Search NASA⌕ Search

SEARCH · Search NASA

Results for “crop model”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Split selectable marker systems utilizing inteins facilitate gene stacking in plants

The ability to stack multiple genes in plants is of great importance in the development of crops with desirable traits but can be challenging due to limited selectable marker options. Here we establish split selectable marker systems using protein splicing elements called “inteins” for Agrobacterium-mediated co-transformation in plants. First, we show that such a split selectable marker system can be used effectively in plants to reconstitute a visible marker, RUBY, from two non-functional fragments through tobacco leaf infiltration. Next, to determine the general applicability of our split selectable marker systems, we demonstrate the utility of these systems in the model plants Arabidopsis and poplar by successfully stacking two reporters eYGFPuv and RUBY, using split Kanamycin or Hygromycin resistance markers. In conclusion, this method enables robust plant co-transformation, providing a valuable tool for the simultaneous insertion of multiple genes into both herbaceous and woody plants efficiently.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Wastewater reuse benefits for municipal complete retention lagoons: Life cycle assessment and dynamic modeling

Complete retention lagoons with wastewater reuse for agricultural purposes may offer sustainability advantages over alternative systems for small communities in semiarid regions. This study quantifies the environmental life cycle impact of adopting agriculture water reuse systems using case study data to estimate operating and building infrastructure impacts and spatial–temporal modeling to quantify resource trade-offs. Water reuse system benefits are highly dependent on supply–storage–demand dynamics. The relative size of irrigated agricultural land to the lagoon size was the most significant factor influencing site water application rates. The benefits are sensitive to changes in air emissions occurring from the agricultural land and further emphasize the importance of proper fertilizer management when adopting water reuse systems. Wastewater reuse from complete retention lagoons reduce life cycle GHG emissions, primarily through excavation reductions, offset fertilizer use, and especially from increased crop yields from wastewater reuse at previously rainfed sites.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Reformulation of dicamba herbicide: Impacts on offsite transport and soybean damage

Abstract The herbicide dicamba (3,6‐dichloro‐2‐methoxybenzoic acid) is commonly used to control broadleaf weeds in soybeans. Dicamba, however, is susceptible to volatilization and drift, thereby causing significant plant damage to nontarget crops downwind. Dicamba was reformulated to reduce volatility and off‐target movement. The effectiveness of the dicamba reformulation was assessed by quantifying dicamba emissions following spray application and investigated how meteorological factors influenced the off‐target movement. The experiments were conducted at the University of Minnesota Agricultural Experiment Station (UMORE Park) during the growing season of 2018, 2019, 2021, and 2022. Multiple high‐flow polyurethane foam air samplers were used to measure dicamba concentrations downwind from a 4‐ha soybean field sprayed with dicamba. Dicamba emissions were estimated using backward Lagrangian modeling constrained by the air sample observations. The results indicate that dicamba emissions and downwind transport were significant for several days following application. Further, non‐traited soybeans located within 15–45 m showed substantial dicamba‐related damage. In warmer, drier seasons, increased dicamba emissions caused more severe damage to downwind soybeans, likely worsened by drought stress preventing recovery. Favorable atmospheric conditions that reduced potential drift can be difficult to achieve in terms of the typical weather experienced over agricultural sites in the Upper Midwest. These results indicate that the dicamba reformulation has not adequately prevented significant post‐spray volatilization losses and downwind transport.

Agriculture↗
DOE OSTI2024

Deployment expectations of multi-gigatonne scale carbon removal could have adverse impacts on Asia’s energy-water-land nexus

Abstract Existing studies indicate that future global carbon dioxide (CO 2 ) removal (CDR) efforts could largely be concentrated in Asia. However, there is limited understanding of how individual Asian countries and regions will respond to varying and uncertain scales of future CDR concerning their energy-land-water system. We address this gap by modeling various levels of CDR-reliant pathways under climate change ambitions in Asia. We find that high CDR reliance leads to residual fossil fuel and industry emissions of about 8 Gigatonnes CO 2 yr −1 (GtCO 2 yr −1 ) by 2050, compared to less than 1 GtCO 2 yr −1 under moderate-to-low CDR reliance. Moreover, expectations of multi-gigatonne CDR could delay the achievement of domestic net zero CO 2 emissions for several Asian countries and regions, and lead to higher land allocation and fertilizer demand for bioenergy crop cultivation. Here, we show that Asian countries and regions should prioritize emission reduction strategies while capitalizing on the advantages of carbon removal when it is most viable.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Defining the scope for altering rice leaf anatomy to improve photosynthesis: a modelling approach

Summary Leaf structure plays an important role in photosynthesis. However, the causal relationship and the quantitative importance of any single structural parameter to the overall photosynthetic performance of a leaf remains open to debate. In this paper, we report on a mechanistic model, eLeaf, which successfully captures rice leaf photosynthetic performance under varying environmental conditions of light and CO 2 . We developed a 3D reaction‐diffusion model for leaf photosynthesis parameterised using a range of imaging data and biochemical measurements from plants grown under ambient and elevated CO 2 and then interrogated the model to quantify the importance of these elements. The model successfully captured leaf‐level photosynthetic performance in rice. Photosynthetic metabolism underpinned the majority of the increased carbon assimilation rate observed under elevated CO 2 levels, with a range of structural elements making positive and negative contributions. Mesophyll porosity could be varied without any major outcome on photosynthetic performance, providing a theoretical underpinning for experimental data. eLeaf allows quantitative analysis of the influence of morphological and biochemical properties on leaf photosynthesis. The analysis highlights a degree of leaf structural plasticity with respect to photosynthesis of significance in the context of attempts to improve crop photosynthesis.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Genomic patterns of structural variation among diverse genotypes of Sorghum bicolor and a potential role for deletions in local adaptation

Genomic structural mutations, especially deletions, are an important source of variation in many species and can play key roles in phenotypic diversification and evolution. Previous work in many plant species has identified multiple instances of structural variations (SVs) occurring in or near genes related to stress response and disease resistance, suggesting a possible role for SVs in local adaptation. Sorghum [Sorghum bicolor (L.) Moench] is one of the most widely grown cereal crops in the world. It has been adapted to an array of different climates as well as bred for multiple purposes, resulting in a striking phenotypic diversity. In this study, we identified genome-wide SVs in the Biomass Association Panel, a collection of 347 diverse sorghum genotypes collected from multiple countries and continents. Using Illumina-based, short-read whole-genome resequencing data from every genotype, we found a total of 24,648 SVs, including 22,359 deletions. The global site frequency spectrum of deletions and other types of SVs fit a model of neutral evolution, suggesting that the majority of these mutations were not under any types of selection. Clustering results based on single nucleotide polymorphisms separated the genotypes into eight clusters which largely corresponded with geographic origins, with many of the large deletions we uncovered being unique to a single cluster. Even though most deletions appeared to be neutral, a handful of cluster-specific deletions were found in genes related to biotic and abiotic stress responses, supporting the possibility that at least some of these deletions contribute to local adaptation in sorghum.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Machine and Deep Learning: Artificial Intelligence Application in Biotic and Abiotic Stress Management in Plants

Biotic and abiotic stresses significantly affect plant fitness, resulting in a serious loss in food production. Biotic and abiotic stresses predominantly affect metabolite biosynthesis, gene and protein expression, and genome variations. However, light doses of stress result in the production of positive attributes in crops, like tolerance to stress and biosynthesis of metabolites, called hormesis. Advancement in artificial intelligence (AI) has enabled the development of high-throughput gadgets such as high-resolution imagery sensors and robotic aerial vehicles, i.e., satellites and unmanned aerial vehicles (UAV), to overcome biotic and abiotic stresses. These High throughput (HTP) gadgets produce accurate but big amounts of data. Significant datasets such as transportable array for remotely sensed agriculture and phenotyping reference platform (TERRA-REF) have been developed to forecast abiotic stresses and early detection of biotic stresses. For accurately measuring the model plant stress, tools like Deep Learning (DL) and Machine Learning (ML) have enabled early detection of desirable traits in a large population of breeding material and mitigate plant stresses. In this review, advanced applications of ML and DL in plant biotic and abiotic stress management have been summarized.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

yuwangcn/C4_dynamic_model

A dynamic systems model of C4 photosynthesis was developed based on the previous NADP-ME metabolic model for maize (Wang et al., 2014 ab). The NADP-ME metabolic model is an ordinary differential equation model including all individual steps in C4 photosynthetic carbon metabolism. Here, the model is extended to include posttranslational regulation and temperature response of enzyme activities, dynamic stomata conductance, and leaf energy balance. This model is written in Matlab (R2019a) Steady-state and dynamic gas exchange data for maize (B73), sugarcane (CP88-1762) and sorghum (Tx430) were measured in a greenhouse in Urbana, IL from July 25, 2019 through August 8, 2019. Data include: CO2 response curves Light response curves Photosynthetic induction curves measured in the transition from darkness to high light (1800 μmol m-2 s-1), data logged every 1 min. Photosynthetic induction in the transition from darkness to high light (1800 μmol m-2 s-1) to determine the kinetics of rubisco activation in these C4 crops (τ_Rubisco), data logged every 10 s. Gas exchange under fluctuating light. After dark adaptation, the leaves undergo three light change steps, light intensity was set as 1800 µmol m-2 s-1, 200 µmol m-2 s-1 and 1800 µmol m-2 s-1 for each 1800 s step.

Wang, Yu↗
DOE OSTI2020

A phytophotonic approach to enhanced photosynthesis

Photosynthesis is the dominant biotic carbon sink on earth and hence presents an opportunity for enhanced sequestration of CO 2 . If the average net carbon fixation efficiency of terrestrial plants could be increased by 3.3%, all anthropogenic CO 2 accumulating in the atmosphere could instead be reduced and incorporated into terrestrial biomass. Plants make inefficient use of the overly abundant sunlight available to them, a result of having evolved to be competitive and survive highly dynamic environmental conditions rather than maximize photosynthetic productivity. We explore herein a phytophotonic approach to enhanced photosynthesis, whereby sunlight is redistributed by means of luminescent or persistent luminescent (PersL) materials. Phytophotonics has potential at varied scales, ranging from photobioreactors to greenhouses all the way to crops in the field, the latter having the potential to impact planetary CO 2 levels. The approach is three-fold: a spectral redistribution to relieve high-light-stress at the top surface of leaves and increasingly drive photosynthesis deeper in leaves and canopies; a minute-scale temporal redistribution to bridge periods of intermittent shade and reduce shock associated with variable light conditions; and a multiple-hour temporal redistribution to shift a fraction of high-intensity midday lighting to evening hours. Based on simulations of photoluminescent materials and light quality experiments with a model algal system, it is shown that while lengthening daylight hours will require significant improvements in PersL materials, the other two approaches show more immediate promise. We demonstrate a means of concentrating PersL light from SrAl 2 O 4 :Eu,Dy, approaching levels needed to effectively bridge periods of natural shade, and outline the scientific questions and technical hurdles remaining to realize the benefits of the proposed spectral shift.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Assessment of Potential Pennycress Availability and Suitable Sites for Sustainable Aviation Fuel Refineries in Ohio

Pennycress grain has a relatively high oil content (25–36%) and it is considered a desirable feedstock to produce sustainable aviation fuel (SAF). Pennycress crop can be integrated into the corn–soybean rotation as a winter cover crop in the midwestern U.S. to provide both ecosystem services and economic benefits for the farmers, while serving as a promising feedstock for SAF production. For pennycress-based SAF biorefineries to be established at the commercial scale, a sustainable design of the supply system is required to provide reliable information on feedstock availability and optimal facility locations. The objectives of this research were to assess the pennycress production potential in Ohio, and to identify the best locations to establish the SAF biorefineries. To estimate the pennycress production potential in Ohio, a geographic information system (GIS)-based model was developed using the spatially explicit six-year historical data on areas that were planted in the corn–soybean rotation for the period of 2013 through 2018, pennycress yield estimates from field-based experiments reported in the literature, and the soil productivity index for the region of study. Optimal SAF biorefinery locations were identified using a GIS-based location-allocation model. Annual land potentially available for pennycress production in Ohio was estimated to be ~0.6 million ha, which could produce ~1.1 million metric tons of pennycress grain as feedstock to produce ~210 million liters of SAF, depending on the pennycress yield level, oil content, and conversion efficiencies. In addition, the optimum locations for 12 biorefineries, each at an annual capacity of 18.9 million liters of SAF, were identified, and the average transportation distance was estimated to be 35 and 58 km for maximizing attendance and coverage conditions, respectively. The outcomes of this research would help minimize the risks associated with feedstock supply and cost variabilities for pennycress-based SAF production in the region.

Mousavi-Avval, Seyed Hashem↗
DOE OSTI2021

Development of an enzyme cocktail to bioconvert untapped starch in sweet sorghum processing by-products: Part II. Application and economic potential

Demand for bioethanol and other biochemicals produced from agricultural crops has increased. Sweet sorghum has been identified as a promising bioenergy crop as it can produce starch, sugar, and fibrous biomass. During processing, starch accumulates in the juice sediments and clarification mud. And, while currently not recovered, it can be made accessible for fermentation by enzymatic hydrolysis. The enzymatic hydrolysis of starch in sweet sorghum processing streams was investigated, followed by fermentation of the resulting glucose to ethanol. The juice sediment contained sufficient starch to increase fermentable sugars by 127%, allowing a final ethanol titer of 11.1 vol%. The economics for fermentation of only dissolved sugars (Scenario 1) versus dissolved sugars and hydrolyzed starch (Scenario 2) were compared using a technoeconomic model. Fixed capital cost was found to be similar for both scenarios. For a set harvest period, Scenario 2 could produce 20% more ethanol; however, if the distillation by-product was dried and marketed as animal feed, Scenario 1 was more cost effective. A plant producing 5.6–5.7 Mkg of fuel ethanol per year had a minimum selling price of $0.67/kg of ethanol with concurrent production of animal feed and zero cost sweet sorghum processing. Finally, even with these optimistic assumptions, the estimated production cost was higher than the current wholesale price of fuel ethanol.

09 BIOMASS FUELS↗
DOE OSTI2022

Automatic recognition system for document digitization in nuclear power plants

With the increasing number of data-driven models in nuclear applications, large volumes of numerical data are required to accurately model and predict the health status of a plant component. However, many historical operation logs that contain useful information are not fully utilized due to the lack of a systematic approach of digitization. To overcome this issue, this study proposes an automatic pipeline for extracting information from handwritten tabular documents collected from nuclear power plants. In our pipeline, we first denoise scanned documents with morphological operations, and then extract relevant parts from individual pages using both traditional computer vision and neural network methods. Handwriting recognition is applied to obtain text and numbers. As the most challenging step is how to crop only relevant information, the main focus of our paper is to detect tables and cells from scanned handwritten documents. Here we evaluate the efficiency and accuracy of our proposed method on handwritten operational reports obtained from a real-world case study. The results demonstrate the high accuracy and practicality of our proposed method.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Step Catalysis to Synthesize Fossil-Free Ammonia at Atmospheric Pressure (Final Technical Report)

Affordable fossil-free ammonia synthesis will enable high-yield sustainable crop production for a growing world population while preserving the planet and making the best use of water and land. Simple technology amenable to intermittent operation using renewable energy will be made available through step catalysis activating dinitrogen at atmospheric pressure by nitride formation. Project objectives: (1) At the single particle level, quantify and analyze N2 activation by doped or alloyed manganese macroscopic- and nano particles at atmospheric pressure, (2) Quantify and analyze ammonia synthesis from doped or alloyed metal nitride particles when contacting them with hydrogen at atmospheric pressure, and (3) Integrate experimental data and atomic-level computational models to predict the behavior of metal alloys in nitrogen activation and subsequent ammonia synthesis.

10 SYNTHETIC FUELS↗
DOE OSTI2024

Biomolecular budget of persistent, microbial-derived soil organic carbon: The importance of underexplored pools

The details of how soil microorganisms contribute to stable soil organic carbon pools are a pressing knowledge gap with direct implications for soil health and climate mitigation. It is now recognized that microbial necromass contributes substantially to the formation of stable soil carbon. However, the quantification of necromass in soils has largely been limited to model molecules such as aminosugar biomarkers. The abundance and chemical composition of other persistent microbial residues remain unresolved, particularly concerning how these pools may vary with microbial community structure, soil texture, and management practices. We use yearlong soil incubation experiments with an isotopic tracer to quantify the composition of persistent residues derived from microbial communities inhabiting sand or silt dominated soil with annual (corn) or perennial (switchgrass) monocultures. Persistent microbial residues were recovered in diverse soil biomolecular pools including metabolites, proteins, lipids, and mineral-associated organic matter (MAOM). The relative abundances of microbial contributions to necromass pools were consistent across cropping systems and soil textures. The greatest residue accumulation was not recovered in MAOM but in the light density fraction of soil debris that persisted after extraction by chemical fractionation using organic solvents. Necromass abundance was positively correlated with microbial biomass abundance and revealed a possible role of cell wall morphology in enhancing microbial carbon persistence; while gram-negative bacteria accounted for the greatest contribution to microbial-derived carbon by mass at one year, residues from gram-positive Actinobacteria and Firmicutes showed greater durability. Together these results offer a quantitative assessment of the relative importance of diverse molecular classes for generating durable soil carbon.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Life Cycle Greenhouse Gas Emissions of Coal-Biomass Co-Firing Power Plants with Carbon Capture and Storage

The United States has set a target to achieve the net-zero economy by 2050. Bioenergy with Carbon Capture and Sequestration (BECCS) is one of the promising negative-emission routes in the mitigation portfolio to help meet this goal. Coal-biomass co-firing with carbon capture and storage (CCS) is a key BECCS technology to realize the carbon mitigation at fossil-fuel power plants. The mitigation potential of co-firing option is affected by numerous critical factors, such as biomass properties, co-firing level, and carbon capture rate. The objectives of the study are to characterize and estimate the life cycle greenhouse gas (GHG) emissions and performance of coal-biomass co-firing power plants with CCS, determine the breakeven co-firing level at power plants necessary to achieve net-zero life cycle emissions, and quantify the variabilities and uncertainties in life cycle emissions. The scope of the life cycle assessment includes the fuel supply, combustion-based power generation, and CO2 transport and storage. A fuel-based life cycle module is developed and embedded in the Integrated Environmental Control Model (IECM), a fossil-fuel power plant modeling tool. This study then applies the enhanced IECM to conduct the process-based life cycle assessment for an array of biomass co-firing scenarios. Deterministic analysis indicates that reaching net-zero life cycle emissions in a biomass co-firing plant without CCS deployment is challenging. Combining biomass co-firing and CCS deployment can significantly lower the overall life cycle emissions of power plants. Net-zero life cycle emissions can be achieved with a 20 wt.% co-firing level and 90% CCS when the Powder River Basin coal is co-fired with energy crops or forestry residues. However, the breakeven co-firing level for net-zero emissions depend on the selected fuel properties. Fuel supply and plant operation are the critical stages influencing the life cycle emissions of power plants with 90% CCS. Deployment of deep CCS beyond 90% CO2 capture can remarkably reduce operational emissions and the breakeven co-firing level. With 99% CCS, the breakeven co-firing rate can be reduced to 12% on average. These findings highlight the trade-offs between technical performance and environmental impact of biomass co-firing at coal-fired power plants and emphasize the role of deep CCS in achieving a net-zero emissions future.

Wu, Wanying↗
DOE OSTI2020

High precision control and deep learning-based corn stand counting algorithms for agricultural robot

This paper presents high precision control and deep learning-based corn stand counting algorithms for a low-cost, ultra-compact 3D printed and autonomous field robot for agricultural operations. Currently, plant traits, such as emergence rate, biomass, vigor, and stand counting, are measured manually. This is highly labor-intensive and prone to errors. The robot, termed TerraSentia, is designed to automate the measurement of plant traits for efficient phenotyping as an alternative to manual measurements. In this paper, we formulate a Nonlinear Moving Horizon Estimator that identifies key terrain parameters using onboard robot sensors and a learning-based Nonlinear Model Predictive Control that ensures high precision path tracking in the presence of unknown wheel-terrain interaction. Moreover, we develop a machine vision algorithm designed to enable an ultra-compact ground robot to count corn stands by driving through the fields autonomously. The algorithm leverages a deep network to detect corn plants in images, and a visual tracking model to re-identify detected objects at different time steps. We collected data from 53 corn plots in various fields for corn plants around 14 days after emergence (stage V3 - V4). The robot predictions have agreed well with the ground truth with C robot =1.02×C human -0.86 and a correlation coefficient R=0.96. The mean relative error given by the algorithm is -3.78%, and the standard deviation is 6.76%. These results indicate a first and significant step towards autonomous robot-based real-time phenotyping using low-cost, ultra-compact ground robots for corn and potentially other crops.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Daily evapotranspiration changes during heatwaves at 32 NEON sites, 2019-2021

This dataset provides partitioned evapotranspiration (ET, the combined loss of water from soil and plant surfaces) anomalies during heatwave events—soil evaporation (E) and transpiration (T)—for 268 heatwave events across 32 National Ecological Observatory Network (NEON) flux sites in the contiguous United States from 2019–2021. Using an ensemble of four high-frequency turbulence methods (Flux-variance Similarity, Conditional Eddy Covariance [CEC], CEC with Water-Use Efficiency, and Conditional Eddy Accumulation; see Zahn and Bou-Zeid 2024), half-hourly transpiration-to-evapotranspiration (T/ET) ratios were derived from 20 hertz (Hz, cycles per second) eddy covariance measurements of carbon dioxide (CO₂) and water vapor (H₂O) concentrations. The dataset spans six vegetation types including evergreen and deciduous forests, grasslands, cultivated crops, shrublands, and emergent herbaceous wetlands. Data Package Contents: The dataset includes a single CSV (comma-separated values) file containing daily anomalies (deviations from baseline conditions) for transpiration (Delta_T), evaporation (Delta_E), total evapotranspiration (Delta_ET), and T/ET ratio (Delta_T_ET) during each day of identified heatwave events. The file also includes site codes, dates, heatwave event identifiers, and day-of-heatwave indicators. The CSV file can be opened with spreadsheet software (Microsoft Excel, Google Sheets) or programming environments (Python, R, MATLAB). This resource enables researchers to investigate ecosystem-specific responses to thermal extremes, validate land surface model partitioning of ET fluxes, and examine feedbacks between water cycling and surface energy balance during heatwaves. The dataset is particularly valuable for studies linking vegetation hydraulic strategies to climate resilience, as it captures the divergent responses of shallow-rooted versus deep-rooted ecosystems. Potential applications include improving drought early warning systems, informing irrigation management strategies, and advancing our mechanistic understanding of land-atmosphere interactions under extreme heat conditions.

Day of Heatwave↗
DOE OSTI2022

Evaluation of artificial neural network performance for classification of potato plants infected with potato virus Y using spectral data on multiple varieties and genotypes

Potato virus Y (Potyviridae, PVY) is a plant virus that poses a significant threat to potato producers on a global basis. The pathogen has disrupted seed potato supplies and negatively impacted yield and quality of commercial potato crops. The potato industry currently manages PVY infection levels via insecticide applications, regional seed certification programs that rely on field scouting to visually assess individual plants for infection status, and destructive and costly tissue sampling coupled with laboratory assays. Despite these efforts, PVY continues to confound potato industry stakeholders resulting in economic harm. Remote sensing and machine learning provide for the development of new tools to more accurately detect and spatially quantify PVY-infected plants versus the current state of the art. However, there is a need to understand how the occurrence of many different potato varieties impact the dynamics of developing models to detect potato plants impacted with PVY and their potential effectiveness. This study evaluates classification modelling outcomes using spectral datasets collected in different temporal and spatial environments (greenhouse and a production field) on multiple potato varieties consisting of labelled instances of plants infected with PVY and those not infected with the virus. A modelling framework was developed to support iterative modelling runs using artificial neural network (ANN) architectures configured as binary classifiers to develop sample populations to support statistical analysis on model performance using specific spectral subsets. When using spectral data to detect PVY-infected plants, ANN models achieved the highest mean accuracy of 0.894 on a single variety. Conversely, the same ANN model architecture only achieved a mean accuracy of 0.575 on a spectral data set representing 29 potato breeding lines. Additionally, statistical analysis indicates spectral regions including the red edge, near infrared and shortwave infrared contain more important spectral features for the ANN classifier introduced in this research.

60 APPLIED LIFE SCIENCES↗