Premium
Aggregate Measures of Watershed Health from Reconstructed Water Quality Data with Uncertainty
Author(s) -
Hoque Yamen M.,
Tripathi Shivam,
Hantush Mohamed M.,
Govindaraju Rao S.
Publication year - 2016
Publication title -
journal of environmental quality
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.888
H-Index - 171
eISSN - 1537-2537
pISSN - 0047-2425
DOI - 10.2134/jeq2015.10.0508
Subject(s) - aggregate (composite) , principal component analysis , dimensionality reduction , watershed , data mining , data set , curse of dimensionality , statistics , series (stratigraphy) , mathematics , computer science , artificial intelligence , machine learning , geology , paleontology , materials science , composite material
Risk‐based measures such as reliability, resilience, and vulnerability (R‐R‐V) have the potential to serve as watershed health assessment tools. Recent research has demonstrated the applicability of such indices for water quality (WQ) constituents such as total suspended solids and nutrients on an individual basis. However, the calculations can become tedious when time‐series data for several WQ constituents have to be evaluated individually. Also, comparisons between locations with different sets of constituent data can prove difficult. In this study, data reconstruction using a relevance vector machine algorithm was combined with dimensionality reduction via variational Bayesian noisy principal component analysis to reconstruct and condense sparse multidimensional WQ data sets into a single time series. The methodology allows incorporation of uncertainty in both the reconstruction and dimensionality‐reduction steps. The R‐R‐V values were calculated using the aggregate time series at multiple locations within two Indiana watersheds. Results showed that uncertainty present in the reconstructed WQ data set propagates to the aggregate time series and subsequently to the aggregate R‐R‐V values as well. This data‐driven approach to calculating aggregate R‐R‐V values was found to be useful for providing a composite picture of watershed health. Aggregate R‐R‐V values also enabled comparison between locations with different types of WQ data. Core Ideas Multidimensional WQ data were aggregated into one‐dimensional time series. Aggregate data retained information in original data sets; data uncertainty was quantified. Risk‐based indices have potential to serve as watershed health assessment tools. Indices calculated from aggregate data and uncertainty showed overall watershed health.