External Research Posters

Follow

• 

  Enhancing Crop Yield through Efficient Anomaly Detection Using Transfer Learning and Multispectral Satellite Imagery

  Muhammad Bhutta, Khandaker Mamun Ahmed, Abid Mehmood, Youssef Harrath, and Jihene Kaabi Dr.

  The increasing demand for sustainable agriculture necessitates innovative approaches for monitoring and enhancing crop health. Data-driven methods, combined with advanced machine learning models and remote sensing technologies, present significant potential to bridge the gap between early anomaly detection and timely intervention. Our research explores the development of a robust system integrating state-of-the-art deep learning techniques with transfer learning and multispectral satellite imagery to detect crop anomalies. The proposed system leverages publicly available datasets to identify early symptoms of crop stress—such as yellowing, spotting, and wilting—in key crops, including corn, soybeans, wheat, and sunflowers. Furthermore, the study investigates the influence of environmental factors, such as lighting conditions, weather patterns, and soil characteristics, on detection accuracy. By providing actionable insights for optimizing intervention strategies, this research aims to advance sustainable agricultural practices and improve crop yields. The work also contributes to the broader field of data science by demonstrating the application of sophisticated models in tackling complex agricultural challenges.

• 

  Generative AI for Synthetic Data Creation: Building Mastery-Focused Educational Datasets

  Tapiwa Amion Chinodakufa and Khandaker Mamun Ahmed

  There is no easily-available dataset for mastery-focused education, where mastery replaces grades while accurately reflecting student performance. Student data is restricted due to privacy & security concerns. One K-12 app was recently discovered selling unmasked data on millions of students Synthetic datasets may solve this by providing utility, privacy preservation, scalability, customization, variability, and resistance to reverse-engineering Techniques used included autoencoders, variational auto-encoders (VAE), generative adversarial networks (GAN) , and copulas combined with GANs.

• 

  AI Super Resolution for Structural Damage Detection From Low Quality Sources

  Catherine Hoier and Khandaker Mamun Ahmed

  The identification of damages following natural disasters is of critical importance, as it plays a crucial role in mitigating the risk of subsequent harm, including additional structural damage, injuries, or fatalities. Artificial intelligence (AI) presents significant advantages in this domain by offering faster, more precise, and scalable assessments compared to traditional reliance on expert evaluations alone. When integrated with expert analysis, AI has the potential to enhance the efficiency and accuracy of damage detection, facilitating a comprehensive and rapid assessment of affected structures. Such capabilities are vital for minimizing future risks and enabling timely and effective recovery efforts. This study proposes an AI-based super-resolution method designed to detect structural damages from low-quality data sources. By enhancing the clarity and detail of damage assessments, the proposed approach provides critical information to first responders, enabling them to take informed and calculated measures in disaster response scenarios. This methodology aims to bridge existing gaps in damage detection systems, contributing to improved resilience and preparedness in the face of natural disasters.

• 

  Machine Learning and SHAP Interpretability for Chronic Disease Understanding

  Nnaemeka Charles Igwe

  Our study predicts non-communicable diseases (NCDs), such as diabetes, by leveraging machine learning algorithms. We leverage hyperparameter tuning techniques for model development and SHapley Additive exPlanation (SHAP) for results interpretations.

• 

  Bones et. al: Educational Human Skeletons Restoration and Investigation

  Emelye Josko and Andrew E. Sathoff

  There has been a longstanding tradition to use real human skeletons as educational aids in classrooms (2). The interactive nature of hands-on learning often results in the degradation of these skeletal specimens, and repairs are needed to bring them back to being fully functional. Drawing techniques from one of the few guides to restoring educational classroom skeletons {1) and museum approaches (2, 3, 5), we are able to find a method that works for three human skeletons at Dakota State University.

• 

  Functional analysis of differentially expressed genes in alfalfa (Medicago sativa) inoculated with Aphanomyces euteiches race 1 and race 2

  Jay Alexander, Deborah A. Samac, and Andrew E. Sathoff

  Aphanomyces root rot caused by Aphanomyces eureiches ,s one of the most destructive diseases of alfalfa. Resistant cultivars have been developed that exhibit race-specific resistance. Transcript profiling was done to gain a better understanding of the compatible and incompatible interactions. Three-day-old Seed lings of the check cultivars WAPH-1 (resistant to race 1 strains) and WAPH-5 ( resistant to race 1 and race 2 strains) were inoculated with MF-1 (race 1) and IVIE R-4 (race 2) and RNA extracted 24 h post-inoculation, with three biological replicates. RNA.seq using an lllumina HiSeq 2500 to obtain 125 bp paired-end reacts was carried out with > 10.5 million reads/sample. Differentially expressed genes (DEGs) were identified after sequence trimming and quality control. The incompatible interaction in WAPH-1 and WAPH-5 to MF-1 contained the most Unique up-regulated DEGs, 637 and 217, respectively. The incompatible response of WAPH-5 to MF-1 and MER-4 appears to be similar with 258 common up-regulated DEGs and only 59 unique DEGs in response to MER-4. Functional an notation of the DEGs was performed using the Blast2GO tool. The unique DEGs of the incompatible interactions were primarily placed into four categories in the Gene Ontology term Biological Processes: 'defense response,' 'response to stress,' 'organic substance catabolic process,' and 'protein phosphorylation'. These results increase understanding of the A. euteiches and alfalfa molecular interaction for development of cultivars with increased resistant to Aphanomyces root rot.

• 

  Quantitative Real-Time PCR Identification of Soybean Pathogens in Eastern South Dakota Soil

  Brandon Daniels, Oleksandra Rachynska, Travis R. Rebstock, Conner L. Tordsen, and Andrew E. Sathoff

  According to the 2021 State Agricultural Overview, South Dakota (SD) planted 5,450,000 acres of soybeans in 2021, and 5.8% of potential soybean production was lost due to diseases. Revealing prevalent soil borne soybean pathogens throughout the state and utilizing the proper management strategies could in crease SD soybean yields. With the relatively recent (2014) first report of soybean sudden death syndrome (SDS) in SD and confirmation of SOS in three more counties in 2017, we utilized quantitative realtime polymerase chain reaction (qPCR) assays to detect pathogens that cause SDS and other soilborne soybean pathogens using DNA extracted from the soil. qPCR-based diagnostics efficiently and specifically test for pathogens with high sensitivity. The soil was sampled from six fields under commercial soybean production in Deuel County and Brookings County. The collected soil was dried at ss·c for two days, and three DNA extractions were done for each field sampled. qPCR assays were performed on a BioRad CFX Opus 96 Real-Time PCR system for several soybean pathogens such as Fusarium virguliforme, Fusarium brasi/iense, Phytophthora sojae, Phytophthara sansomeana, and Phiolophora gregata. qPCR reactions were run in triplicate, with three technical replicates on each biological replicate per field assessed. The presence of P. gregata was detected in three out of the six fields evaluated, while F. virguliforme, F. brasiliense, P. sojae, and P. sansomena were not detected. Our primary objective was to develop distinct qPCR protocols on samples of DNA extracted directly from the soil for a more extensive SD soil borne soybean pathogen survey in Fall 2022 and Summer 2023. Providing SD soybean growers with accurate, timely information about pathogens detect ed in their soil should allow them to take proper management strategies and increase their yields.

• 

  Identification and Characterization of Pythium Species Isolated From Commercial Alfalfa Fields in South Dakota

  Oleksandra Rachynska, Travis R. Rebstock, Conner L. Tordsen, Jennifer M. Giles, and Andrew E. Sathoff

  Alfalfa (Medicaga sativa) seeds are often planted when environmental conditions are optimal for Pythium seed rot and damping-off, which is caused by various different Pythium species. Pythium seed rot can devastate alfalfa stands requiring them to be completely replanted. South Dakota plants the second most acres of alfalfa in the United States, and surveys describing Pythium spp. causing disease on alfalfa In the state were lacking. In this study, putative Pythium isolates were baited from soil samples collected In eastern South Dakota using the rolled•towel technique. Pure cultures were obtained, and Pythium spp. were identified using ITS and cox1 sequences. The Pythium isolates were assessed for pathogenicity on alfalfa using a culture plate method. P. sylvaticum was the most frequently Isolated alfalfa pathogen. Several commercial fungicides were evaluated against Pythium spp. using agar plate-based assays. CruiserMaxx (mefenoxam, fludioxonil, thiamethoxam) demonstrated strong activity against Pythium isolates. This study establishes the presence of a diverse array of Pythium spp. that are alfalfa pathogens in South Dakota, and the fungicide sensitivity tests provide growers with localized information to select effective fungicide treatments. Increased grower awareness to Pythium diseases of alfalfa may lead to better disease management and increased alfalfa yields in South Dakota.ds

• 

  Assessing Commercial Biological Control Agents for Activity Against Alfalfa Root Rotting Pathogens

  Travis R. Rebstock, Conner L. Tordsen, Brandon Daniels, Oleksandra Rachynska, and Andrew E. Sathoff

  Alfalfa is the fourth most valuable crop in the United States and is widely grown as feed for livestock due to Its high protein content. According to the USDA 2021 Crop Production Summary, the United States planted 1,646,000 acres of newly seeded alfalfa, and alfalfa seedlings are highly susceptible to disease. Pathogens such as Aphanomyces euteiche.s and Pythium sp. have devastating effects on newly seeded alfalfa stands causing seed rot, reduced root development, and diminished stand establishment. Current management strategies for these diseases are fungicidal seed treatments and planting of disease resistant alfalfa varieties. To expand upon these management strategies, we investigated commercial biological control (biocontrol) treatments. Isolates of both A. euteiches and Pythium sp. were tested against commercial biocontrol agents with active ingredients such as: Streptomyces octinobacterium K61 {Mycostop), Bacillus amyloliquefociens D747 (Southern Ag), Srrepromyces lydicus WYEC 108 (Actinovate), Bacillus subrilis QST 713 (Minuet/Serenade), Trichoderma aspere/fum ICC012 and Trichodermo gamsii ICC080 (Tenet), and Trichodermo hawanum Rifai KRL-AG2 (RootShield). Biocontrol activity against A. euteiches and Pythium sp. was evaluated in growth chamber assays using a susceptible alfalfa variety, Saranac. Treatment effectiveness against A. ,uteiches was assessed by rating seedling roots using the NAAIC Standard Test rating scale of 1-5, with a score> 2 indicating susceptibility. Seedlings in pots inoculated with Pythium sp. were counted after 5 days to calculate percent germination. Biological controls with the active ingredient, 8. amylolique/aciens 0747 have antagonistic effects ,gains! Pythium sp. increasing percent germination of alfalfa by 21-70% depending on the pathogen isolate. 5. 1ctinobacterium K6! (Mycostop) had high activity against A. euteiches. Several biological control agents demonstrated activity against both A. euteiches and Pythium sp., providing an additional management strategy against these root rotting pathogens.

• 

  Managing South Dakota Alfalfa Diseases with Commercial Biological Control Agents

  Travis R. Rebstock, Conner L. Tordsen, Brandon Daniels, Oleksandra Rachynska, and Andrew E. Sathoff

  Alfalfa is the fourth most valuable crop in the United States and is widely grown as feed for livestock due to its high protein content. In 2021, South Dakota harvested 1,320,000 acres of alfalfa and has some of the most acres growing in the United States. Alfalfa seedlings are highly susceptible to disease, which reduces field establishment and yield. Oomycete pathogens, Aphanomyces euteiches and Pythium sp., have devastating effects on newly seeded alfalfa fields causing seed rot and reduced root development. Current management strategies are fungicidal seed coatings and planting disease resistant alfalfa varieties. To create more of an Integrated management strategy, we investigated numerous commercial, organic biological control (biocontrol) treatments, which had previously shown to be effective against oomycetes but have not been tested against alfalfa pathogens. South Dakota and USDA isolates of both A. euteiches and Pythium sp. were evaluated against biocontrols with active ingredients such as: Streptomyces octinobacterium K61 (Mycostop), Bacillus amyloliquefaciens D747 (Southern Ag), Streptomyces lydicus WYEC 108 (Actinovate), and Bacillus subtilis QST 713 (Serenade). Biocontrol activity against A. euteiches and Pythium sp. was evaluated in growth chamber assays using seed of a susceptible alfalfa variety, Saranac. Treatment effectiveness against A. euteiches was assessed by rating seedling roots after 29 days using a standardized rating scale. Seedlings inoculated with Pythium sp. were evaluated after 5 days to calculate percent germination. Biocontrols with the active ingredient, B. amyloliquefaciens D747 have antagonistic effects against Pythium sp. increasing percent germination by up to 71%. 5. octlnobacterium K61 had high activity against several isolates of A. euteiches. Various biological control agents demonstrated activity against alfalfa pathogens, which provides growers with an additional management strategy to protect their fields. In Fall 2022, we plan on testing A. euteiches and Pythium sp. isolates against biocontrol treatments that use fungal antagonists.

• 

  Assessing Commercial Biological Control Agents for Activity Against South Dakota Alfalfa Pathogens

  Conner L. Tordsen and Andrew E. Sathoff

  Alfalfa is the third most valuable crop in the United States and is commonly grown in South Dakota. It is used as a protein-rich feed for livestock, a cover crop that protects against soil erosion, and a natural fertilizer because of its ability to fix nitrogen in the soil. According to the USDA 2021 Crop Production Summary, South Dakota ranks third in the US for newly seeded acres, and alfalfa seedlings are highly susceptible to disease. Oomycete pathogens are arguably the most economically important pathogens causing negative effects on alfalfa field establisthment and yield. These root rotting pathogens (Aphanomyces euteiches and Pythium spp.) can cause seed rot, reduce root development, and diminish stand establishment. Oomycete pathogens that inhabit the soil can remain present and pathogenic as oospores for many years regardless of soil conditions. Seed rot is a major issue, forcing growers to spend a substantial amount of money to replant stands. Recent research tested the management strategy of using fungicidal treatment to inhibit these pathogens. These chemical treatments were unsuccessful against many of these pathogens in field studies (Smith, 2014). In this study, alfalfa root rotting pathogen isolates from South Dakota fields and the USDA were evaluated for sensitivity to biological control treatments. A biological control is the addition of a natural microbial predator to a inhibit the growth of a pathogen or pest. This research will identify additional management strategies for South Dakota alfalfa diseases and provide growers with the information necessary to make educated decisions to increase yields and maximize their profits.

• 

  Isolation and Characterization of Pythium spp. from South Dakota soils under commerical alfalfa production

  Jennifer M. Giles and Andrew E. Sathoff

  Alfalfa is a significant crop in South Dakota that provides many different benefits for its growers. South Dakota plants the most acres of alfalfa in the United States. It is used as a protein protein-rich feed for livestock, a cover crop that protects against soil erosion, and a natural fertilizer because of its ability to fix nitrogen in the soil. However, alfalfa seedlings are susceptible to many diseases. Pythium root and seed rot is one disease known to have devastating effects on alfalfa field establishment and yield. Pythium species are oomycete pathogens that inhabit the soil and remain present and pathogenic as oospores. Pythium diseases of alfalfa cause reduced root systems, plant size, length, and growth rate. Pythium management is centered on fungicidal seed treatments. There have been recent reports of Pythium spp. infecting alfalfa across the world in places like Sudan and China, but current research in South Dakota is needed. In our research, we isolated Pythium spp. from Lake County South Dakota soils under commercial alfalfa production. We also characterized these isolates with a DNA sequencing analysis and evaluated the isolates for fungicide sensitivity. This summer, we will conduct a statewide Pythium disease survey and assess the collected isolates for fungicide sensitivity and pathogenicity towards various commercial lines of alfalfa. This research will provide growers with the information necessary to Make educated decisions in order to increase yields and maximize their profits.

• 

  Aphanomyces root rot of alfalfa disease survey in Eastern South Dakota establishes widespread pathogen distribution

  Jennifer M. Giles, Conner L. Tordsen, and Andrew E. Sathoff

  Aphanomyces euteiches causes Aphanomyces root rot (ARR) and damping-off in alfalfa (Medicago sativa), along with root rotting in many other legumes. According to the United States Department of Agriculture 2020 Crop Production Summary, South Dakota plants the most acres of alfalfa in the United States but is the sixth highest state in production. Identification of A. euteiches has been confirmed in several states surrounding South Dakota providing the need for detection in state since ARR management centers on planting resistant alfalfa cultivars.

• 

  Assessment of Wax Worms (Galleria mellonella) as a Suitable Alternative Host to Study the Virulence of the Marine Pathogen Vibrio coralliilyticus

  Vaille Swenson, Darrell Artz, Alexy Jakowicz, Timothy Cramer, Trever Listman, Michael Gaylor, Blake Ushijima, and Patrick Videau

• 

  Science at Dakota State University

  Vaille Swenson, Michael Gaylor, Blake Ushijima, and Patrick Videau