Skip to content

Agriculture Resources

Resources for Proposals in Agriculture 

This document represents a collection of resources from the Technical Advisory Panel as an addition to those referenced in the RFP document. These are intended to provide assistance in obtaining relevant background information, preparing a competitive proposal, and completing quality work. 

These resources are not intended to be exhaustive nor authoritative. This document does not represent an endorsement of work by the Lacuna Fund Secretariat, the TAP, or individual members. 

PREVIOUS WORK AND RELEVANT BACKGROUND 

Relevant recent challenges and other efforts: 

  • Papers from the recent International Conference on Learning Representations (ICLR) Computer Vision 4 Agriculture (CV4A) workshop. 
  • Steffen Fritz et al., “A Global Dataset of Crowdsourced Land Cover and Land Use Reference Data,” Scientific Data 4, no. 1 (December 2017): 170075, https://doi.org/10.1038/sdata.2017.75 
  • Juan Carlos Laso Bayas et al., “A Global Reference Database of Crowdsourced Cropland Data Collected Using the Geo-Wiki Platform,” Scientific Data 4, no. 1 (December 2017): 170136, https://doi.org/10.1038/sdata.2017.136; 
  • IIASA Earth Challenge 2020 (press release). 

PRIVACY AND ETHICS 

  • See Overseas Development Institute’s (ODI) Data Ethics Canvas as a helpful resource to consider ethical issues in a proposed project. 

OTHER RESOURCES ON OPEN DATA INCLUDE: 

  • “Legal and Ethical Issues around Incorporating Traditional Knowledge in Polar Data Infrasrtuctures” Data Science Journal 16(1)pp1-14. 

Although U.S.-oriented, recent work by Trust in Food highlights farmer perspectives related to ground data collection. 

DATA QUALITY 

See the following references for considerations related to data quality: 

  • Pengra, Bruce W., et al. “Quality Control and Assessment of Interpreter Consistency of Annual Land Cover Reference Data in an Operational National Monitoring Program.” Remote Sensing of Environment, Time Series Analysis with High Spatial Resolution Imagery, 238 (March 1, 2020): 111261. https://doi.org/10.1016/j.rse.2019.111261. 
  • Ambica Paliwal and Meha Jain, “The Accuracy of Self-Reported Crop Yield Estimates and Their Ability to Train Remote Sensing Algorithms,” Frontiers in Sustainable Food Systems 4 (2020), https://doi.org/10.3389/fsufs.2020.00025. 
  • Arthur Elmes et al., “Accounting for Training Data Error in Machine Learning Applied to Earth Observations,” Remote Sensing 12, no. 6 (March 23, 2020): 1034, https://doi.org/10.3390/rs12061034. 

Note, these are only a few of many resources in this domain. 

LABELING TOOLS 

The following tools are open source or free to use: 

There are many other available annotation tools, both free and paid, for a variety of purposes. 

CATALOGING TOOLS 

The following tools are designed to make it easy to create SpatioTemporal Asset Catalog (STAC) metadata: 

  • PySTAC – Catalog generation to the latest STAC specification. 
  • Stac-Browser – Python package to browse created STAC catalogs. 

DATA SHARING 

Global Open Data for Agriculture and Nutrition network (GODAN) resources on data standards: 

  • Pesce, Valeria, Jeni Tennison, Lisette Mey, Clement Jonquet, Anne Toulet, Sophie Aubin, and Panagiotis Zervas. “A Map of Agri-Food Data Standards.” F1000Research 7 (February 12, 2018). https://doi.org/10.7490/f1000research.1115260.1. 

PUBLIC WEBINARS