Maize is pivotal in supporting global agriculture and addressing food security challenges.Crop root systems are critical for water uptake and nutrient acquisition,which impacts yield.Quantitative trait phenotyping is ...Maize is pivotal in supporting global agriculture and addressing food security challenges.Crop root systems are critical for water uptake and nutrient acquisition,which impacts yield.Quantitative trait phenotyping is essential to understand better the genetic factors underpinning maize root growth and development.Root systems are challenging to phenotype given their below-ground,soil-bound nature.In addition,manual trait annotations of root images are tedious and can lead to inaccuracies and inconsistencies between individuals,resulting in data discrepancies.In this study,we explored juvenile root phenotyping in the presence and absence of auxin treat-ment,a key phytohormone in root development,using manual curation and gene expression analyses.In addition,we developed an automated phenotyping pipeline for field-grown maize crown roots by leveraging open-source software.By examining a test set of 11 diverse maize genotypes for juvenile-adult root trait correlations and gene expression patterns,an inconsistent correlation was observed,underscoring the developmental plasticity preva-lent during maize root morphogenesis.Transcripts involved in hormone signaling and stress responses were among differentially expressed genes in roots from 20 diverse maize genotypes,suggesting many molecular processes may underlie the observed phenotypic variance.In particular,co-expressed gene expression networks associated with module-trait relationships included 1,3-β-glucan,which plays a crucial role in cell wall dynamics.This study furthers our understanding of genotype-phenotype relationships,which is relevant for informing agricultural strategies to improve maize root physiology.展开更多
High-throughput phenotyping is the bottleneck for advancing field trait characterization and yield improvement in major field crops.Specifically for sorghum(Sorghum bicolor L.),rapid plant-level yield estimation is hi...High-throughput phenotyping is the bottleneck for advancing field trait characterization and yield improvement in major field crops.Specifically for sorghum(Sorghum bicolor L.),rapid plant-level yield estimation is highly dependent on characterizing the number of grains within a panicle.In this context,the integration of computer vision and artificial intelligence algorithms with traditional field phenotyping can be a critical solution to reduce labor costs and time.Therefore,this study aims to improve sorghum panicle detection and grain number estimation from smartphone-capture images under field conditions.A preharvest benchmark dataset was collected at field scale(2023 season,Kansas,USA),with 648 images of sorghum panicles retrieved via smartphone device,and grain number counted.Each sorghum panicle image was manually labeled,and the images were augmented.Two models were trained using the Detectron2 and Yolov8 frameworks for detection and segmentation,with an average precision of 75%and 89%,respectively.For the grain number,3 models were trained:MCNN(multiscale convolutional neural network),TCNN-Seed(two-column CNN-Seed),and Sorghum-Net(developed in this study).The Sorghum-Net model showed a mean absolute percentage error of 17%,surpassing the other models.Lastly,a simple equation was presented to relate the count from the model(using images from only one side of the panicle)to the field-derived observed number of grains per sorghum panicle.The resulting framework obtained an estimation of grain number with a 17%error.The proposed framework lays the foundation for the development of a more robust application to estimate sorghum yield using images from a smartphone at the plant level.展开更多
The XXV International Grassland Congress was held in Covington,Kentucky,USA,May 14–19,2023.The theme of the conference was Grassland for Soil,Animal,and Human Health.More than 400 presentations were delivered to an e...The XXV International Grassland Congress was held in Covington,Kentucky,USA,May 14–19,2023.The theme of the conference was Grassland for Soil,Animal,and Human Health.More than 400 presentations were delivered to an estimated audience of 650 delegates from more than 50 countries.Here,we outline the general themes presented,as well as a few specific details from some presentations that were invited plenary and keynote speeches.In addition,a select few presentations have now been published in a virtual special issue of Grassland Research—https://onlinelibrary.wiley.com/doi/toc/10.1002/(ISSN)2770-1743.xxv-igc-vi.展开更多
The fall armyworm,Spodoptera frugiperda,is a species native to the Americas and has spread to many countries in Africa and Asia in recent years.Proactive actions for potential invasion of S.frugiperda to China coordin...The fall armyworm,Spodoptera frugiperda,is a species native to the Americas and has spread to many countries in Africa and Asia in recent years.Proactive actions for potential invasion of S.frugiperda to China coordinated by government agencies and agricultural extension systems resulted in timely detection in January 2019 in Yunnan province neighboring onto Myanmar.The extensive monitoring in southern provinces of China since February 2019 resulted in dynamic tracking of S.frugiperda spreading to 13 provincial regions in China within 4 months by May 10,2019,which is crucial for timely management actions in the fields.The first detections of S.frugiperda(corn strain)in China were confirmed using cytochrome oxidase subunit 1(COl)and triosephosphate isomerase(Tpi)genes molecular marker method.In addition to S.frugiperda,larvae of three other noctuid species with similar morphological appearance(S.litura,S.exigna and Mythimna separata)can occur simultaneously and cause similar damage in cornfields in southern China.Thus,we can use both morphological and molecular marker methods to compare larval stages of four noctuid species.Further,we discuss the risk of potential spread of invasive S.frugiperda to other regions and impact on corn production in China.展开更多
Southern corn rust(SCR),caused by the fungal pathogen Puccinia polysora,is a major threat to maize pro-duction worldwide.Efficient breeding and deployment of resistant hybrids are key to achieving durable control of S...Southern corn rust(SCR),caused by the fungal pathogen Puccinia polysora,is a major threat to maize pro-duction worldwide.Efficient breeding and deployment of resistant hybrids are key to achieving durable control of SCR.Here,we report the molecular cloning and characterization of RppC,which encodes an NLR-type immune receptor and is responsible for a major SCR resistance quantitative trait locus.Further-more,we identified the corresponding avirulence effector,AvrRppC,which is secreted by P.polysora and triggers RppC-mediated resistance.Allelic variation of AvrRppC directly determines the effectiveness of RppC-mediated resistance,indicating that monitoring of AvrRppC variants in the field can guide the rational deployment of RppC-containing hybrids in maize production.Currently,RppC is the most frequently deployed SCR resistance gene in China,and a better understanding of its mode of action is crit-ical for extending its durability.展开更多
Diabrotica virgifera virgifera(western corn rootworm,WCR)is one of the most destructive agricultural insect pests in North America.It is highly adaptive to environmental stimuli and crop protection technologies.Howeve...Diabrotica virgifera virgifera(western corn rootworm,WCR)is one of the most destructive agricultural insect pests in North America.It is highly adaptive to environmental stimuli and crop protection technologies.However,little is known about the underlying genetic basis of WCR behavior and adaptation.More specifically,the involvement of small RNAs(s RNAs),especially micro RNAs(mi RNAs),a class of endogenous small non-coding RNAs that regulate various biological processes,has not been examined,and the datasets of putative s RNA sequences have not previously been generated for WCR.To achieve a comprehensive collection of s RNA transcriptomes in WCR,we constructed,sequenced,and analyzed s RNA libraries from different life stages of WCR and northern corn rootworm(NCR),and identified 101 conserved precursor mi RNAs(pre-mi RNAs)in WCR and other Arthropoda.We also identified 277 corn rootworm specific pre-mi RNAs.Systematic analyses of s RNA populations in WCR revealed that its s RNA transcriptome,which includes PIWI-interacting RNAs(pi RNAs)and mi RNAs,undergoes a dynamic change throughout insect development.Phylogenetic analysis of mi RNA datasets from model species reveals that a large pool of species-specific mi RNAs exists in corn rootworm;these are potentially evolutionarily transient.Comparisons of WCR mi RNA clusters to other insect species highlight conserved mi RNA-regulated processes that are common to insects.Parallel Analysis of RNA Ends(PARE)also uncovered potential mi RNA-guided cleavage sites in WCR.Overall,this study provides a new resource for studying the s RNA transcriptome and mi RNA-mediated gene regulation in WCR and other Coleopteran insects.展开更多
Aims The ability to form persistent seed banks is one of the best predictors of species’potential to establish in new ranges.Wild sunflower is native to North America where the formation of persistent seed banks is p...Aims The ability to form persistent seed banks is one of the best predictors of species’potential to establish in new ranges.Wild sunflower is native to North America where the formation of persistent seed banks is promoted by disturbance and it plays a key role on the establishment and persistence of native populations.However,the role of the seed banks on the establishment and persistence of invasive populations has not been studied.Here,we evaluated the role of seed bank and disturbance on the establishment and fitness,and seed persistence in the soil in several sunflower biotypes collected in ruderal(wild Helianthus annuus)and agrestal(natural crop–wild hybrid)habitats of Argentina as well as volunteer populations(progeny of commercial cultivars).Methods In a seed-bank experiment,we evaluated emergence,survival to reproduction,survival of emerged seedlings,inflorescences per plant and per plot under disturbed and undisturbed conditions over 2 years;in a seed-burial experiment,we evaluated seed persistence in the soil over four springs(6,18,30 and 42 months).Important Findings Overall,seedling emergence was early in the growing season(during winter),and it was promoted by disturbance,especially in the first year.Despite this,the number of inflorescences per plot was similar under both conditions,especially in ruderals.In the second year,emergence from the seed bank was much lower,but the survival rate was higher.In the seed-burial experiment,genetic differences were observed but seeds of ruderals and agrestals persisted up to 42 months while seeds of the volunteer did not persist longer than 6 months.The agrestal biotype showed an intermediate behavior between ruderals and volunteers in both experiments.Our findings showed that wild and crop–wild sunflower can form persistent seed banks outside its native range and that disturbance may facilitate its establishment in new areas.展开更多
13-Lipoxygenases(LOXs)initiate the synthesis of jasmonic acid(JA),the best-understood oxylipin hormone in herbivory defense.However,the roles of 9-LOX-derived oxylipins in insect resistance remain unclear.Here,we repo...13-Lipoxygenases(LOXs)initiate the synthesis of jasmonic acid(JA),the best-understood oxylipin hormone in herbivory defense.However,the roles of 9-LOX-derived oxylipins in insect resistance remain unclear.Here,we report a novel anti-herbivory mechanism mediated by a tonoplast-localized 9-LOX,ZmLOX5,and its linolenic acid-derived product,9-hydroxy-10-oxo-12(Z),15(Z)-octadecadienoic acid(9,10-KODA).Transposon-insertional disruption of ZmLOX5 resulted in the loss of resistance to insect herbivory.lox5 knockout mutants displayed greatly reduced wound-induced accumulation of multiple oxylipins and defense metabolites,including benzoxazinoids,abscisic acid(ABA),and JA-isoleucine(JA-Ile).However,exogenous JA-Ile failed to rescue insect defense in lox5 mutants,while applications of 1 mM 9,10-KODA or the JA precursor,12-oxo-phytodienoic acid(12-OPDA),restored wild-type resistance levels.Metabolite profiling revealed that exogenous 9,10-KODA primed the plants for increased production of ABA and 12-OPDA,but not JA-Ile.While none of the 9-oxylipins were able to rescue JA-Ile induction,the lox5 mutant accumulated lower wound-induced levels of Ca^(2+),suggesting this as a potential explanation for lower wound-induced JA.Seedlings pretreated with 9,10-KODA exhibited rapid or more robust woundinduced defense gene expression.In addition,an artificial diet supplemented with 9,10-KODA arrested fall armyworm larvae growth.Finally,analysis of single and double lox5 and lox10 mutants showed that ZmLOX5 also contributed to insect defense by modulating ZmLOX10-mediated green leaf volatile signaling.Collectively,our study uncovered a previously unknown anti-herbivore defense and hormonelike signaling activity for a major 9-oxylipin α-ketol.展开更多
Breakup patterns of agricultural formulations are explored using unsupervised learning techniques to elucidate themechanics of atomization for oil-in-water formulations.Previous researchers have shown these formulatio...Breakup patterns of agricultural formulations are explored using unsupervised learning techniques to elucidate themechanics of atomization for oil-in-water formulations.Previous researchers have shown these formulations succumb to a different breakup mechanism than conventional formulations,beginning with inhomogeneities within the liquid sheet that nucleate holes within the material being sprayed,beginning themechanism responsible for breaking the sheet into droplets.The Latent Dirichlet Allocation(LDA),a Bayesian hierarchical model,is used to explore unsupervised learning relationships between image analysis metrics on spray video data and the resulting atomization droplet size.Latent factors discovered by LDA were used for classification of video segments and achieved 99.9%accuracy(3-fold cross validation).Seventy-five videos were used for regression where each video had a unique measured droplet size distribution(D10,D50,and D90 values)for atomization.Experiments using the features learnt by Latent Dirichlet Allocation used with regression have extremely good results(R^2~0.995 in 3-fold cross validation,R^2~0.963 on never-seen videos),which serves as evidence for the potential use of this model in image analysis of agricultural spray patterns.LDA has huge potential in both learning and predicting atomization patterns[e.g.,driftable fines(drops<150μm)]when used with images based on the breakup phenomena in agricultural spray.These small drop sizes that occur during atomization have the greatest propensity for off-target movement through wind induced drift.LDA proved useful in characterizing current and future formulation designs using only images as witnessed by observations and excellent predictions summarized in this paper.In fact,thesemethods offer potential for use under field conditions to address spray performance based upon images of spray patterns at the nozzle without the need for expensive light scattering equipment often used to measure this phenomenon.展开更多
基金supported by the United States Department of Agriculture(USDA)the National Institute of Food and Agriculture(NIFA)+5 种基金the Agriculture and Food Research Initiative(AFRI)award number GRANT12907916 to DRK and JW Wthe Hatch Act State of Iow a funds IOW 03649 and IOW 05745 to DRKthe Hatch Act and State of Iow a funds IOW04108 to JWWthe Iowa State University Plant Science Institute(JWW)the ISU Crop Bioengineering Center(DRK and JWW)and a Department of Defense(DOD)Science,Mathematics,and Research for Transformation(SMART)scholarship to JBC.HS was supported by NSF BIORETS award number 2147083.
文摘Maize is pivotal in supporting global agriculture and addressing food security challenges.Crop root systems are critical for water uptake and nutrient acquisition,which impacts yield.Quantitative trait phenotyping is essential to understand better the genetic factors underpinning maize root growth and development.Root systems are challenging to phenotype given their below-ground,soil-bound nature.In addition,manual trait annotations of root images are tedious and can lead to inaccuracies and inconsistencies between individuals,resulting in data discrepancies.In this study,we explored juvenile root phenotyping in the presence and absence of auxin treat-ment,a key phytohormone in root development,using manual curation and gene expression analyses.In addition,we developed an automated phenotyping pipeline for field-grown maize crown roots by leveraging open-source software.By examining a test set of 11 diverse maize genotypes for juvenile-adult root trait correlations and gene expression patterns,an inconsistent correlation was observed,underscoring the developmental plasticity preva-lent during maize root morphogenesis.Transcripts involved in hormone signaling and stress responses were among differentially expressed genes in roots from 20 diverse maize genotypes,suggesting many molecular processes may underlie the observed phenotypic variance.In particular,co-expressed gene expression networks associated with module-trait relationships included 1,3-β-glucan,which plays a crucial role in cell wall dynamics.This study furthers our understanding of genotype-phenotype relationships,which is relevant for informing agricultural strategies to improve maize root physiology.
文摘High-throughput phenotyping is the bottleneck for advancing field trait characterization and yield improvement in major field crops.Specifically for sorghum(Sorghum bicolor L.),rapid plant-level yield estimation is highly dependent on characterizing the number of grains within a panicle.In this context,the integration of computer vision and artificial intelligence algorithms with traditional field phenotyping can be a critical solution to reduce labor costs and time.Therefore,this study aims to improve sorghum panicle detection and grain number estimation from smartphone-capture images under field conditions.A preharvest benchmark dataset was collected at field scale(2023 season,Kansas,USA),with 648 images of sorghum panicles retrieved via smartphone device,and grain number counted.Each sorghum panicle image was manually labeled,and the images were augmented.Two models were trained using the Detectron2 and Yolov8 frameworks for detection and segmentation,with an average precision of 75%and 89%,respectively.For the grain number,3 models were trained:MCNN(multiscale convolutional neural network),TCNN-Seed(two-column CNN-Seed),and Sorghum-Net(developed in this study).The Sorghum-Net model showed a mean absolute percentage error of 17%,surpassing the other models.Lastly,a simple equation was presented to relate the count from the model(using images from only one side of the panicle)to the field-derived observed number of grains per sorghum panicle.The resulting framework obtained an estimation of grain number with a 17%error.The proposed framework lays the foundation for the development of a more robust application to estimate sorghum yield using images from a smartphone at the plant level.
文摘The XXV International Grassland Congress was held in Covington,Kentucky,USA,May 14–19,2023.The theme of the conference was Grassland for Soil,Animal,and Human Health.More than 400 presentations were delivered to an estimated audience of 650 delegates from more than 50 countries.Here,we outline the general themes presented,as well as a few specific details from some presentations that were invited plenary and keynote speeches.In addition,a select few presentations have now been published in a virtual special issue of Grassland Research—https://onlinelibrary.wiley.com/doi/toc/10.1002/(ISSN)2770-1743.xxv-igc-vi.
基金This work was supported by the National Key Research and Development Program of China(2018YFD020062)the Modern Agricultural Industry Technology System(CARS-02).
文摘The fall armyworm,Spodoptera frugiperda,is a species native to the Americas and has spread to many countries in Africa and Asia in recent years.Proactive actions for potential invasion of S.frugiperda to China coordinated by government agencies and agricultural extension systems resulted in timely detection in January 2019 in Yunnan province neighboring onto Myanmar.The extensive monitoring in southern provinces of China since February 2019 resulted in dynamic tracking of S.frugiperda spreading to 13 provincial regions in China within 4 months by May 10,2019,which is crucial for timely management actions in the fields.The first detections of S.frugiperda(corn strain)in China were confirmed using cytochrome oxidase subunit 1(COl)and triosephosphate isomerase(Tpi)genes molecular marker method.In addition to S.frugiperda,larvae of three other noctuid species with similar morphological appearance(S.litura,S.exigna and Mythimna separata)can occur simultaneously and cause similar damage in cornfields in southern China.Thus,we can use both morphological and molecular marker methods to compare larval stages of four noctuid species.Further,we discuss the risk of potential spread of invasive S.frugiperda to other regions and impact on corn production in China.
基金supported by grants from the National Key Research and Development Program of China(2021YFF1000302)the National Natural Science Foundation of China(31901550)+2 种基金the Ministry of Science and Technology of China(2016YFD0101803)the National Natural Science Foundation of China(31501326)Innovative Talents in Colleges and Universities of Henan Province(19HASTIT010)was a funding pro-vided by Henan Province government of China.
文摘Southern corn rust(SCR),caused by the fungal pathogen Puccinia polysora,is a major threat to maize pro-duction worldwide.Efficient breeding and deployment of resistant hybrids are key to achieving durable control of SCR.Here,we report the molecular cloning and characterization of RppC,which encodes an NLR-type immune receptor and is responsible for a major SCR resistance quantitative trait locus.Further-more,we identified the corresponding avirulence effector,AvrRppC,which is secreted by P.polysora and triggers RppC-mediated resistance.Allelic variation of AvrRppC directly determines the effectiveness of RppC-mediated resistance,indicating that monitoring of AvrRppC variants in the field can guide the rational deployment of RppC-containing hybrids in maize production.Currently,RppC is the most frequently deployed SCR resistance gene in China,and a better understanding of its mode of action is crit-ical for extending its durability.
基金supported by the Dow Agro SciencesFunding from Beijing Academy of Agriculture and Forestry Sciences(Grant Nos.KJCX20180425 and KJCX20180204 to XY)。
文摘Diabrotica virgifera virgifera(western corn rootworm,WCR)is one of the most destructive agricultural insect pests in North America.It is highly adaptive to environmental stimuli and crop protection technologies.However,little is known about the underlying genetic basis of WCR behavior and adaptation.More specifically,the involvement of small RNAs(s RNAs),especially micro RNAs(mi RNAs),a class of endogenous small non-coding RNAs that regulate various biological processes,has not been examined,and the datasets of putative s RNA sequences have not previously been generated for WCR.To achieve a comprehensive collection of s RNA transcriptomes in WCR,we constructed,sequenced,and analyzed s RNA libraries from different life stages of WCR and northern corn rootworm(NCR),and identified 101 conserved precursor mi RNAs(pre-mi RNAs)in WCR and other Arthropoda.We also identified 277 corn rootworm specific pre-mi RNAs.Systematic analyses of s RNA populations in WCR revealed that its s RNA transcriptome,which includes PIWI-interacting RNAs(pi RNAs)and mi RNAs,undergoes a dynamic change throughout insect development.Phylogenetic analysis of mi RNA datasets from model species reveals that a large pool of species-specific mi RNAs exists in corn rootworm;these are potentially evolutionarily transient.Comparisons of WCR mi RNA clusters to other insect species highlight conserved mi RNA-regulated processes that are common to insects.Parallel Analysis of RNA Ends(PARE)also uncovered potential mi RNA-guided cleavage sites in WCR.Overall,this study provides a new resource for studying the s RNA transcriptome and mi RNA-mediated gene regulation in WCR and other Coleopteran insects.
基金supported by the National Agency for Scientific and Technological Promotion(PICT 2012-2854)by the Universidad Nacional del Sur(PGI 24/A204).
文摘Aims The ability to form persistent seed banks is one of the best predictors of species’potential to establish in new ranges.Wild sunflower is native to North America where the formation of persistent seed banks is promoted by disturbance and it plays a key role on the establishment and persistence of native populations.However,the role of the seed banks on the establishment and persistence of invasive populations has not been studied.Here,we evaluated the role of seed bank and disturbance on the establishment and fitness,and seed persistence in the soil in several sunflower biotypes collected in ruderal(wild Helianthus annuus)and agrestal(natural crop–wild hybrid)habitats of Argentina as well as volunteer populations(progeny of commercial cultivars).Methods In a seed-bank experiment,we evaluated emergence,survival to reproduction,survival of emerged seedlings,inflorescences per plant and per plot under disturbed and undisturbed conditions over 2 years;in a seed-burial experiment,we evaluated seed persistence in the soil over four springs(6,18,30 and 42 months).Important Findings Overall,seedling emergence was early in the growing season(during winter),and it was promoted by disturbance,especially in the first year.Despite this,the number of inflorescences per plot was similar under both conditions,especially in ruderals.In the second year,emergence from the seed bank was much lower,but the survival rate was higher.In the seed-burial experiment,genetic differences were observed but seeds of ruderals and agrestals persisted up to 42 months while seeds of the volunteer did not persist longer than 6 months.The agrestal biotype showed an intermediate behavior between ruderals and volunteers in both experiments.Our findings showed that wild and crop–wild sunflower can form persistent seed banks outside its native range and that disturbance may facilitate its establishment in new areas.
基金supported by United States Department of Agriculture(USDA)-National Institute of Food and Agriculture(NIFA)2017-67013-26524 and 2021-67013-33568 grants awarded to M.V.K.
文摘13-Lipoxygenases(LOXs)initiate the synthesis of jasmonic acid(JA),the best-understood oxylipin hormone in herbivory defense.However,the roles of 9-LOX-derived oxylipins in insect resistance remain unclear.Here,we report a novel anti-herbivory mechanism mediated by a tonoplast-localized 9-LOX,ZmLOX5,and its linolenic acid-derived product,9-hydroxy-10-oxo-12(Z),15(Z)-octadecadienoic acid(9,10-KODA).Transposon-insertional disruption of ZmLOX5 resulted in the loss of resistance to insect herbivory.lox5 knockout mutants displayed greatly reduced wound-induced accumulation of multiple oxylipins and defense metabolites,including benzoxazinoids,abscisic acid(ABA),and JA-isoleucine(JA-Ile).However,exogenous JA-Ile failed to rescue insect defense in lox5 mutants,while applications of 1 mM 9,10-KODA or the JA precursor,12-oxo-phytodienoic acid(12-OPDA),restored wild-type resistance levels.Metabolite profiling revealed that exogenous 9,10-KODA primed the plants for increased production of ABA and 12-OPDA,but not JA-Ile.While none of the 9-oxylipins were able to rescue JA-Ile induction,the lox5 mutant accumulated lower wound-induced levels of Ca^(2+),suggesting this as a potential explanation for lower wound-induced JA.Seedlings pretreated with 9,10-KODA exhibited rapid or more robust woundinduced defense gene expression.In addition,an artificial diet supplemented with 9,10-KODA arrested fall armyworm larvae growth.Finally,analysis of single and double lox5 and lox10 mutants showed that ZmLOX5 also contributed to insect defense by modulating ZmLOX10-mediated green leaf volatile signaling.Collectively,our study uncovered a previously unknown anti-herbivore defense and hormonelike signaling activity for a major 9-oxylipin α-ketol.
文摘Breakup patterns of agricultural formulations are explored using unsupervised learning techniques to elucidate themechanics of atomization for oil-in-water formulations.Previous researchers have shown these formulations succumb to a different breakup mechanism than conventional formulations,beginning with inhomogeneities within the liquid sheet that nucleate holes within the material being sprayed,beginning themechanism responsible for breaking the sheet into droplets.The Latent Dirichlet Allocation(LDA),a Bayesian hierarchical model,is used to explore unsupervised learning relationships between image analysis metrics on spray video data and the resulting atomization droplet size.Latent factors discovered by LDA were used for classification of video segments and achieved 99.9%accuracy(3-fold cross validation).Seventy-five videos were used for regression where each video had a unique measured droplet size distribution(D10,D50,and D90 values)for atomization.Experiments using the features learnt by Latent Dirichlet Allocation used with regression have extremely good results(R^2~0.995 in 3-fold cross validation,R^2~0.963 on never-seen videos),which serves as evidence for the potential use of this model in image analysis of agricultural spray patterns.LDA has huge potential in both learning and predicting atomization patterns[e.g.,driftable fines(drops<150μm)]when used with images based on the breakup phenomena in agricultural spray.These small drop sizes that occur during atomization have the greatest propensity for off-target movement through wind induced drift.LDA proved useful in characterizing current and future formulation designs using only images as witnessed by observations and excellent predictions summarized in this paper.In fact,thesemethods offer potential for use under field conditions to address spray performance based upon images of spray patterns at the nozzle without the need for expensive light scattering equipment often used to measure this phenomenon.
