Submission information
Submission Number: 67
Submission ID: 98
Submission UUID: 26bdb683-607b-4cce-b447-41aeb596aa91
Submission URI: /form/project
Created: Fri, 09/18/2020 - 16:59
Completed: Fri, 09/18/2020 - 17:05
Changed: Thu, 11/18/2021 - 09:27
Remote IP address: 132.198.130.210
Submitted by: Jarlath O'Neil-Dunne
Language: English
Is draft: No
Webform: Project
| Project Title | Deep Learning High-Resolution Land Cover Mapping for Vermont |
|---|---|
| Program | Northeast |
| Project Leader | Jarlath O'Neil-Dunne |
| joneildu@uvm.edu | |
| Mobile Phone | 802-598-9668 |
| Work Phone | 802-656-3324 |
| Mentor(s) | Keri Toksu |
| Student-facilitator(s) | Jackson Schilling |
| Mentee(s) | |
| Project Description | Executive Summary Funding is requested from the Northeast CyberTeam to support an undergraduate intern who will help advance remote sensing deep learning workflows supporting Vermont’s high-resolution land cover initiative. The internship will be based out of the University of Vermont Spatial Analysis Laboratory (SAL) and supervised by SAL Director and faculty member Jarlath O’Neil-Dunne. This internship will make extensive use of the Vermont Advanced Computing Core (VACC), particularly the DeepGreen GPU cluster. Background The State of Vermont is under both regulatory and public pressure to improve the water quality of Lake Champlain. State agencies must have access to high-resolution land cover information that is detailed enough to provide parcel-level quantification of land cover features. The University of Vermont, with funding from the State of Vermont, led the development of the 2016 statewide, high-resolution land cover dataset. This 2016 land cover dataset is the most accurate, detailed, and comprehensive land cover map ever made of Vermont. The existing workflows employed to develop this land cover dataset are slow and expensive, running on individual desktop computer workstations. Moreover, the land cover dataset was already out of date the moment it was produced. In February 2020, a meeting was held consisting of the state agency representatives, the Vermont Advanced Computing Core, and the Spatial Analysis Laboratory. State agencies voiced their desire to have an approach to land cover mapping that would allow for more rapid updates of high-resolution land cover products, and that would capture fine-scale changes that could influence water quality, such as the construction of a new building. Activity This project will focus on integrating deep learning approaches into the SAL’s feature extraction workflows. Deep learning has shown tremendous potential for mapping land cover from high-resolution remotely sensed datasets. Deep learning techniques by themselves may not always be optimal for updating existing land cover datasets as false change can result in differences stemming from the source data or errors in the mapping itself. We propose to leverage deep learning to more efficiently update the Sate’s high-resolution land cover maps through a hybrid approach. Our desire is to take advantage of the potential that deep learning offers while still employing the methodologies that ensure quality specifications are met. The goal of this hybrid approach is to have a faster, more efficient, and more accurate approach to updating existing high-resolution land cover products. High-performance computing will be employed to tackle the most computationally intensive aspects of deep learning, the model training process. These models will then be integrated into the existing workflows to produce areas showing areas of change, and the existing high-resolution land cover to enable rapid updating of the statewide landcover data set. This project will leverage the University of Vermont’s recent investments in high-performance computing architecture. Deep Green, an NSF-funded supercomputer, will be employed. The phases for this project are: 1) deep learning system design, 2) deep learning system development, 3) deep learning system implementation, 4) integration of deep learning into object-based feature extraction workflow, 5) production of an updated statewide land cover map. The software technologies employed will include TensorFlow and eCognition for feature extraction and ArcGIS for visualization. This project is incredibly valuable to the state of Vermont as the State is struggling to meet regulatory requirements to reduce non-point source pollution to Lake Champlain, the state’s largest lake that extends into New York and Quebec. Access to current, accurate high-resolution land cover is imperative if the State is going to make decisions on how to reduce non-point source pollution best and fund these activities. Furthermore, the State has no dedicated remote sensing scientists on staff and lacks the computing and technical resources to carry out land cover mapping on this scale. The intern funded as part of this project will work with a talented team that consists of individuals who are internationally recognized for their expertise in automated feature extraction. |
| Project Deliverables | 1) Model for deep learning high-resolution land cover mapping. 2) Updated Vermont statewide high-resolution land cover dataset |
| Project Deliverables | |
| Student Research Computing Facilitator Profile | Jackson Schilling Jackson is an undergraduate student who has worked in the Spatial Analysis Laboratory for nearly a year. He has experience with GIS, image processing, scripting using Python, and an introductory knowledge of deep learning workflows. |
| Mentee Research Computing Profile | |
| Student Facilitator Programming Skill Level | Practical applications |
| Mentee Programming Skill Level | |
| Project Institution | University of Vermont |
| Project Address | 81 Carrigan Drive Burlington, Vermont. 05405 |
| Anchor Institution | NE-University of Vermont |
| Preferred Start Date | 10/01/2020 |
| Start as soon as possible. | No |
| Project Urgency | Already behind3Start date is flexible |
| Expected Project Duration (in months) | |
| Launch Presentation | |
| Launch Presentation Date | |
| Wrap Presentation | |
| Wrap Presentation Date | |
| Project Milestones |
|
| Github Contributions | |
| Planned Portal Contributions (if any) | Model documentation |
| Planned Publications (if any) | The dataset will be published to the Vermont Open Geospatial Data Portal |
| What will the student learn? | How to design, develop, and deploy deep learning for statewide land cover mapping. |
| What will the mentee learn? | |
| What will the Cyberteam program learn from this project? | The challenges associated with integrating deep learning into remote sensing workflows and how the resulting products are received by stakeholders. |
| HPC resources needed to complete this project? | DeepGreen - UVM's GPU cluster. |
| Notes | |
| What is the impact on the development of the principal discipline(s) of the project? | |
| What is the impact on other disciplines? | Land cover mapping is used for a variety of domains from land cover mapping to urban planning. By reducing the cost of land cover mapping, this project provided efficiencies to other disciplines. |
| Is there an impact physical resources that form infrastructure? | No. |
| Is there an impact on the development of human resources for research computing? | This project established procedures that allow non-experts to apply deep learning approaches to land cover mapping. |
| Is there an impact on institutional resources that form infrastructure? | No |
| Is there an impact on information resources that form infrastructure? | No |
| Is there an impact on technology transfer? | Technology transfer was an important part of this project. The workflows and methodologies were developed to allow for those with a background in geospatial technology but with limited AI expertise, to deploy deep learning technology for land cover mapping. |
| Is there an impact on society beyond science and technology? | This project generated data that is helping to drive resource management decisions in Vermont around the areas of stormwater runoff and forest fragmentation. |
| Lessons Learned | Deep learning technology has tremendous potential for land cover mapping but employing the technology requires substantial expertise and experience in the field of artificial intelligence. This barrier can be substantially lowered by developing standardized workflows that enable those with a strong foundation in geospatial technology to harness the power of deep learning for land cover mapping. |
| Overall results | This project developed methodologies and workflows for using deep learning for high-resolution land cover mapping. These outputs are being used to further land cover mapping in Vermont by personnel without extensive AI expertise. |