Cropland Classification Algorithms.
Contracting Office Address
USGS OAG SACRAMENTO ACQUISITION BR. MODOC HALL, CSUS 3020 STATE UNIVERSITY DRIVE EAST SACRAMENTO CA 95819-6027 US
Cropland Classification Algorithms: The U.S. Geological Survey (USGS) is conducting market research to determine the availability of qualified businesses capable of providing the creation of consistent and accurate global food security support-analysis data (GFSAD) at fine spatial resolution, at not more than 30m resolution. This sources sought announcement is not a request for quote or proposal and the Government is not committed to award of a purchase order or contract pursuant to this announcement. The information resulting from this market research is simply for planning purposes to assist the Government in determining its acquisition strategy. The Government will not pay for any costs incurred in the preparation of information for responding to this notice. The North American Industry Classification System (NAICS) code 541715, Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology) and associated size standard 1,000 Employees applies to this announcement. All responsible sources may submit a brochure and/or technical specifications detailing the ability of their services to meet the minimum requirements included with this announcement. All responses shall be limited to 10 pages. Responses to this announcement shall only be accepted through electronic mail addressed to firstname.lastname@example.org and must be uploaded and received in their entirety no later than 07/31/2018. Responses submitted by hardcopy or the FedConnect web portal or the FedConnect Message Center shall not be accepted or considered. At a minimum, potential contractors must be able to produce GFSAD models, maps, and monitoring tools using machine learning algorithms (MLAs) on cloud computing platforms with the ability to handle multi-satellite, multi-sensor remotely sensed big-data, leading to a comprehensive set of 30-m or better cropland products in support of ensuring global food security by developing multiple cropland mapping algorithms (CMAs) that include multiple mature MLAs such as spectral matching techniques (SMTs), random forest, and support vector machines. Using Google Earth Engine (GEE), identify the following for the entire world at 30-m or better: 1. Irrigated versus rain-fed; 2. Cropping intensities; 3. 11 major crop types; and 4. Croplands versus cropland fallow to allow for accurate Hind-casting, Now-casting, and Future-casting real and potential food supply support analysis data derived from satellites such as Landsat, and Sentinels.
Original Point of Contact
POC Evans, Stewart
Place of Performance
Link: FBO.gov Permalink
Bookmark This Notice