You are here:
Report on approaches to predicting probability of cyanobacteria blooms or related indices based on nutrient inputs and other ecosystem attributes in lakes
Citation:
Kreakie, B., Jeff Hollister, AND Bryan Milstead. Report on approaches to predicting probability of cyanobacteria blooms or related indices based on nutrient inputs and other ecosystem attributes in lakes. U.S. Environmental Protection Agency, Washington, DC, 2015.
Impact/Purpose:
This website will be the APR for SSWR 2.3c. It will be an SSWR public website to summarize and present all research conducted for SSWR 2.3c
Description:
Despite a lengthy history of research on cyanobacteria, many important questions about this diverse group of aquatic, photosynthetic “blue-green algae” remain unanswered. For example, how can we more accurately predict cyanobacteria blooms in freshwater systems? Which lakes have elevated risks for such blooms? And what characteristics mark areas with high risks for cyanobacteria blooms? These are important questions, and our work is an attempt to move us closer to finding answers to some of these questions.There are numerous viable modes of research that can be applied to cyanobacteria research. Our research specifically follows a computation ecology research mode that is heavily entrenched in an ethos of open science. More explicitly our approaches tend to be computational demanding and machine-learning based. We rely on large (both in size and spatial extent) data sets to extract information about water quality and related indicators. Additionally, all aspects of our research are open and freely available to the public; including our data, code and final formalized products. In accordance with this philosophy, this website is an effort to publically present all our recent research on approaches for predicting indices of cyanobacteria
URLs/Downloads:
PREDICTING_INDICES.PDF (PDF, NA pp, 536.847 KB, about PDF)https://github.com/USEPA/modelling_hab_indices