NA24OARX021G0004
Project Grant
Overview
Grant Description
Purpose: Much of the US coastal zone is covered in a veneer of mobile sediment, and the size of this sediment determines under what conditions it moves.
Accurate measurement of coastal sediment grain size is critical for work on coastal erosion, shoreline change, total water level forecasting, storm impact predictions, planning, designing nature-based coastal protections, and other coastal resilience projects.
Measurement of grain size is time consuming, costly, and requires a laboratory.
Inaccurate measurements result in degraded performance of models, plans, predictions, and forecasts.
To address slow measurement speed and high cost-per-sample, we have built a new handheld camera-based system that uses on-device machine learning, does not require calibration, and provides accurate field measurements of grain size within 1 second, ~1,000,000x faster than lab quotes of 2 weeks.
We propose three research objectives to dramatically improve the performance of our technology for coastal sites of the US, regardless of sediment size, distribution, color, and composition:
First, field collections to grow our training dataset;
Second, machine learning model development to increase performance and reduce training data requirements;
Third, targeted work to determine presence and percentage of specific minerals used for some coastal projects.
We anticipate the proposed work will lead to the development of a device that:
1) Can accurately measure all types of sediment present along the continental US coastline;
2) Contains a new pretrained machine learning model - made using weak supervision - that will improve model results;
And 3) Detects the presence and weight percentage of specific minerals used in some coastal projects.
Quantitative metrics will allow us to measure the success of each research objective.
The implication of the proposed work is the development of a new instrument able to measure sediment grain size quickly and accurately in the field at any US coastal location.
Customer discovery work from 150+ interviews suggests:
1) A field device for grain size measurement is an innovation that will compress project timelines, reduce costs (labor, subcontracting, lab services), and enable rapid in-house field monitoring;
2) This device will be transformative for industries tasked with measuring and monitoring, such as coastal engineering firms, coastal restoration outfits, geotechnical firms, and local, state, federal agencies.
Our innovation will compress project timelines, reduce costs (labor, subcontracting), and enable rapid in-house field analysis for coastal restoration and engineering firms and local, state, and federal agencies.
Accurate measurement of coastal sediment grain size is critical for work on coastal erosion, shoreline change, total water level forecasting, storm impact predictions, planning, designing nature-based coastal protections, and other coastal resilience projects.
Measurement of grain size is time consuming, costly, and requires a laboratory.
Inaccurate measurements result in degraded performance of models, plans, predictions, and forecasts.
To address slow measurement speed and high cost-per-sample, we have built a new handheld camera-based system that uses on-device machine learning, does not require calibration, and provides accurate field measurements of grain size within 1 second, ~1,000,000x faster than lab quotes of 2 weeks.
We propose three research objectives to dramatically improve the performance of our technology for coastal sites of the US, regardless of sediment size, distribution, color, and composition:
First, field collections to grow our training dataset;
Second, machine learning model development to increase performance and reduce training data requirements;
Third, targeted work to determine presence and percentage of specific minerals used for some coastal projects.
We anticipate the proposed work will lead to the development of a device that:
1) Can accurately measure all types of sediment present along the continental US coastline;
2) Contains a new pretrained machine learning model - made using weak supervision - that will improve model results;
And 3) Detects the presence and weight percentage of specific minerals used in some coastal projects.
Quantitative metrics will allow us to measure the success of each research objective.
The implication of the proposed work is the development of a new instrument able to measure sediment grain size quickly and accurately in the field at any US coastal location.
Customer discovery work from 150+ interviews suggests:
1) A field device for grain size measurement is an innovation that will compress project timelines, reduce costs (labor, subcontracting, lab services), and enable rapid in-house field monitoring;
2) This device will be transformative for industries tasked with measuring and monitoring, such as coastal engineering firms, coastal restoration outfits, geotechnical firms, and local, state, federal agencies.
Our innovation will compress project timelines, reduce costs (labor, subcontracting), and enable rapid in-house field analysis for coastal restoration and engineering firms and local, state, and federal agencies.
Awardee
Funding Goals
18 CLIMATE ADAPTATION AND MITIGATION 19 WEATHER-READY NATION 20 HEALTHY OCEANS 21 RESILIENT COASTAL COMMUNITIES AND ECONOMIES
Grant Program (CFDA)
Awarding / Funding Agency
Place of Performance
Greensboro,
North Carolina
274011753
United States
Geographic Scope
Single Zip Code
Related Opportunity
Sediment was awarded
Project Grant NA24OARX021G0004
worth $174,693
from National Oceanic and Atmospheric Administration in August 2024 with work to be completed primarily in Greensboro North Carolina United States.
The grant
has a duration of 5 months and
was awarded through assistance program 11.021 NOAA Small Business Innovation Research (SBIR) Program.
The Project Grant was awarded through grant opportunity NOAA SBIR FY 2024 Phase I.
SBIR Details
Research Type
SBIR Phase I
Title
Measuring coastal sediment grain size instantly using Instagrain, a hand-held camera with on-device machine learning
Abstract
Much of the US coastal zone is covered in a veneer of mobile sediment, and the size of this sediment determines under what conditions it moves. Accurate measurement of coastal sediment grain size is critical for work on coastal erosion, shoreline change, total water level forecasting, storm impact predictions, planning, designing nature-based coastal protections, and other coastal resilience projects. Measurement of grain size is time consuming, costly, and requires a laboratory. Inaccurate measurements result in degraded performance of models, plans, predictions, and forecasts. To address slow measurement speed and high cost-per-sample, we have built a new handheld camera-based system that uses on-device machine learning, does not require calibration, and provides accurate field measurements of grain size within 1 second, ~1,000,000x faster than lab quotes of 2 weeks. We propose three research objectives to dramatically improve the performance of our technology for coastal sites of the US, regardless of sediment size, distribution, color, and composition: First, field collections to grow our training dataset; Second, machine learning model development to increase performance and reduce training data requirements; Third, targeted work to determine presence and percentage of specific minerals used for some coastal projects.
Topic Code
9.2
Solicitation Number
NOAA-OAR-TPO-2024-2008184
Status
(Complete)
Last Modified 2/19/25
Period of Performance
8/1/24
Start Date
1/31/25
End Date
Funding Split
$174.7K
Federal Obligation
$0.0
Non-Federal Obligation
$174.7K
Total Obligated
Activity Timeline
Transaction History
Modifications to NA24OARX021G0004
Additional Detail
Award ID FAIN
NA24OARX021G0004
SAI Number
NA24OARX021G0004-002
Award ID URI
None
Awardee Classifications
Small Business
Awarding Office
1305N2 DEPT OF COMMERCE NOAA
Funding Office
1333BR OFC OF PROG.PLANNING&INTEGRATION
Awardee UEI
NJJPKBT9JNK7
Awardee CAGE
None
Performance District
NC-06
Senators
Thom Tillis
Ted Budd
Ted Budd
Modified: 2/19/25