From d1be0697c4690535da76288410ee21fc02a60b26 Mon Sep 17 00:00:00 2001 From: ejm714 Date: Fri, 25 Oct 2024 10:00:20 -0700 Subject: [PATCH] add acknowledgements --- papers/emily_dorne/main.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/papers/emily_dorne/main.md b/papers/emily_dorne/main.md index f364486ba5..c53249cbf0 100644 --- a/papers/emily_dorne/main.md +++ b/papers/emily_dorne/main.md @@ -588,6 +588,14 @@ As decision-makers begin experimenting with CyFi, we recommend calculating histo CyFi is a powerful tool for identifying high and low levels of cyanobacteria, and enables humans to make more timely and targeted decisions when issuing public health guidance around current cyanobacteria levels. Areas with low-density cyanobacteria counts can be excluded from ground sampling to better prioritize limited resources, while areas with high-density cyanobacteria counts can be prioritized for public health action. The development of CyFi illustrates the utility of machine learning competitions as a first step toward open source tools. CyFi's primary use cases show how machine learning can be incorporated into human workflows to enable more efficient and more informed decision making. +# Acknowledgements + +This project was supported by funding from National Aeronautics and Space Administration Science Mission Directorate's Earth Science Applied Sciences, Health and Air Quality, and the NASA Prizes, Challenges, and Crowdsourcing Programs. The project was led by DrivenData and managed by the NASA Tournament Lab, part of the Prizes, Challenges, and Crowdsourcing Program in NASA's Space Technology Mission Directorate for the NASA Open Innovation Services 2 (NOIS2) contract 80JSC020D0041. + +The authors express their gratitude to collaborators, advisors, and data providers at the following organizations, whose support made this study possible: National Oceanic and Atmospheric Administration, Environmental Protection Agency, Alaska Department of Environmental Conservation, Arizona Department of Environmental Quality, Bureau of Water Kansas Department of Health and Environment, California Environmental Data Exchange Network, Centers for Disease Control and Prevention, Connecticut State Department of Public Health, Delaware National Resources and the University of Delaware's Citizen Monitoring Program, EPA Central Data Exchange, EPA National Aquatic Research Survey, EPA Ohio, EPA Water Quality Data Portal, Indiana State Department of Health, Iowa Department of Natural Resources, Louisiana Department of Environmental Quality, Maine Bureau of Water Quality - Division of Environmental Assessment, N.C. Division of Water Resources N.C. Department of Environmental Quality, New Jersey Department of Environmental Protection, New Mexico Environment Department, New York State Department of Environmental Protection, North Dakota Department of Environmental Quality, Pennsylvania Department of Environmental Protection, Rhode Island Department of Environmental Management - Office of Water Resources, South Carolina Department of Health and Environmental Control, State of Georgia - Environmental Protection Division, State of Michigan - Lake Michigan Unit - Surface Water Assessment Section - Water Resources Division - Department of Environment Great Lakes and Energy, Tennessee Department of Environment and Conservation, Texas Commission on Environmental Quality, UMRBA (Upper Mississippi River Basin Association), US Army Corps of Engineers, USGS Water Quality Data Portal - Harmful Algal Bloom Science in Texas, Utah Department of Environmental Quality - Division of Water Quality, Vermont Department of Health - Health and the Environment, Virginia Department of Health, West Virginia Department of Environmental Protection, Wisconsin Department of Natural Resources, Wyoming Department of Environmental Quality. The authors would like to thank Yang Xu, Andrew Wheeler, and Raphael Kimina, the Tick Tick Bloom competition winners whose modeling approaches provided the foundation for CyFi. The authors also thank the reviewers who provided constructive comments and suggestions to improve the quality of the manuscript. + +Correspondence regarding the CyFi Python package should be directed to Emily Dorne at emily@drivendata.org. Correspondence regarding this open innovation project should be directed to Shobhana Gupta at shobhana.gupta@nasa.gov. Correspondence regarding the NASA Tournament Lab should be directed to Ryon Stewart at ryon.stewart@nasa.gov. Mention of trade names or commercial products does not constitute endorsement or recommendation for use by the US Government. The views expressed in this article are those solely of the authors and do not necessarily reflect the views or policies of the US Government. + [^footnote-1]: @ttb_results [^footnote-2]: The authors would like to thank Yang Xu, Andrew Wheeler, and Raphael Kimina, the Tick Tick Bloom competition winners whose modeling approaches provided the foundation for CyFi. [^footnote-3]: The success of decision tree models in the Tick Tick Bloom competition is consistent with other DrivenData competitions where the task was point-based prediction from satellite imagery (i.e., estimating the [amount of water in snowpack](https://github.com/drivendataorg/snowcast-showdown) and estimating [levels of air pollution](https://github.com/drivendataorg/nasa-airathon/tree/main/pm25)).