ARS Researchers: Want your research featured on the SCINet website and newsletter?
Research highlights from researchers who use SCINet resources are added quarterly. Contact ARS-SCINet-Office@usda.gov for more information.
User Stories
-
Humanely deterring birds around aquaculture and development of AI-driven, non-lethal deterrence tactics
Predatory birds such as Great Blue Herons, Canada Geese, and Egrets can cause significant losses at fish ponds. Traditional deterrents like netting and noise cannons are often intrusive or ineffective over time. The project leverages SCINet’s high-performance computing resources to train and optimize YOLO-based deep-learning models using large datasets of bird images. These trained models make it possible to implement detection and identification of birds in real time at aquaculture ponds in the field.
-
Advancing Irrigation Mapping Through AI and Remote Sensing
Accurate mapping of irrigation methods is essential for tackling water scarcity across large regions, boosting agricultural productivity, and informing conservation practices. Researchers at the USDA-ARS Northwest Irrigation and Soils Research Laboratory at Kimberly, Idaho are spearheading the development of an irrigation methods mapping tool by leveraging Artificial Intelligence (AI) and publicly available satellite imagery.
-
Comparative genomics reveals a light-activated phytotoxin that contributes to red leaf blotch disease of soybean
Coniothyrium glycines causes red leaf blotch, a major disease of soybean in Africa (Figure 1). It is one of two fungal pathogens listed on the USDA APHIS Plant Protection and Quarantine Select Agents and Toxins list owing to its likely destructive potential if it spreads to major soybean growing regions.
-
High-Performance Computing Facilitates Improved Understanding of Phenotypic Plasticity in Maize
In maize and other crops, important traits are often complex, affected by genetics, the environment, and their interaction. In addition, different crop varieties exhibit varying degrees of phenotypic plasticity, in which a given genotype displays different phenotype values in different environments.
-
SCINet as a Resource for Safeguarding and Advancing ARS's Biological Collections
Across the USDA’s Agricultural Research Service (ARS) there are nealy 100 biological collections containing millions of preserved and viable specimens including animal tissues, seeds, fungal cultures, plant accessions, pinned insects, and viral isolates. These specimens and the data about them document and support ARS research efforts and are an integral part of delivering on the Agency’s mission.
-
Monte Carlo simulations on Atlas for soil content determinations
The Monte Carlo Method, or multiple probability simulation, is a mathematical technique used to estimate possible outcomes of uncertain events. The Monte Carlo Method was applied for nuclear problems by John von Neumann and Stanislaw Ulam during work on the Manhattan Project.
-
SCINet Resources for Photogrammetry
Scientists at the NWRC use UAS to research long-term vegetation dynamics in sagebrush-dominated rangelands. Multispectral, hyperspectral, and natural color imagery are collected to study the effects of fire, grazing, and invasive weed encroachment.
-
CameraTrapDetectoR: Detecting, Classifying and Counting Animals in Camera Trap Images
The use of camera traps is a popular and cost-effective way to monitor animal populations, evaluate animal behavior, and study ecological processes influencing populations. However, a camera trap dataset for a single site or research question can result in millions of images that require classification to be useful for analysis.
-
Cattle Genome, Pangenome, Annotation, and FarmGTEx
FarmGTEx Consortium aims to create a comprehensive public resource for studying tissue-specific gene expression and regulation in major livestock species, including cattle, pigs, sheep, goats, and chickens.
-
A Machine Learning Tool to Collapse Diet or Microbiome Data Using Taxonomic Structure
Researchers at the USDA-ARS Western Human Nutrition Research Center (WHNRC) are leveraging machine learning to uncover the molecular underpinnings of diet’s association with health.
-
Modeling the Spread of a Livestock Disease With Semi-Supervised Spatiotemporal Deep Neural Networks
Dr. Michael Alcorn has been researching the potential for using spatiotemporal deep neural networks (STNNs) to model vesicular stomatitis risk through both space and time.
-
Use of UAS Imagery to Detect Prairie Dog Burrows, Map Burrow Density, and Estimate Colony Acreage
Dr. Kearney is using unmanned aerial system (UAS) imagery to detect individual prairie dog burrows, map burrow density and, ultimately, estimate colony acreage within managed rangelands.
-
Exploring Methods for Developing 3D Maps of Soil Organic Carbon
Scientists at the Cropping Systems and Water Quality Research Unit in Columbia, Missouri have extensive experience estimating soil biological, physical, and chemical properties using proximal soil sensors.
-
Using SCINet HPC Resources to Develop Efficient UAS Imagery Analysis Workflows for Rangeland Management
Dr. Clark is developing and evaluating UAS imagery collection and analysis workflows with an eye towards augmenting or replacing field biomass measurements on spatially-extensive rangelands.
-
Guidemaker: software for CRISPR based gene function discovery
CRISPR-Cas is a powerful tool for gene editing. CRISPR can also be used to discover gene function by disrupting every gene in the genome and screening millions of cells in parallel.
-
SCINet accelerates development of a big-data driven and inter-disciplinary technology platform for soybean post-genomic research
Soybean (Glycine max (L.) Merr.) is a versatile, nutrients-laden, economically invaluable crop with capacity to restore soil fertility through atmospheric nitrogen fixation. It holds great significance in ensuring adequate global nutritional food security and environmentally friendly sustainable agriculture.
-
Putting flowers on the map: Quantifying spatio-temporal patterns in floral resources for pollinators
Flowers provide critical nectar and pollen resources to support foraging, learning and memory, and reproduction of pollinating insects, but there are very few large-scale maps of floral resources for pollinators.
-
Faster, Better Metagenome Analysis: One genome, one contig for metagenome samples sequenced with PacBio HiFi reads
All plant and animal species must interact with microbes to survive and thrive.
-
SCINet resources for creating livestock reference genomes
As a scientist in USDA-ARS’s Animal Genomics and Improvement Lab, one of our missions is to generate scientific resources used to improve our ability to raise cattle, sheep and goats to their fullest potential…
-
Selecting Robust Climate Change Projections for Agricultural Systems
Scientists of many disciplines, including agricultural fields, often use climate change projections in their research
-
Generating whole-genome data from a single insect: PacBio HiFi genome assembly and HiC scaffolding pipelines for reference quality genomes using SCINet
The damage that insect pests cost to human health and agriculture is enormous. For instance, invasive insects cost …
-
Spatial Disease Modelling on the Ceres HPC
A fundamental need to meet USDA ARS’s Grand Challenge initiative is to improve agricultural production while reducing the impact of the emerging pests, pathogens, and invasive species that threaten US livestock.
-
The SCINet-LTAR phenology working group: Improving the accuracy of agriculturally-relevant models to meet growing and changing food demand
Meeting growing and changing demands for food and agricultural products requires models and forecasts that accurately characterize hydrology-soil-climate interactions…
-
The ARS Arthropod Genomics Research (AGR) working group: Agency-wide advancement in research capabilities to address stakeholder concerns
Arthropod pests cause damage to crop, livestock and forestry products, as well as ornamental plants and urban structures, that inflicts an economic cost of several billion dollars annually…
-
Antigenic and genetic evolution of contemporary swine H1 influenza viruses in the US
Influenza A viruses (IAV) that circulate in North American pigs maintain a high degree of diversity determined by the hemagglutinin (HA) gene, especially those of the H1 subtype.