You are here:
Machine Learning Tools for Predicting Freshwater Fish Populations (ICRW7 Proceedings)
Citation:
Patton, Douglas A, M. Cyterski, D. Smith, K. Wolfe, B. Rashleigh, JohnM Johnston, AND R. Parmar. Machine Learning Tools for Predicting Freshwater Fish Populations (ICRW7 Proceedings). In Proceedings, Seventh Interagency Conference on Research in the Watersheds (ICRW7), Tifton, GA, November 16 - 19, 2020. USDA Forest Service, 147, (2022). https://doi.org/10.2737/SRS-GTR-264
Impact/Purpose:
Advancing Watershed Science using Machine Learning, Diverse Data, and Mechanistic Modeling
Description:
To address the lack of publicly available fish community data for most of US lotic freshwater habitats we develop scientific software modules and databases for predicting fish populations by NHDPlus (National Hydrography Dataset) ComId (Common Identifier) segment. We build predictive models of fish species presence in freshwater streams in CONUS using several customized Scikit-learn (Pedregosa and others 2011) machine learning pipelines. The dataset derives from EPA, USGS, and state agency records and contains 565 fish species observed through electrofishing in 28,519 stream segments identified by their NHDplus ComId sampling locations. We use the observations of fish to develop a binary dataset for each species, labeling as present(1) each species found at least once by electrofishing in sampled ComIds. Then for each species, we use the collection of HUC8’s where that species may be found and we label the remaining sampled ComIds as absent(0). To describe the catchment where each sampled ComId is located, we develop a set of 270 predictor variables for each sampled catchment by condensing the full collection of Streamcat metrics (Hill and others 2016) with operations such as: retaining only an average of each landcover time series, dropping older iterations of multi-version metrics, and dropping meta-data variables.
URLs/Downloads:
DOI: Machine Learning Tools for Predicting Freshwater Fish Populations (ICRW7 Proceedings)
https://www.fs.usda.gov/research/treesearch/64307#