We present a stepwise color correction (CC) pipeline for controlled imaging environments. The workflow integrates flat-field correction (FFC), gamma correction, and white-balance correction, followed by a color-mapping (CM) stage using machine-learning regression-linear, partial least squares, and neural networks (NNs)-to deliver reliable CC in digital images. The pipeline reduces perceptual color differences in the corrected images. An NN with a second-degree polynomial expansion consistently outperformed other CM methods, yielding the lowest color errors and robust performance across varying imaging conditions. Tests showed that illumination quality and placement are critical: although the common 45 degrees geometry produces favorable uncorrected images, top-mounted area lighting combined with FFC yielded the best corrected color. Imaging-environment materials also mattered; object background color and sidewalls affected fidelity, with diffusely reflective white performing best. Applied to various colored fruit samples, the proposed pipeline produced more consistent fruit colors across illuminants. An open-source Python package and an interactive user interface implementing this pipeline are available, enabling reproducible analyses and straightforward adaptation to other controlled imaging tasks. Overall, the pipeline improved color reproduction and measurement in digital images and helped bridge the gap between sophisticated CC methods and practical, routine applications.

The authors would like to thank Dr. Katherine East and Brandon Peterson for their efforts collecting these soils. This work was supported in part by USDA NIFA Agriculture and Food Research Initiative grant #2020-67021-32799/project accession #1024178 (Margenot) and Illinois Nutrient Research & Education Council #2021-4-360731-469 (Margenot). This study was funded by USDA-ARS projects 2072-30500-001-000D and 2072-21000-057-000-D (Rippner). A portion of this research was performed on project awards (https://www.osti.gov/awar d-doi-service/biblio/10.46936/intm.proj.2022.60475/6000854; https://www.osti.gov/award-doi-service/biblio/10.46936/ficus.proj. 2024.61325/60012668) from the Environmental Molecular Sciences Laboratory, a DOE Office of Science User Facility sponsored by the Biological and Environmental Research program under Contract No. DE-AC05-76RL01830. A portion of the results in this report are derived from work, funded by the U.S. Department of Energy, Office of Biological and Environmental Research at the Advanced Photon Source, a U.S. DOE Office of Science User Facility, supported by the U.S. DOE, Office of

Fruit size, shape, color, and percent fruit rot are important quality traits for breeding cranberry (Vaccinium macrocarpon Ait.). Image analysis can be used to measure these traits, but affordable hardware for standardized image capture and integrated user-friendly software pipelines are lacking. Additionally, no image-based method exists to estimate percent fruit rot, an otherwise tediously and subjectively measured trait. We created the BerryBox, a simple and inexpensive lightbox, camera mount, and accompanying software pipeline to standardize the capture and analysis of postharvest fruit images. Trained deep neural network models were highly accurate for segmenting sound fruit (F1 score: 99.4%) and detecting rotten fruit (F1 score: 98.5%). We applied the BerryBox to images of cranberries harvested across 3 years from a 156-clone breeding population. Narrow-sense heritability estimates of image-based fruit color, shape, size, and percent fruit rot ranged from 0.37 to 0.95. Random subsampling showed that 25-30 berries per genotype were sufficient to describe the variation in the full dataset. We demonstrated the utility of BerryBox traits in a small-scale genetic linkage mapping analysis, detecting significant marker-trait associations that coincided with those of traditionally measured traits. The BerryBox software was able to accurately segment fruit from images of blueberries without model retraining, showing its applicability to other similarly shaped fruits. The software pipeline and BerryBox materials and assembly instructions are publicly available for others to adopt for low-cost image-based phenotyping.

Abstract Healthy soils are fundamental to sustainable agriculture, but research efforts have largely centered on annual cropping systems, with far less attention given to the unique dynamics of perennial systems such as vineyards. Addressing this gap requires long‐term research efforts designed to monitor how soil health evolves under different management practices. This study was conducted to (1) describe the establishment and experimental design of a long‐term soil health research wine grape ( Vitis vinifera) vineyard in eastern Washington and (2) characterize baseline physical, chemical, and biological soil health indicator values across the site. Soils were sampled pre‐ and post‐planting across five management treatments and four depth intervals (0–15 cm, 15–30 cm, 30–60 cm, and 60–90 cm) of a vineyard with two wine grape cultivars on a common rootstock. Post‐plant samples were also collected in the under‐vine and alleyway areas to capture initial spatial variability associated with floor management zones. Samples were analyzed for a suite of chemical, biological, and physical soil health indicators. Pre‐ and post‐planting soil characterization confirmed that the experimental design adequately accounted for spatial variability, providing a reliable baseline for evaluating subsequent management and temporal effects on soil health. Most soil health indicator values were surface‐weighted, with organic carbon and microbial activity concentrated in the top 30 cm, while inorganic carbon was the dominant carbon pool at depth. These results establish a robust foundation for detecting long‐term management effects, highlight depth‐driven soil processes, and inform indicator selection for monitoring vineyard soil health over time.

Soil organic matter (SOM) has attracted a great deal of interest; particularly for its potential to mitigate human derived CO2 emissions. Studies have demonstrated that SOM plays a critical role in carbon storage and COQ sequestration. However, the sorption properties of SOM, which influence its transport in pore water and stabilization within the soil, remain poorly understood. This study develops a workflow to: (1) examine compound-specific advective and diffusive transport and desorption behaviors, (2) quantify desorption rates through stop-flow and continuous-flow column experiments, and (3) evaluate the impact of soil microporosity on SOM mobility using high-resolution imaging and extractions. Intact core column experiments were conducted on Uncultivated (Natural) and Cultivated soil samples, both were arid soils, collected in Washington State. X-ray computed tomography was employed to measure porosity and pore connectivity, while Fourier-transform ion cyclotron resonance mass spectrometry was used to analyze SOM composition. The findings revealed that cultivation increased total carbon and nitrogen levels due to irrigation and fertilization, enhancing carbon capture potential in arid soils. In contrast, the Natural soil, characterized by higher porosity and connectivity, contained more oxidized carbon. Pore network analysis indicated that soil compaction in the Cultivated soil may lead to longer diffusion pathways, significantly influencing SOM transport and stability.

Walnut rootstocks are commonly used in California orchards to provide resistance to soil-borne pests and diseases. However, little information exists about the impact of commercial rootstock on the common scion's physiological response under drought. This is becoming increasingly important since walnuts are commonly cultivated in semi-arid regions where frequent and severe droughts require efficient water use. We previously reported that own-rooted walnut rootstocks (RX1, VX211 and Vlach) differ in their physiological performance under drought. Here, we evaluated whether similar water relations and performance are conferred to a common English walnut scion (Juglans regia cv. Cisco). To do so, we used a mini-lysimeter platform to continuously track soil moisture and transpirational water loss from trees. Along with the canopy's estimated leaf area, changes in canopy shape and texture were evaluated using deep learning as an independent method to analyze canopy response to water stress. In support of our recent findings, the scion grafted onto rootstock RX1 exhibited subtle improvements in physiological performance associated with higher transpiration and canopy conductance under well-watered condition compared to Vlach and VX211 rootstocks. Canopy conductance, texture, and shape were not significantly affected by rootstock under water stress. However, Cisco grafted onto RX1 exhibited higher leaf turgor and water use efficiency, and lower osmotic potentials under water stress. Our results suggest some subtle differences in water relations between the rootstock genotypes, and propose an efficient deep-learning method to screen canopies for water stress-induced response through image processing.

Rangelands have the potential to be provisioners of ecosystem services, including livestock products, carbon storage and greenhouse gas regulation, water and nutrient cycling, wildlife habitat, and biodiversity. Due to their vast extent and landscape heterogeneity, the degree to which different ecological components of rangelands contribute to ecosystem services can be varied. Soils are the foundation of rangeland health and associated ecosystem services. While many studies have examined the effect of grazing intensity on rangeland ecosystem services, few studies have looked at the broader rangeland landscape and how managing varying vegetation types can influence soil-based ecosystem services. In this study, a suite of physical, chemical, and biological soil health indicators were measured in various vegetation types found within a working cattle ranch, including coastal live oak woodlands, coastal scrublands, annual grassland, and restored native perennial grassland. Based on the measured soil health indicators, results from this study show scrubland significantly diverges from other vegetation types, having higher water infiltration and plant available water, carbon stocks, and a more diverse microbial community that drives more dynamic cycling of carbon and nitrogen. Strategically maintaining scrubland on unproductive, highly erosive slopes downgradient of highly productive grassland areas could maintain forage production while protecting water quality and increasing carbon storage. These results highlight the relevance of holistically evaluating rangeland operations to assess soil function and ecosystem services and the potential risks and co-benefits of varying vegetation types. Ultimately, process-based linkages described here may provide a working example of how to manage ranches as functional mosaics of strategically maintained vegetation types.

Abstract Tuber size, shape, colorimetric characteristics, and defect susceptibility are all factors that influence the acceptance of new potato cultivars. Despite the importance of these characteristics, our understanding of their inheritance is substantially limited by our inability to precisely measure these features quantitatively on the scale needed to evaluate breeding populations. To alleviate this bottleneck, we developed a low‐cost, semiautomated workflow to capture data and measure each of these characteristics using machine vision. This workflow was applied to assess the phenotypic variation present within 189 F1 progeny of the A08241 breeding population. Machine vision was applied to estimate linear and volumetric tuber size, assess tuber shape characteristics using aspect ratio and biomass profiles, and quantify tuber skin and flesh color; additionally, a deep learning mode was developed to classify the presence of hollow‐heart defect. Our results provide an example of quantitative measurements acquired using machine vision methods that are reliable, heritable, and capable of being used to understand and select multiple traits simultaneously in structured potato breeding populations.

The Columbia root-knot nematode ( Meloidogyne chitwoodi ) is a destructive soil borne pest that can cause serious economic damage to potato tubers within infected, unfumigated fields. There are very few known sources of genetic resistance to root-knot nematodes and no released potato cultivars exhibit this trait. Literature indicates that nematode resistance introgressed from Solanum bulbocastanum is dominantly inherited across many genetic backgrounds. We generated a 32 family half-diallel progeny test population utilizing 3 root-knot nematode resistant clones (female) and 11 clones (male) with russet skin type (1,600 clones, between 25 – 60 clones per family). In 2023, 1,200 progeny were evaluated relative to 6 control varieties planted at high replication at the Washington State University Experiment Station in Othello, WA. A scale, RGB-D imaging conveyor, and index scoring system was used to record: total yield, the number of tubers per plant, tuber size distribution, aspect ratio, skin color, starch content, and defect severity from all samples within this population. The distribution of phenotypic values observed from the progeny suggest that choice of parent is a highly significant factor that influences almost all traits evaluated. The phenotyping strategy utilized by our team is inexpensive, expandable, and flexible enough to be adopted by many different types of vegetable breeding programs. Data from this experiment is being used to develop potato tuber defect classification models and assess the utility of adopting genomic selection within our potato breeding program.

Environmental evaluations of metal nanoparticles (NP) rely on metal ion controls to distinguish between effects of the metal NP and its dissolution products. However, the coordinating or counter anion used in experimental controls may potentially influence biotic indicators used in ecotoxicology and soil health monitoring, compromising the ability to detect real nanoparticle effects and confounding interpretation of metal NP impacts. Using the example of copper oxide (CuO) NP, we demonstrate for the first time that depending on the anion used in the metal ion control (CuCl2 versus CuSO4), differing and even opposite conclusions may be drawn for CuO NP effects on a key microbiological indicator (enzyme activities) in environmental samples (soils). Moreover, this effect was specific to environmental conditions (soil management system) and indicator type (enzyme class), raising important methodological and interpretive implications for assessments of CuO NP impacts on soils. Our findings imply that assessments of soil health impacts of metal NP should consider multiple coordinating anion controls for a given metal, especially when the specific counterion is known to impact the biotic indicator (e.g., nutrient ions).

Abstract Hop cone morphology can influence picking and drying ability, and color can impact consumer preference and may be indicative of quality. However, these characteristics are not generally evaluated in hop breeding programs due to the tedious nature of trait quantification and the extensive variation among cones within a genotype. We developed the HopBox, which is a simply constructed light box with a camera mount, and a publicly available image processing pipeline that identifies hop cones within color‐corrected images, reads a QR code within the image, and outputs data on hop cone length, width, area, perimeter, openness, weight, color, and density. The trained model was applied to images of 500 cones each from 15 replicated advanced hop genotypes from the USDA‐ARS breeding program in Prosser, Washington. Analysis of variance revealed significant (p < 0.001) differences between genotypes for all traits measured, enabling breeders to discriminate between genotypes for selection purposes. Broad sense heritability for all traits ranged from 0.23 to 0.59. A random sampling of hop cones from the complete dataset revealed that imaging only 5–10 cones adequately captured genotypic variation and provided acceptable rank correlations (rs > 0.75); however, increasing the sample size to 30 provided optimal precision. Instructions for constructing a HopBox and the code for the analysis pipeline are publicly available online and have wide applicability for hop breeding and research.

Background and goals During wine fermentation, grape berry components, including seeds, undergo extensive physical and chemical changes that result in the release of flavonoids, such as tannins, from seeds into wine. Understanding changes in seed morphology during fermentation is crucial for aiding the development of accurate prediction models for flavonoid extraction during winemaking, which enhances fermentation management and ensures consistency in wines from year to year. Methods and key findings High-resolution x-ray microcomputed to-mography (x-ray mu CT) was used to investigate the effect of red wine fermentation on changes in grape seed morphology. Using a PyTorch-based implementation of a fully con-volutional network with a Resnet-101 back-bone for semantic segmentation of x-ray mu CT images, we quantified extensive alteration to grape seed structure during fermentation. Image analyses revealed the development of a pore network breaking apart the seed endosperm by the end of fermentation, leading to an increase in surface area. Conclusions and significance Fermentation significantly altered grape seed morphology. Such alterations could enable transport of seed flavonoids from inside the endosperm and integument to outside the seed. Further research on the physical processes occurring in seeds during wine fermentation is necessary to build better physiochemical models.

Abstract Northern root‐knot nematode (Meloidogyne hapla) and ring nematode (Mesocriconema xenoplax) are the most prevalent plant‐parasitic nematodes of wine grapes in the Pacific Northwest, but M. hapla is most important in eastern Washington and M. xenoplax in western Oregon. These regions differ edaphically where Washington soils are minimally weathered and alkaline while Oregon soils are highly weathered and acidic. To examine the effect of soil texture and pH on nematode reproduction, an alkaline, sandy loam soil (pH 7.9) from Washington and an acidic loam soil from Oregon (pH 5.4) were modified to the other pH extreme, and to a middle pH of 6.9. Tomatoes were planted into each soil/pH combination, and either 500 M. hapla second‐stage juveniles or M. xenoplax individuals were added to each pot. After 7 weeks, plants were harvested, three roots collected for analysis, remaining roots and leaves dried and weighed, and nematode population densities determined as eggs on roots (M. hapla) and nematodes in soil (M. xenoplax). Soil texture (sandy loam or loam) had no effect on either nematode, but M. hapla reproduction was greater in the lowest pH soil while M. xenoplax was unaffected by soil pH. Mesocriconema xenoplax parasitism reduced root length and root tip number, whereas M. hapla increased root mass in the highest pH Washington soil. Under these experimental conditions, it appears vineyard soil texture in the Pacific Northwest is not a determining factor in population growth of these nematodes, but M. hapla performed better at low pH.

Similar to other cropping systems, few walnut cultivars are used as scion in commercial production. Germplasm collections can be used to diversify cultivar options and hold potential for improving crop productivity, disease resistance and stress tolerance. In this study, we explored the anatomical and biochemical bases of photosynthetic capacity and response to water stress in 11 Juglans regia accessions in the U.S. department of agriculture, agricultural research service (USDA-ARS) National Clonal Germplasm. Net assimilation rate (An ) differed significantly among accessions and was greater in lower latitudes coincident with higher stomatal and mesophyll conductances, leaf thickness, mesophyll porosity, gas-phase diffusion, leaf nitrogen and lower leaf mass and stomatal density. High CO2 -saturated assimilation rates led to increases in An under diffusional and biochemical limitations. Greater An was found in lower-latitude accessions native to climates with more frost-free days, greater precipitation seasonality and lower temperature seasonality. As expected, water stress consistently impaired photosynthesis with the highest % reductions in lower-latitude accessions (A3, A5 and A9), which had the highest An under well-watered conditions. However, An for A3 and A5 remained among the highest under dehydration. J. regia accessions, which have leaf structural traits and biochemistry that enhance photosynthesis, could be used as commercial scions or breeding parents to enhance productivity.

ORCiD: [ORCiD of presenting author] Jaebum Park [0000-0001-6459-909X] AND/OR Max Feldman [0000-0002-5415-4326] Tuber size and shape, colorimetric characteristics of tuber skin and flesh, and tuber defect susceptibility are all factors that influence the adoption of potato cultivars. Despite the importance of these characteristics, our understanding of their inheritance is limited by our inability to precisely measure these features on the scale needed to evaluate breeding populations. To alleviate this bottleneck, we have developed a low-cost, semi-automated workflow to capture data and quantify each of these characteristics using machine vision. This workflow was applied to assess the phenotypic variation present within 189 F1 progeny of the A08241 breeding population and map the genetic basis of tuber characteristics. Several medium-to-large effect, quantitative trait loci (QTL) were found to be associated with different measurements of tuber shape. These results indicate that quantitative measurements acquired using machine vision methods are reliable, heritable, and can be used to map and select upon multiple traits simultaneously in structured potato breeding populations.

X-ray micro-computed tomography (X-ray μCT) has enabled the characterization of the properties and processes that take place in plants and soils at the micron scale. Despite the widespread use of this advanced technique, major limitations in both hardware and software limit the speed and accuracy of image processing and data analysis. Recent advances in machine learning, specifically the application of convolutional neural networks to image analysis, have enabled rapid and accurate segmentation of image data. Yet, challenges remain in applying convolutional neural networks to the analysis of environmentally and agriculturally relevant images. Specifically, there is a disconnect between the computer scientists and engineers, who build these AI/ML tools, and the potential end users in agricultural research, who may be unsure of how to apply these tools in their work. Additionally, the computing resources required for training and applying deep learning models are unique, more common to computer gaming systems or graphics design work, than to traditional computational systems. To navigate these challenges, we developed a modular workflow for applying convolutional neural networks to X-ray μCT images, using low-cost resources in Google’s Colaboratory web application. Here we present the results of the workflow, illustrating how parameters can be optimized to achieve best results using example scans from walnut leaves, almond flower buds, and a soil aggregate. We expect that this framework will accelerate the adoption and use of emerging deep learning techniques within the plant and soil sciences.

Microbial response to copper oxide nanoparticles in soils is controlled by land use rather than copper fate.

Biochar is purported to provide agricultural benefits when added to the soil, through changes in saturated hydraulic conductivity (Ksat) and increased nutrient retention through chemical or physical means. Despite increased interest and investigation, there remains uncertainty regarding the ability of biochar to deliver these agronomic benefits due to differences in biochar feedstock, production method, production temperature, and soil texture. In this project, a suite of experiments was carried out using biochars of diverse feedstocks and production temperatures, in order to determine the biochar parameters which may optimize agricultural benefits. Sorption experiments were performed with seven distinct biochars to determine sorption efficiencies for ammonium and nitrate. Only one biochar effectively retained nitrate, while all biochars bound ammonium. The three biochars with the highest binding capacities (produced from almond shell at 500 and 800 ∘C (AS500 and AS800) and softwood at 500 ∘C (SW500)) were chosen for column experiments. Biochars were amended to a sandy loam and a silt loam at 0 % and 2 % (w/w), and Ksat was measured. Biochars reduced Ksat in both soils by 64 %–80 %, with the exception of AS800, which increased Ksat by 98 % in the silt loam. Breakthrough curves for nitrate and ammonium, as well as leachate nutrient concentration, were also measured in the sandy loam columns. All biochars significantly decreased the quantity of ammonium in the leachate, by 22 % to 78 %, and slowed its movement through the soil profile. Ammonium retention was linked to high cation exchange capacity and a high oxygen-to-carbon ratio, indicating that the primary control of ammonium retention in biochar-amended soils is the chemical affinity between biochar surfaces and ammonium. Biochars had little to no effect on the timing of nitrate release, and only SW500 decreased total quantity, by 27 % to 36 %. The ability of biochar to retain nitrate may be linked to high micropore specific surface area, suggesting a physical entrapment rather than a chemical binding. Together, this work sheds new light on the combined chemical and physical means by which biochar may alter soils to impact nutrient leaching and hydraulic conductivity for agricultural production.