Transactions of the ASABE最新文献

{"title":"Investigation of Branch Accessibility with a Robotic Pruner for Pruning Apple Trees","authors":"A. Zahid, Long He, D. Choi, J. Schupp, P. Heinemann","doi":"10.13031/trans.14132","DOIUrl":"https://doi.org/10.13031/trans.14132","url":null,"abstract":"HighlightsA branch accessibility simulation was performed for robotic pruning of apple trees.A virtual tree environment was established using a kinematic manipulator model and an obstacle model.Rapidly-exploring random tree (RRT) was combined with smoothing and optimization for improved path planning.Effects on RRT path planning of the approach angle of the end-effector and cutter orientation at the target were studied.Abstract. Robotic pruning is a potential solution to reduce orchard labor and associated costs. Collision-free path planning of the manipulator is essential for successful robotic pruning. This simulation study investigated the collision-free branch accessibility of a six rotational (6R) degrees of freedom (DoF) robotic manipulator with a shear cutter end-effector. A virtual environment with a simplified tall spindle tree canopy was established in MATLAB. An obstacle-avoidance algorithm, rapidly-exploring random tree (RRT), was implemented for establishing collision-free paths to reach the target pruning points. In addition, path smoothing and optimization algorithms were used to reduce the path length and calculate the optimized path. Two series of simulations were conducted: (1) performance and comparison of the RRT algorithm with and without smoothing and optimization, and (2) performance of collision-free path planning considering different approach poses of the end-effector relative to the target branch. The simulations showed that the RRT algorithm successfully avoided obstacles and allowed the manipulator to reach the target point with 23 s average path finding time. The RRT path length was reduced by about 28% with smoothing and by 25% with optimization. The RRT smoothing algorithm generated the shortest path lengths but required about 1 to 3 s of additional computation time. The lowest coefficient of variation and standard deviation values were found for the optimization method, which confirmed the repeatability of the method. Considering the different end-effector approach poses, the simulations suggested that successfully finding a collision-free path was possible for branches with no existing path using the ideal (perpendicular cutter) approach pose. This study provides a foundation for future work on the development of robotic pruning systems. Keywords: Agricultural robotics, Collision-free path, Manipulator, Path planning, Robotic pruning, Virtual tree environment.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"22 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86337276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Downwind Spray Drift Assessment for Airblast Sprayer Applications in a Modern Apple Orchard System","authors":"A. Rathnayake, L. Khot, G. Hoheisel, H. Thistle, M. Teske, M. Willett","doi":"10.13031/TRANS.14324","DOIUrl":"https://doi.org/10.13031/TRANS.14324","url":null,"abstract":"HighlightsAirblast sprayer drift potential was evaluated up to 183 m (600 ft) downwind from an orchard edge.A central leader apple orchard was sprayed at dormant and full canopy stage.Higher drift at full canopy stage was likely due to higher wind speeds and lower humidity.String and artificial foliage samplers had higher collection efficiencies than Mylar cards.Abstract. Risk assessment of orchard pesticide spraying is currently based on spray drift estimation using a worst-case scenario (dormant stage). However, most spray applications are conducted during non-dormant canopy growth stages. Such overestimation leads to restrictive operational regulations in pest management activities. Therefore, field data were generated and studied for a mechanistic model that will predict spray drift from airblast spray applications in tree fruit orchards. Spray trials were conducted at dormant and full canopy growth stages in a central leader trained apple orchard. An axial-fan airblast sprayer sprayed fluorescent tracer in the third row from the orchard’s downwind edge, with four passes being one run. A total of 20 runs, i.e., 17 spray runs and three blanks, were performed during each of the two crop growth stages. Mylar cards, artificial foliage (AF), and horizontal strings (HS) were used to quantify drifting spray deposition up to 183 m (600 ft) downwind. Within the orchard, the deposition on card samplers 3 m upwind of the sprayed row was 21.94% ±4.63% (mean ± standard deviation) of applied dose (AD) at dormant stage and 16.02% ±2.86% AD at full canopy stage. Deposition downwind and adjacent (-3 m) to the sprayed row was 17.92% ±2.70% AD and 7.15% ±1.78% AD at dormant and full canopy stages, respectively. Spray drift decreased substantially at the orchard edge to 3.18% ±1.30% AD at dormant stage and 2.30% ±1.16% AD at full canopy stage. Spray drift was very low at 183 m (600 ft) downwind of the orchard, with deposition of 0.002% ±0.003% AD at dormant stage and 0.003% ±0.004% AD at full canopy stage. Deposition data collected at common sampler locations showed that HS and AF samplers collected significantly (p < 0.05) more drifting spray than card samplers. Downwind speeds had a strong linear relationship with spray drift at both growth stages (dormant: R2= 0.80, full canopy: R2= 0.86), while the influence of temperature and humidity could not be directly observed from the collected data. Keywords: Airblast spraying, Deposit samplers, Dormant and full canopy, Drift, Modern orchard systems.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"112 1","pages":"601-613"},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87712941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reduction of Torsional Vibration in Resonance Phenomena for Tractor Power Take-Off Drivelines Using Torsional Damper","authors":"Dang Ahn, In-Kyung Shin, Jooseon Oh, W. Chung, Hyun-Woo Han, Ji-Tae Kim, Young-Jun Park","doi":"10.13031/TRANS.13971","DOIUrl":"https://doi.org/10.13031/TRANS.13971","url":null,"abstract":"HighlightsRattling of tractor power take-off drivelines can be detrimental to operators.A novel driveline model, which includes a torsional damper, was constructed.The behavior of the model was validated against that of an actual tractor driveline.The validated model was used to determine the optimal torsional damper parameters.These optimal parameters were validated by laboratory tests.Abstract. Rattle noise and high levels of vibration in agricultural tractors lower the productivity of the operators and may cause serious health issues in them. This study examined a method for preventing resonance and reducing the torsional vibration that causes rattling in tractor power take-off (PTO) drivelines in the idle state using a two-stage torsional damper. The PTO driveline was simplified to a 6-DOF model based on the principle of equivalent mass moment of inertia using commercial simulation software. The variations in the angular velocity of the PTO drive shaft in an actual tractor were measured and compared to the simulation results using a single-stage torsional damper to validate the model. Using this validated PTO driveline model, the pre spring of a two-stage torsional damper was investigated to determine its optimal torsional stiffness to minimize torsional vibration. The simulation results showed that the variations in the angular velocity of the PTO drive shaft decreased as the torsional stiffness of the pre spring decreased; accordingly, an appropriate torsional stiffness reduced the variation in the angular velocity delivered to the PTO drive shaft. The optimal torsional stiffness of the pre spring was determined by considering the manufacturing limitations of the torsional damper and the magnitude of the input engine torque. A pre spring with this optimal torsional stiffness was installed on an actual PTO driveline to measure the angular velocity transmissibility, which was the ratio of the variation in the angular velocity of the engine flywheel to the variation in the angular velocity of the PTO drive shaft, and the results were compared with those of the simulation. When the angular velocity of the engine was 850 rpm, the angular velocity transmissibility of the PTO drive shaft was 0.4 in the actual test, similar to the value of 0.29 obtained using the simulation. Thus, the simulation-optimized pre spring was able to avoid the resonance domain, while considerably reducing the torsional vibration that leads to rattling. The results of this study support the safe operation of agricultural tractors and guide the evaluation of torsional damper configurations of different vehicles. Keywords: PTO driveline, Resonance, Simulation model, Torsional damper, Torsional vibration, Tractor rattle.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"54 1","pages":"365-376"},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90088334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of Intelligent Carbon Fiber Heater on Pig Behavior, Production Performance, and Energy Consumption","authors":"Li Xiusong, Zhangying Ye, Guo-Qun Li, Pan Shen, Songming Zhu, Zhao Shiguang, Dezhao Liu, Zhang Jie, Shen Zhongyin, Gao Weiwei","doi":"10.13031/TRANS.14104","DOIUrl":"https://doi.org/10.13031/TRANS.14104","url":null,"abstract":"HighlightsIntelligent carbon fiber heaters (ICFH) increased the tendency of sows to expose their udders toward the heating area.During the first week after birth, piglets with ICFH used the heating area more frequently and spent less time in the areas close to sows than piglets with incandescent heat lamps (IHL).ICFH helped to reduce the piglet crushing rate.Farrowing houses with ICFH can save 40.6% of the electricity usage compared to IHL.Abstract. Current Chinese heating systems (primarily incandescent heat lamps, IHL) for piglets are energy-consuming, fragile, and short-lived. To overcome these disadvantages, the objectives of this study were to (1) develop an intelligent carbon fiber heater (ICFH) and (2) conduct field experiments to evaluate the performance of the developed heater. The ICFH mainly consisted of an intelligent control unit, a carbon fiber tube, and a heater cover. Three treatments, i.e., ICFH, ICFH with light (ICFHL), and IHL, were respectively assigned to three farrowing pig houses. Pig behaviors, production performance, and electricity usage were recorded in two complete farrowing batches. The results showed that the sows in the ICFH and ICFHL treatments exposed their udders toward the heating area more often than their backs (p < 0.01). Piglets at 1 to 3 days of age in the ICFH and ICFHL treatments increased their time in the heating area by >4.3% (p < 0.01). The proportion of piglets within 0.08 m of the sows was highest for the IHL treatment during 1 to 3 days of age (p < 0.01) but similar among the treatments after day 3 (p = 0.45). The piglet crushing rate in the ICFH and ICFHL treatments was reduced by >2.2% (p < 0.01), while daily weight gain was not significantly different among the treatments (p = 0.16). Using ICFH and ICFHL can reduce electricity usage by 40.6%. It is concluded that the newly developed heater is beneficial for pig thermal comfort, production, and energy savings. Keywords: Automatic sensor technology, Carbon fiber heater, Piglet crushing, PLF.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"95 1","pages":"259-272"},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80286384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Soil Particle Modeling and Parameter Calibration for Use with Discrete Element Method","authors":"Yukun Yang, Baoqin Wen, Longpeng Ding, Liqiao Li, Xinghua Chen, Jingbin Li","doi":"10.13031/trans.14083","DOIUrl":"https://doi.org/10.13031/trans.14083","url":null,"abstract":"HighlightsSoil particle shapes were statistically analyzed, and four representative particles were obtained.A particle model was established using three-dimensional non-contact surface topography.This study used a response surface design method to calibrate significant soil parameters.The simulation parameters were verified by rotary tiller experiment.Abstract. The discrete element method (DEM) has broad prospects for application in soil-tool simulations. To ensure the reliability of simulations, appropriate simulation parameters and particle modeling are essential. Therefore, in this article, a method combining simulation and actual tests is proposed to calibrate the critical soil parameters. First, the effect of soil particle shape on particle contact was considered. Soil particle shapes were statistically analyzed using an improved GrabCut algorithm and k-means algorithm. Four representative soil particles were obtained. Second, a soil particle model was established by microscope and three-dimensional non-contact surface topography. Finally, taking the angle of repose as the response value, the three parameters with significant effects on the angle of repose, i.e., soil shear modulus, Hertz-Mindlin with Johnson-Kendall-Roberts contact model (JKR), and soil-soil restitution coefficient, were obtained via a Plackett-Burman experiment. The optimal value intervals of the significant parameters were determined by the steepest climbing test. A polynomial regression model between the angle of repose and the three significant parameters was established with a Box-Behnken experiment using three factors and three levels. The interactions between the three significant parameters were not significant, as revealed by response surface analysis. The optimal values of the significant parameters were obtained by taking the actual angle of repose as the target and resulted in a soil shear module of 9.8 MPa, JKR of 0.063, and soil-soil restitution coefficient of 0.478. To verify the reliability of the calibrated parameters, the soil angles of repose from the simulation and from actual tests were compared and analyzed. For a simulated angle of repose of 38.5°, the actual angle of repose was 38.6°, and the relative error was 0.26%. DEM was also used to simulate a rotary tiller with the calibrated parameters. The maximum error of the simulated soil throwing angle was less than 10% when compared with the actual throwing angle. The experimental results showed that the calibrated parameters were accurate and can provide a reference for the selection of soil discrete element parameters. Keywords: Angle of repose, Numerical simulation, Parameter calibration, Shape survey, Soil.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"1 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73459413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Proposed Method for Quantifying Thermal Exposure Incurred during Rough-Rice Drying","authors":"S. Graham‐Acquaah, T. Siebenmorgen","doi":"10.13031/TRANS.14063","DOIUrl":"https://doi.org/10.13031/TRANS.14063","url":null,"abstract":"HighlightsDrying conditions affect rice end-use functionality.Thermal exposure incurred by rough rice may differ depending on drying conditions.A framework is proposed for deriving an index that can show how much heat exposure rough rice incurs during drying.Abstract. Heated air is used to dry most rice in the U.S. Thus, commercial rice drying can be considered a thermal process that aims to remove moisture from rough rice until a desired moisture content is reached. Parallels can be drawn between rice drying and thermal sterilization that is targeted at reducing microbial load because moisture content reduction during drying follows similar decay rate kinetics as the reduction in microbial load during thermal sterilization. Given the different combinations of drying air conditions (air temperature and relative humidity), as well as drying and tempering durations, employed in various dryer designs for rice drying and the impact that these conditions have on rice end-use functionality, this study sought to derive a thermal treatment index (drying process values) that is similar to the F0 value concept used in thermal sterilization for quantifying and comparing the thermal exposure incurred by rice during drying under various scenarios. Using data collected from rough-rice drying experiments, a decimal desorption value (Dmv) that represents the duration required to cause a 90% reduction in moisture ratio during drying at a specified temperature was determined, from which a thermal desorption constant (Zmv) that represents the increase in temperature necessary to cause a 90% reduction in Dmv during drying was established. Subsequently, a thermal desorption value (Fmv) was derived to express the duration that a rice lot would have been heat treated at a reference temperature during drying to produce an equivalent effect on moisture content as that produced by the actual drying process. Keywords: End use, Moisture content, Peak viscosity, Postharvest, Relative humidity, Rice, Temperature.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"41 1","pages":"475-484"},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74560343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental Research on the Bending and Fracture Characteristics of Cotton Stalk","authors":"Peng Jiang, Yaping Li, Jiali Li, Hewei Meng, Xiangbin Peng, Bingcheng Zhang, Jiaxing He, Za Kan","doi":"10.13031/trans.14589","DOIUrl":"https://doi.org/10.13031/trans.14589","url":null,"abstract":"HighlightsA two-factor randomized block design was used to study the influence of experimental factors on indicators.Specific fracture energy can indicate the relationship between mass and power.A cotton stalk model was established using the discrete element method (DEM).Abstract. Effectively chopping of the mixture of mulch film and cotton stalk recycled by machine is the only way to achieve subsequent separation of the materials. Cotton stalk is one of the main components of the mixture. According to the working principle of a chopping device, the bending and fracture characteristics of cotton stalk samples were measured. A two-factor random block design was used to study the effects of moisture content and sample location on the plant on the mechanical characteristics of the stalk samples. According to the results, the specific fracture energy of the stalk samples was calculated. The results showed that the relationship between the moisture content and bending performance of the samples was an inverse proportional function in general. However, when the moisture content was 20% to 30%, the fracture energy in the double-support bending tests was low, which was therefore the most suitable condition for chopping. In addition, a cotton stalk model was established using the discrete element method (DEM), and the optimal parameter combination was determined. Compared with the actual test results, the model error of the peak bending force was 1.20%. This study can support the analysis of chopping device simulation and material preparation in experimental research. Keywords: Bending fracture characteristics, Cotton stalk, Discrete element method, Three-point bending test.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"10 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74373485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling Soil Forces on a Rotary Tine Tool in Artificial Soil","authors":"Safal Kshetri, B. Steward, M. Tekeste","doi":"10.13031/trans.14336","DOIUrl":"https://doi.org/10.13031/trans.14336","url":null,"abstract":"HighlightsA mathematical model of soil reaction forces on a rotary tine tool was developed.Soil bin experiments using artificial soil enabled observation of soil failure due to soil-tine interaction.The model-predicted forces were similar to experimentally measured forces.Abstract. Understanding soil-tool interaction can enable better control of weeding tools to achieve higher weeding efficacy. The interaction between a vertical tine (mounted on a rotating disc) and soil was investigated using a mathematical model that estimated soil horizontal forces on the tine operating at different linear and rotational velocities. The kinematics associated with the linear and rotational velocities of the rotary tine tool were modeled, and the shearing and inertial forces were estimated. To evaluate model performance with different experimental factors, two sets of soil bin experiments were conducted using an artificial soil: with one tine to estimate model parameters and with two tines 180° apart. Experimental factors were longitudinal velocity (travel speed) at three levels (0.09, 0.29, and 0.5 m s-1) and speed ratio, i.e., the ratio of longitudinal velocity to peripheral velocity of the tines, at three levels (1, 1.5, and 2). Soil horizontal force and torque on the rotary tine tool were measured. A nonlinear least squares method was used to estimate model parameters from the experimental data, resulting in shearing force coefficients ranging from 2.9 to 37 N and inertial force coefficients ranging from 16 to 528 N s2 m-2. The variations in the shearing and inertial forces on the tine were due to differences in soil failure patterns among the treatments. The predicted longitudinal and tangential forces for two tines using the model showed trends that were similar to the forces measured in the experiment. However, the model overestimated the predicted forces because it did not account for the reduced force on a tine due to soil disturbance created by the other tine. Keywords: Soil-tine interaction, Weed control.","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"69 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85644456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Mechanical Model of Cutting Citrus Fruit Stems Based on Partial Least Squares Method","authors":"Wan Yi, Dun Liu, Yitan Zhang, Hexing Yu, Hongmei Zhao, Kai Wang, Yali Li","doi":"10.13031/TRANS.14093","DOIUrl":"https://doi.org/10.13031/TRANS.14093","url":null,"abstract":"","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"59 1","pages":"577-586"},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84891631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hyperspectral Imaging with Cost-Sensitive Learning for High-Throughput Screening of Loblolly Pine (Pinus taeda L.) Seedlings for Freeze Tolerance","authors":"Yuzhen Lu, K. Payn, P. Pandey, J. Acosta, Austin J. Heine, Trevor D. Walker, Sierra N. Young","doi":"10.13031/TRANS.14708","DOIUrl":"https://doi.org/10.13031/TRANS.14708","url":null,"abstract":"HighlightsA hyperspectral imaging approach was developed for freeze-tolerance phenotyping of loblolly pine seedlings.Image acquisition was conducted before and periodically after artificial freezing of the seedlings.A hyperspectral data processing pipeline was developed to extract the spectra from seedling segments.Cost-sensitive support vector machine (SVM) was used for classifying stressed and healthy seedlings.Post-freeze scanning of seedlings on day 41 achieved the highest screening accuracy of 97%.Abstract. Loblolly pine (Pinus taeda L.) is a commercially important timber species planted across a wide temperature gradient in the southeastern U.S. It is critical to ensure that the planting stock is suitably adapted to the growing environment to achieve high productivity and survival. Long-term field studies, although considered the most reliable method for assessing cold hardiness of loblolly pine, are extremely resource-intensive and time-consuming. The development of a high-throughput screening tool to characterize and classify freeze tolerance among different genetic entries of seedlings will facilitate accurate deployment of highly productive and well-adapted families across the landscape. This study presents a novel approach using hyperspectral imaging to screen loblolly pine seedlings for freeze tolerance. A diverse population of 1549 seedlings raised in a nursery were subjected to an artificial mid-winter freeze using a freeze chamber. A custom-assembled hyperspectral imaging system was used for in-situ scanning of the seedlings before and periodically after the freeze event, followed by visual scoring of the frozen seedlings. A hyperspectral data processing pipeline was developed to segment individual seedlings and extract the spectral data. Examination of the spectral features of the seedlings revealed reductions in chlorophylls and water concentrations in the freeze-susceptible plants. Because the majority of seedlings were freeze-stressed, leading to severe class imbalance in the hyperspectral data, a cost-sensitive learning technique that aims to optimize a class-specific cost matrix in classification schemes was proposed for modeling the imbalanced hyperspectral data, classifying the seedlings into healthy and freeze-stressed phenotypes. Cost optimization was effective for boosting the classification accuracy compared to regular modeling that assigns equal costs to individual classes. Full-spectrum, cost-optimized support vector machine (SVM) models achieved geometric classification accuracies of 75% to 78% before and within 10 days after the freeze event, and up to 96% for seedlings 41 days after the freeze event. The top portions of seedlings were more indicative of freeze events than the middle and bottom portions, leading to better classification accuracies. Further, variable selection enabled significant reductions in wavelengths while achieving even better accuracies of up to 97% than full-spectrum SVM modeling. This study ","PeriodicalId":23120,"journal":{"name":"Transactions of the ASABE","volume":"47 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78723058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}