurements, respectively.Conclusion. Newly developed semiautomatic segmentation provides an accurate, more reproducible, and faster AVA segmentation result.

High Performance Materials Development in the 21st Century: Trends and Directions

2004 ◽  
Vol 449-452 ◽  
pp. 7-12
Author(s):  
James C. Williams
Keyword(s):  
Material Properties ◽  
Gas Turbines ◽  
High Performance ◽  
Matrix Composites ◽  
New Materials ◽  
Materials Development ◽  
Recent Developments ◽  
New Material ◽  
Time Required ◽  
The Cost

Product performance including the cost of ownership is becoming increasingly dependent on the availability of high quality, high performance, affordable materials of construction. Today, the requirements placed on a new material for a high performance structural application extend well beyond the improvement of one or more material properties. This makes the introduction of a new material a multi-faceted activity. Modern structural materials derive their performance from a combination of composition and processing, the results of which are inextricably intertwined. This statement pertains to both metallic alloys and to fiber reinforced composite materials. In addition, material cost and the reproducibility of material properties are becoming more central as acceptance criteria for incorporating new materials into new products. This paper will use examples of recent developments in materials for aircraft gas turbines to depict the materials introduction process. Some of these developments have been successful and others have not. These examples illustrate the changing picture that represents the successful introduction of a new structural material, even in a high performance, high value product such as a gas turbine. Specific examples will include metal matrix composites, Ni-base alloys and improved reliability Ti alloys. The basis for successful introduction, or lack thereof will be discussed. While the examples are specific to gas turbines, they are generally instructive and depict the growing complexity of the process of developing and introducing new materials into a high value product. An additional issue for all new materials introduction is the time required to achieve product readiness. As the time required for product design decreases, there has been little commensurate reduction in materials development cycle time. This matter also will be discussed and some possible reasons and potential solutions will be described.

scholarly journals Recent Developments on Ethylene Dimerization with Focus on Alphabutol Optimization

2019 ◽  
Vol 8 (10) ◽  
pp. 3969-3975
Keyword(s):  
Heat Exchanger ◽  
Ethylene Dimerization ◽  
Research Technology ◽  
Area Of Interest ◽  
Significant Area ◽  
Recent Developments ◽  
Time Required ◽  
Operational Issues ◽  
Operational Processes ◽  
And Control

Butene-1 is an essential compound or co-monomer typically used to regulate and control the density of both high-density polyethylene (HDPE) and linear low-density polyethylene (LLDPE). The production of Butene-1 has become a significant area of interest to the industrial and educational-research sectors. Alphabutol technology is one of the Butene-1 production processes. This paper attempts to find a problem that has not been addressed by previous research on production of Butene-1 by using ethylene demineralization route focussing on Alphabutol Technology. The first part of this paper is on the ethylene dimerization techniques available in the literature. Most research on the ethylene dimerization technique emphasized on how to enhance the selectivity of Butene-1 from ethylene using different types of catalyst. The second part of this paper reviews the operational processes used to minimise fouling reported in the literature review. Most of the literatures focused ethylene dimerization and not on the operational issues to be overcome during chemical reactions to enhance the selectivity of Butene-1. Fouling problem in Alphabutol process is still an area that is not adequately addressed in the literature. There is also no literature on operating or maintenance procedure to address these problems of the technology. Therefore, there is still room for improvement on the ethylene dimerization research technology, particularly in the operational process and conditions where the improvement in the reaction parameters of the Alphabutol reactor can improve selectivity of butene-1, extend the run time of the heat exchanger and reduce the time required to clean the heat exchanger fouling.

scholarly journals Sugarcane root length density and distribution from root intersection counting on a trench-profile

2011 ◽  
Vol 68 (1) ◽  
pp. 94-101 ◽  
Author(s):  
Mateus Carvalho Basilio de Azevedo ◽  
Jean Louis Chopart ◽  
Cristiane de Conti Medina
Keyword(s):  
Root Length ◽  
Root Length Density ◽  
Soil Layer ◽  
Soil Tillage ◽  
Soil Core ◽  
Critical Feature ◽  
Saccharum Spp ◽  
In Situ Method ◽  
Cropping Season

Root length density (RLD) is a critical feature in determining crops potential to uptake water and nutrients, but it is difficult to be measured. No standard method is currently available for assessing RLD in the soil. In this study, an in situ method used for other crops for studying root length density and distribution was tested for sugarcane (Saccharum spp.). This method involved root intersection counting (RIC) on a Rhodic Eutrudox profile using grids with 0.05 x 0.05 m and modeling RLD from RIC. The results were compared to a conventional soil core-sampled method (COR) (volume 0.00043 m³). At four dates of the cropping season in three tillage treatments (plowing soil, minimum tillage and direct planting), with eight soil depths divided in 0.1 m soil layer (between 0-0.6 and 1.6-1.8 m) and three horizontal distances from the row (0-0.23, 0.23-0.46 and 0.46-0.69 m), COR and RIC methods presented similar RLD results. A positive relationship between COR and RIC was found (R² = 0.76). The RLD profiles considering the average of the three row distances per depth obtained using COR and RIC (mean of four dates and 12 replications) were close and did not differ at each depth of 0.1 m within a total depth of 0.6 m. Total RLD between 0 and 0.6 m was 7.300 and 7.100 m m-2 for COR and RIC respectively. For time consumption, the RIC method was tenfold less time-consuming than COR and RIC can be carried out in the field with no need to remove soil samples. The RLD distribution in depth and row distance (2-D variability) by RIC can be assessed in relation to the soil properties in the same soil profiles. The RIC method was suitable for studying these 2-D (depth and row distance in the soil profile) relationships between soil, tillage and root distribution in the field.

Sign in / Sign up

Export Citation Format

Share Document