Merge pull request #839 from MoeRichert-USDA/comp

update details

_data/tables/funded_FY22.csv

@@ -2,7 +2,7 @@ Title,Mentor,Co-mentor(s)
 Developing tools for the real-time monitoring and query of all the world's publicly available sequence data.,Adam Rivers,
 Determining the structure and function of proteins of foodborne and plant pathogens using Alphafold2 and top-down proteomic analysis,Clifton K. Fagerquist,
 AI-driven phenotype extraction from UAS imagery for crop genetics and breeding,Jacob Washburn,"Alisa Coffin, Max Feldman"
-Machine learning approaches to gain structural and functional insights of genes regulating climate adaptability,Carson Andorf,Taner Sen
+Machine learning approaches to gain structural and functional insights of genes regulating environment adaptability,Carson Andorf,Taner Sen
 Inferring Protein Function for Enhanced Breeding using Machine Learning and Protein Structure Prediction,Taner Sen,Carson Andorf
 A MATLAB toolbox for dynamic prediction of meteorological drought across Southern Great Plains,Daniel Moriasi,Ali Mirchi
 Optimization of AI-based microscope image analysis with the Blackbird imaging robot,Lance Cadle-Davidson,Yu Jiang
@@ -11,10 +11,10 @@ Improving the accuracy and scope of machine learning tools for camera trap-based
 "A broadly deployable deep learning workflow for image feature identification, segmentation, and data extraction.",Devin A Rippner,"Jeff Neyhart , Kayla Altendorf, Garett Heineck, Andrew McElrone"
 An AI approach for discovering novel blast disease resistance sources in rice.,Jeremy Edwards,Yulin Jia
 Predicting interspecies transmission of influenza A virus from swine to humans with machine learning,Tavis Anderson,Amy Vincent
-Modeling the Spread and Adaptation of Stored-Product Insect Pests in the Face of Climate Change,Alison Gerken,Rob Morrison
-Using AI to Analyze Climate Effects on Crop Performance,Xianran Li,
+Modeling the Spread and Adaptation of Stored-Product Insect Pests,Alison Gerken,Rob Morrison
+Using AI to Analyze Environmental Effects on Crop Performance,Xianran Li,
 AI/ML and Deep Learning to Enhance Understanding of Dietary Patterns that Promote Human Health,David Baer,Lauren O'Connor
 The evolutionary genomics of Macrophomina phaseolina.,Peter Montgomery Henry,
 Spatial multi-criterion optimization of agricultural ecosystem services at the landscape scale,Sarah Goslee,
 Application of machine learning in livestock genomics,George Liu,
-Determining the pervasiveness of hybridization and introgression in agriculture and the driving mechanisms,Christopher Owen,
+Determining the pervasiveness of hybridization and introgression in agriculture and the driving mechanisms,Christopher Owen,

pages/opportunities/ai-innovation/ai-innovation-fy24-awards.md

@@ -45,7 +45,7 @@ The ARS AI Center of Excellence (AI-COE) funded four AI Innovation Fund proposal
 
 * **PI and Co-PIs:** Carson Andorf, Hye-Seon Kim, and Taner Sen
 * **Amount of award:** $100,000
-* **Abstract:** _Fusarium_ is a pervasive fungal pathogen that poses significant threats to global food security and causes billions of dollars in economic loss annually. Climate change is predicted to enhance susceptibility to crop pathogens, demanding new resources to empower researchers and breeders to develop resilient strategies against _Fusarium_. Here we propose to develop the _Fusarium_-Host Interactome Discovery App, a digital application to identify genetic and proteomic interactions between _Fusarium_ and its cereal crop hosts: wheat, maize, barley, oat, and rye. The project will create an innovative artificial intelligence (AI) workflow that will predict host-pathogen protein-protein interactions, identify the functional consequences of missense mutations across all the species, provide protein functional and structural annotations, and create a web-based application. This application will utilize advanced protein language and protein diffusion models to elucidate the interactions of _Fusarium_ and cereal proteins that result in susceptibility or resistance. Visualization tools will enable users to explore how genetic mutations across 22 _Fusarium_ genomes and 135 cereal genomes impact protein interactions and identify potential targets for developing disease-resistant varieties. This collaborative project combines the expertise from multiple USDA-ARS Area locations, fostering synergy among maize, small grains, and _Fusarium_ research communities. The collective effort aims to aid researchers, breeders, and farmers in safeguarding cereal crop health against biotic threats by providing valuable foresight into the potential risks of emerging pathogens, their virulence levels, and the extent of variation in resistant germplasm. The application and datasets will be easily accessible through the GrainGenes and MaizeGDB databases.
+* **Abstract:** _Fusarium_ is a pervasive fungal pathogen that poses significant threats to global food security and causes billions of dollars in economic loss annually. Environmental change is predicted to enhance susceptibility to crop pathogens, demanding new resources to empower researchers and breeders to develop resilient strategies against _Fusarium_. Here we propose to develop the _Fusarium_-Host Interactome Discovery App, a digital application to identify genetic and proteomic interactions between _Fusarium_ and its cereal crop hosts: wheat, maize, barley, oat, and rye. The project will create an innovative artificial intelligence (AI) workflow that will predict host-pathogen protein-protein interactions, identify the functional consequences of missense mutations across all the species, provide protein functional and structural annotations, and create a web-based application. This application will utilize advanced protein language and protein diffusion models to elucidate the interactions of _Fusarium_ and cereal proteins that result in susceptibility or resistance. Visualization tools will enable users to explore how genetic mutations across 22 _Fusarium_ genomes and 135 cereal genomes impact protein interactions and identify potential targets for developing disease-resistant varieties. This collaborative project combines the expertise from multiple USDA-ARS Area locations, fostering synergy among maize, small grains, and _Fusarium_ research communities. The collective effort aims to aid researchers, breeders, and farmers in safeguarding cereal crop health against biotic threats by providing valuable foresight into the potential risks of emerging pathogens, their virulence levels, and the extent of variation in resistant germplasm. The application and datasets will be easily accessible through the GrainGenes and MaizeGDB databases.
 
 
 ### Bad apples? Next generation postharvest risk assessment tools

sn_collections/_posts/2021-01-10-Geil.md

@@ -7,6 +7,7 @@ excerpt: "Scientists of many disciplines, including agricultural fields, often u
 author:  Kerrie Geil
 affiliation: USDA-ARS, SCINet Postdoctoral Fellow, Las Cruces, NM
 
+
 ---
 
 

sn_collections/_posts/2021-04-15-Hudson.md

@@ -7,6 +7,7 @@ excerpt: "Rising global temperatures have cascading effects on Earth’s agro-ec
 author: Amy Hudson
 affiliation: USDA-ARS, SCINet Postdoctoral Fellow, Las Cruces, NM
 
+published: false
 ---
 
 

sn_collections/_workshops/2023-geospatial-workshop/2023-9-25-Geospatial-Workshop-1.md

@@ -93,7 +93,7 @@ Noa Mills | My research focuses on using deep learning tools to identify agricul
 Andrea Albright | UAS image processing using ODM on the HPC
 Piyush Pandey | I will present my work in using deep learning models for object detection with UAV images. I have used several approaches to accomplish this including the creation of synthetic training images. I will present tools that may be useful for researchers trying to identify objects and extract traits from UAV imagery.
 Haoteng Zhao | Using SCINet and remote sensing to monitor crop conditions
-Laura Tibbs-Cortes | Switchgrass is not only a native North American prairie grass, but also a biofuel crop, and its response to climate change will have impacts on both conservation and agriculture. This project identifies genetic and environmental factors affecting important fitness and agronomic traits in switchgrass including flowering time, biomass, and winter survival. These results, combined with future climate predictions, indicate that a major shift in the distribution of switchgrass subpopulations is likely by the end of this century as warming temperatures alter the competitive advantage of alleles.
+Laura Tibbs-Cortes | Switchgrass is not only a native North American prairie grass, but also a biofuel crop, and its response to environmental change will have impacts on both conservation and agriculture. This project identifies genetic and environmental factors affecting important fitness and agronomic traits in switchgrass including flowering time, biomass, and winter survival. These results, combined with future predictions, indicate that a major shift in the distribution of switchgrass subpopulations is likely by the end of this century as warming temperatures alter the competitive advantage of alleles.
 Kevin Li | Landscapes can support multiple ecosystem services, or benefits from nature to people. The requirements for these ecosystem services may result in trade-offs and synergies when considering alternative landscape scenarios. The goal of our project is to use machine learning to identify scenarios that optimize multiple ecosystem services within a landscape.
 Dalmo Vieira | A methodology was developed to estimate soil erosion for large watersheds using machine learning and RUSLE2.  The approach uses improved terrain analysis methods to define surface runoff patterns and subdivide the study area into hillslopes for erosion calculation.  Machine learning was used to speed up RUSLE2 erosion calculations by a factor of 65,000, allowing for the production of erosion maps for very large areas at 10-meter resolution.
 Lucas Heintzman | Ditch networks enhance field drainage, mediate runoff contamination, and are crucial habitat for species. However, our understanding of ditch networks (and associated ecological dynamics) has been constrained due to private land access and insufficient elevation models. Thus, our project aims to develop a regional classification and accounting system to accurately delineate and quantify ditch networks via LiDAR and ML.