User Tools

Site Tools



This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
projects:year9:9a.001.ul [2021/05/06 08:21]
sally.johnson [Project - Documents]
projects:year9:9a.001.ul [2022/02/08 08:28] (current)
sally.johnson [Project - Documents]
Line 3: Line 3:
 <WRAP leftalign box > <WRAP leftalign box >
-In this project we plan to utilize state of the art Machine Learning (ML) based data fusion methods and workflows to optimize the level of information obtained from the plethora of available environmental datasets. Currently, the state of Louisiana is pursuing a statewide modeling and monitoring effort for flood applications. This statewide effort can greatly benefit from methods that can reduce the amount of confusion resulting from the availability of the large amounts of data that will be collected by field sensors and generated by hydrologic and hydraulic models. After a thorough literature review of the current state of technology, it is clear to us that there are gaps to fill in order to make the best use of the available data fusion methods for environmental applications in general and flood modeling in particular. Very few studies explored multimodal (e.g., different sensors and different spatiotemporal resolutions) data fusion methods using the latest advances in ML in environmental sciences applicationsThese studies are limited to certain applications such as land cover classification. In additiona much smaller set of these studies utilized cooperative multimodal data fusion (i.e., combining information from multiple independent sources into a new more complex type of informationusing ML methods such as Support Vector Machine (SVM) and ranking SVM toolsIn this project we plan to focus on feature based data fusion analyses. This will allow us to produce datasets that are free of redundant information and where the input datasets are ranked and prioritized based on the information they contribute to the consequent ML based prediction models. As an examplethese methods will be able to fuse multimodal data obtained from different sensors (e.g.satellite and ground observations) and different types (e.g., model outputs at different spatial and temporal resolutions)+**OBJECTIVES** 
 +  * Identify and implement latest Deep Learning and data mining approaches to establishing ontology-based data integration for variables with different spatial and temporal resolution’s (e.g., raster vsvectorhourly model outputs vssatellite overpass). 
 +  * Identify and implement methods to maximize AI model learning efficiency through identifying the significant variablesinter-data relationships, and the elimination of redundant information  
 </WRAP> </WRAP>
 ===== Project - Team ===== ===== Project - Team =====
-^ Team Member        ^ Role        ^ Email                            ^ Phone Number    ^ Academic Site/IAB   ^ +^ Team Member                                              ^ Role            ^ Email                             ^ Phone Number    ^ Academic Site/IAB   ^ 
-| Emad Habib         | PI          |         | (337) 482-6513  | UL Lafayette        | +| [[about:personnel:emad_habib|Emad Habib]]                | PI              |          | (337) 482-6513  | UL Lafayette        | 
-| Mohamed ElSaadani Researcher  |  | N/A             | UL Lafayette        | +| [[about:personnel:mohamed_elsaadina|Mohamed ElSaadani]]  Co-PI           |   | (337) 789-9828  | UL Lafayette        | 
-| Magdy Bayoumi      Researcher  |            | (337) 482-5365  | UL Lafayette        | +| [[about:personnel:magdy_bayoumi|Magdy Bayoumi]]          Co-PI           |             | (337) 482-5365  | UL Lafayette        | 
-TBD                | Student     N/A                              | N/A             | UL Lafayette        | +[[about:personnel:ahmed_abdelhameed|Ahmed Abdelhameed]]  | Student  | N/A             | UL Lafayette        | 
-                                                                |                 | **Funded by: CGI**  |+Sumit Shah                                               Project Mentor  |         | (202) 309-8790  | CGI                 | 
 +|                                                          |                                                   |                 | **Funded by: CGI**  |
 ===== Project - Novelty of Approach ===== ===== Project - Novelty of Approach =====
 <WRAP leftalign box > <WRAP leftalign box >
-Despite the great potential of the available ML methods and tools available, the environmental sciences field is yet to catch up with the current state of the artIn additionnow that we have achieved the CNN and conv-LSTM models for prediction; there are no studies that utilized the large number of available data to enhance the performance and the predictive ability of our ML forecast models+  * Efficiently quantify the added-value of including a given available dataset in decreasing the models’ learning time and increasing the overall performance, this is needed to avoid redundancy and un-needed information. 
 +  * Due to the large amounts of the available data, a single data source or a combination of data sources with similar features (e.g., raster only data) are often used to derive the DL models. We will over come this issue by using innovative data merging approaches to get the best out of the available data.
Line 23: Line 29:
 ===== Project - Deliverables ====== ===== Project - Deliverables ======
-^    ^ Deliverables                                                                                                           +^    ^ Deliverables                                                                                                                                                                                                                                                                             
-| 1  | Multimodal cooperative data fusion methods in the field of environmental sciences that are scalable and transferable +| 1  | Develop methods to fuse data with different spatial and temporal resolutions and eliminate un-needed information                                                                                                                                                                       
-| 2  | Documentation of resultsevaluation, and lessons learned.                                                             | +| 2  | Produce and document a systematic evaluation methodology that quantifies the added-value of each input variable in terms of its contribution to the DL model computational efficiencythe significance of the information it provides, and the overall quality of the DL model output |
-| 3  | Documentation of future work and areas of future enhancement                                                         |+
 ===== Project - Benefits to IAB ===== ===== Project - Benefits to IAB =====
 <WRAP leftalign box > <WRAP leftalign box >
Line 39: Line 44:
 ===== Project - Documents ===== ===== Project - Documents =====
 +{{ :projects:year9:9a.001.ul_cvdi_year_9_final_project_report.pdf |}}\\
 {{ :meetings:spring2021:9a.001.ul_final_update_presentation.pptx |}}\\ {{ :meetings:spring2021:9a.001.ul_final_update_presentation.pptx |}}\\
 {{ :meetings:spring2020:9a.001.ul_year_9_proposed_project_executive_summary.docx |}}\\ {{ :meetings:spring2020:9a.001.ul_year_9_proposed_project_executive_summary.docx |}}\\
projects/year9/9a.001.ul.1620307293.txt.gz · Last modified: 2021/05/06 08:21 by sally.johnson