Progress 05/01/24 to 04/30/25
Outputs
Target Audience:ThetargetaudienceincludefacultyandstudentsinbothCollegeofEngineeringandCollegeofAgriculture,Food,and Natural Resources at PVAMU. Specifically, the following seminars had been offered to the faculty and students in both College of Engineering and College of Agriculture, Food and Natural Resources at PVAMU: Title: "Deep Knowledge Tracing for Personalized Adaptive Learning at Historically Black Colleges and Universities (HBCUs)," by Co-PI Dr. Xishuang Dong, Assistant Professor, Department of Electrical and Computer Engineering, Prairie View A&M University, on Oct 23, 2024. Title: "Building urban climate resilience using spatial data science," by Wei Zhai, Ph.D., Assistant Professor, Urban and Regional Planning, Architecture and Planning, University of Texas San Antonio, on Oct 9, 2024. Title: "Mechanical Stimulation Increases Sorghum Stem Strength and Flexibility and is Associated with Altered Transcriptome Expression and Hormone Homeostasis," by Qing Li, Ph.D., Post-doctoral researcher, CARC, College of Agriculture, Food, and Natural Resources, Prairie View A&M University, on April 24, 2024. Title: "Toward reliability evaluation of computational models of protein molecules and their interactions," by Md Hossein Shuvo, Ph.D., Assistant Professor, Department of Computer Science, Roy G. Perry College of Engineering, Prairie View A&M University, on Feb 19, 2025. Title: "Vascular tissue-mediated molecular responses to low phosphorus," by Cankui Zhang, Ph.D., Associate Professor, Dept. of Agronomy at Purdue University, on March 5, 2025. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided? Multiple students have worked closely with the PIs on the project. The PIs hold regular bi-weekly meetings with the students, discuss their progress and provide guidance on their research works. The PIs also provides feedback on their draft papers and thesis, project reports and presentations. The students are encouraged to present their research results in professional conferences and workshops and develop their professional networks. We have provided multiple tutorial workshops and trainings to students. For instance, a Python Programming Workshop was offered in Fall 2024 at PVAMU. How have the results been disseminated to communities of interest?The results are disseminated through a seminar series organized by the PIs, journal and conference publications, new courses, trainings, and a website dedicated to this project. In addition, the PIs also visited many researchers in the field to discuss research results and seek potential collaborations. Specifically, (1)A website has been created and maintained to help disseminate the research results and recruit students to participate in this project: https://www.pvamu.edu/engineering/usda-nifa/ (2)A seminar series had been offered: Title: "Deep Knowledge Tracing for Personalized Adaptive Learning at Historically Black College and Universities (HBCUs)," by Co-PI Dr. Xishuang Dong, Assistant Professor, Department of Electrical and Computer Engineering, Prairie View A&M University, on Oct 23, 2024. Title: "Building urban climate resilience using spatial data science," by Wei Zhai, Ph.D., Assistant Professor, Urban and Regional Planning, Architecture and Planning, University of Texas San Antonio, on Oct 9, 2024. Title: "Mechanical Stimulation Increases Sorghum Stem Strength and Flexibility and is Associated with Altered Transcriptome Expression and Hormone Homeostasis," by Qing Li, Ph.D., Post-doctoral researcher, CARC, College of Agriculture, Food, and Natural Resources, Prairie View A&M University, on April 24, 2024. Title: "Toward reliability evaluation of computational models of protein molecules and their interactions," by Md Hossein Shuvo, Ph.D., Assistant Professor, Department of Computer Science, Roy G. Perry College of Engineering, Prairie View A&M University, on Feb 19, 2025. Title: "Vascular tissue-mediated molecular responses to low phosphorus," by Cankui Zhang, Ph.D., Associate Professor, Dept. of Agronomy at Purdue University, on March 5, 2025. What do you plan to do during the next reporting period to accomplish the goals? We plan to collect images of plants using UAV at the experimental farm field at PVAMU. We plan to explore the application of the emerging generative AI tools for this project.
Impacts
What was accomplished under these goals?
During this funding period, we started to explore images from drones for crop/vegetation health assessment and prediction. Specifically, themulti-spectral images of farm land taken by drones are used to calculate theNormalized Difference Vegetation Index (NDVI) values.Then various machine learning models such as CNN based models and Transformer-based models have been designed and implemented to forecast Normalized Difference Vegetation Index (NDVI) values.
Publications
- Type:
Peer Reviewed Journal Articles
Status:
Published
Year Published:
2025
Citation:
Wilson, D.D., Tefera, G.W., Ray, R.L. 2025. Application of Google Earth Engine to Monitor Greenhouse Gases. A Review. Data/MDPI, 10(1), 8. https://doi.org/10.3390/data10010008
|
Progress 05/01/23 to 04/30/24
Outputs
Target Audience:The target audience include faculty and students in both College of Engineering and College of Agriculture,Food, and Natural Resources at PVAMU. Specifically, we have reached to the following groups: (1) A new course, "Machine Learning for Engineering Applications" has been developed in Fall 2022 and taught in both Fall 2022 andFall 2023semester by co-PI (Dong). Many students enrolled in the class and very positive feedback had been obtained from the students. (2) The following seminars had been offered to the faculty and students in both College of Engineering and College of Agriculture, Food and Natural Resources at PVAMU: (i) Title: "Proformer-Based Ensemble Learning for Gene Expression Prediction," by Co-PI Dr. Xishuang Dong, Assistant Professor,Department of Electrical and Computer Engineering, Prairie View A&M University, on March 6, 2024. (ii) Title: "Branches, Boundaries and Bracts: in Search of the Meristematic Homunculus," by Dr. Clint Whipple, Associate Professor,Whipple Lab, Biology, College of Life Sciences, Brigham Young University, on October4, 2023. (iii)Title: "Functionally repolarizing myeloid stroma with synthetic STING agonists drives immune clearance of Glioblastoma," by Dr.Michael Curran, Associate Professor, Department of Immunology, Division of Basic Science Research, The University of Texas MD Anderson Cancer Center, Houston, TX on May 10, 2023. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?(1) Multiple students have worked closely with the PIs on the project. The PIs hold regular bi-weekly meetings with the students, discuss their progress and provide guidance on their research works. The PIs also provides feedback on their draft papers and thesis, project reports and presentations. (2) The students are encouraged to present their research results in proefsssional conferences and wrokshops and develop their professsional networks. (3) We have provided multiple tutorial workshops and trainings to students: for instance, we organized and delivered (together with NVIDIA) the Workshop and Training Courses of "Fundamental of Deep Learning" on October 19, 2023 at PVAMU campus. Many students received NVIDIACertificate in Deep Learning after participating the training. How have the results been disseminated to communities of interest?The results are disseminated through a seminar series organized by the PIs, journal and conference publications, new courses, trainings, and a website dedicated to this project.In addition, the PIs also visited many researchers in the field to discuss research results and seek potential collaborations. Specifically, (i) Two conference papers were published and presented and one journal paper was submitted and under review. -- Journal paper: Olamofe, R. Ray, X. Dong, and L. Qian, "Normalized Difference Vegetation Index Prediction using Reservoir Computing and Pretrained Language Models," submitted to Artificial Intelligence in Agriculture, 2024. -- Conference papers: 1) J. Olamofe, R. Ray, X. Dong, and L. Qian, "Normalized Difference Vegetation Index Prediction using Reservoir Computing and Pretrained Language Models," The 2024 AI in Agriculture and Natural Resources Conference, April 15-17, 2024, College Station, TX. 2) L. Nwosu, X. Li, S. Kim, L. Qian, X. Dong (2023). "Proformer-based Ensemble Learning for Gene Expression Prediction," ICIBM. (ii) A website has been created and maintained to help disseminate the research results and recruit students to participate in this project: https://www.pvamu.edu/engineering/usda-nifa/ (iii) A seminar serieshad been offered: 1) Title: "Proformer-Based Ensemble Learning for Gene Expression Prediction," by Co-PI Dr. Xishuang Dong, Assistant Professor,Department of Electrical and Computer Engineering, Prairie View A&M University, on March 6, 2024. 2) Title: "Branches, Boundaries and Bracts: in Search of the Meristematic Homunculus," by Dr. Clint Whipple, Associate Professor,Whipple Lab, Biology, College of Life Sciences, Brigham Young University, on October4, 2023. 3)Title: "Functionally repolarizing myeloid stroma with synthetic STING agonists drives immune clearance of Glioblastoma," by Dr.Michael Curran, Associate Professor, Department of Immunology, Division of Basic Science Research, The University of Texas MD Anderson Cancer Center, Houston, TX on May 10, 2023. What do you plan to do during the next reporting period to accomplish the goals?(1) We plan to collect sensor data in the Summerof 2024 using the field sensors deployed in the PVAMU research farm. We also plan to collect images of plants using UAV at the same experimental farm field. (2) We plan to explore the application of the emerging generative AI tools for this project. (3) We plan to recruit more students especially female students to participate this project.
Impacts
What was accomplished under these goals?
During this funding period, we evaluated the performance of Reservoir Computing (RC) and Transformer-based model to forecast Normalized Difference Vegetation Index (NDVI) values. Using "MODIS/Terra Vegetation Indices 16-Day L3 Global 250m SIN Grid V061" dataset, we compared the forecast performance of these models to traditional ML/DL methods such as Nonlinear Regression, Decision Tree, Reservoir Computing (RC), Pretrained LSTM Reservoir, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and DLinear. Notably, the DLinear/LSTM model showed exceptional predictive accuracy, while the Pretrained RC model significantly enhanced traditional RC model forecasts. Additionally, Frozen Pretrained Transformer (FPT) showed superior performance in forecasting specific NDVI values (most often peak/lowest NDVI), suggesting its effectiveness in precise time series predictions. Transformer-based models, specifically PatchTST and FPT, demonstrated substantial mean squared error reductions, particularly in limited data scenarios (50% and 1% sample sizes), indicating their robustness in precise NDVI time series predictions under data constraints.
Publications
- Type:
Journal Articles
Status:
Under Review
Year Published:
2024
Citation:
J. Olamofe, R. Ray, X. Dong, and L. Qian, Normalized Difference Vegetation Index Prediction using Reservoir Computing and Pretrained Language Models, submitted to Artificial Intelligence in Agriculture, 2024
- Type:
Conference Papers and Presentations
Status:
Accepted
Year Published:
2024
Citation:
J. Olamofe, R. Ray, X. Dong, and L. Qian, Normalized Difference Vegetation Index Prediction using Reservoir Computing and Pretrained Language Models, The 2024 AI in Agriculture and Natural Resources Conference, April 15-17, 2024, College Station, TX.
|
Progress 05/01/22 to 04/30/23
Outputs
Target Audience:The target audience include faculty and students in both College of Engineering and College of Agriculture and Human Sciences at PVAMU. Specifically, we have reached to the following groups: (1) A new course, "Machine Learning for Engineering Applications"has been developed and taught in Fall 2022 semesterby co-PI (Dong). fifteen (15) students enrolled in the class and very positive feedback had beenobtained from the students. (2) The following seminars had been offered to thefaculty and students in both College of Engineering and College of Agriculture and Human Sciences at PVAMU: (i) Title: "Decoding Sorghum genome using a mutant population," by Dr. Yinping Jiao, Assistant Professor, Institute of Genomics for Crop Abiotic Stress Tolerance (IGCAST), Texas Tech University, on Jan.25, 2023. (ii) Title: "Several partially distinct molecular pathways control shoot branching in the grasses," by Dr. Tesfamichael Kebrom, Research Scientist, CARC, College of Agriculture and Human Sciences & CCSB, Electrical and Computer Engineering Department, Roy G. College of Engineering, Prairie View A&M University, on Feb. 08, 2023. Changes/Problems:
Nothing Reported
What opportunities for training and professional development has the project provided?(1) Students have worked closely with the PIs on the project. The PIs hold regular bi-weekly meetings with the students, discuss their progress and provide guidance on their research works. The PIs also provides feedback on their draft papers and thesis, project reports and presentations. (2)A hands-on Python tutorial training was offered in Fall 2022semester. Many faculty, staff, and students participated the training and very positive feedback has been received. The PIs plan to offer more tutorials in the coming semesters. (3) A new course, "Machine Learning for Engineering Applications"has been developed and taught in Fall 2022 semesterby co-PI (Dong). fifteen (15) students enrolled in the class and trained on using machine learning to solve real-world problems. How have the results been disseminated to communities of interest?The results are disseminated through a seminar series organized by the PIs, journal and conference publications, new courses, trainings, and a website dedicated to this project.In addition, the PIs also visited many researchers in the field to discuss research results and seek potential collaborations. Specifically, (1) A new course, "Machine Learning for Engineering Applications"has been developed and taught in Fall 2022 semesterby co-PI (Dong). The research results have been incorporated in the class materials. Fifteen (15) students enrolled in the class and very positive feedback had beenobtained from the students. (2) The following seminars had been offered to thefaculty and students in both College of Engineering and College of Agriculture and Human Sciences at PVAMU: (i) Title: "Decoding Sorghum genome using a mutant population," by Dr. Yinping Jiao, Assistant Professor, Institute of Genomics for Crop Abiotic Stress Tolerance (IGCAST), Texas Tech University, on Jan.25, 2023. (ii) Title: "Several partially distinct molecular pathways control shoot branching in the grasses," by Dr. Tesfamichael Kebrom, Research Scientist, CARC, College of Agriculture and Human Sciences & CCSB, Electrical and Computer Engineering Department, Roy G. College of Engineering, Prairie View A&M University, on Feb. 08, 2023. (3) A conference paper was submitted for publication. (4) A webpage has been created for this project.Publications, research activities and software packages are available on the website to share with the research community at large. What do you plan to do during the next reporting period to accomplish the goals?We will collect drone image data and field sensor data in Spring and Summer of 2023 and complete the multi-resolution data processing as planned. Inaddition, novel semi-supervised deep learning models and reservoir computing models will be developed for plant health prediction.
Impacts
What was accomplished under these goals?
(1) The satellite image dataset had been obtained and converted to NDVI values for the farms in Texas from 2000 to 2022. Then various machine learning and deep learning models including decision trees, linear regression, CNN, LSTM have been trained on the obtained data. It is observed that LSTM outperformed other models in terms of MAPE and MSE. (2) Field sensors have been deployed in the testbed of the PVAMU farm. We plan to collect sensor data in the Spring and Summer growing season of 2023.
Publications
- Type:
Conference Papers and Presentations
Status:
Submitted
Year Published:
2023
Citation:
L. Nwosu, X. Li, S. Kim, L. Qian, X. Dong (2023). Proformer-based Ensemble Learning for Gene Expression Prediction, submitted to ICIBM.
- Type:
Websites
Status:
Published
Year Published:
2023
Citation:
https://www.pvamu.edu/engineering/usda-nifa/
|