Mixture tuned matched filtering (MTMF) image classification capitalizes on the increasing spectral and spatial resolutions of available hyperspectral image data to identify the presence, and potentially the abundance, of a given cover type or endmember. Previous studies using MTMF have relied on extensive user input to obtain a reliable classification. In this study, we expand the traditional MTMF classification by using a selection of supervised learning algorithms with rigorous cross-validation. Our approach removes the need for subjective user input to finalize the classification, ultimately enhancing replicability and reliability of the results. We illustrate this approach with an MTMF classification case study focused on leafy spurge (Euphorbia esula), an invasive forb in Western North America, using free 30-m hyperspectral data from the National Aeronautics and Space Administration’s (NASA) Hyperion sensor. Our protocol shows for our data, a potential overall accuracy inflation between 18.4% and 30.8% without cross-validation and according to the supervised learning algorithm used. We propose this new protocol as a final step for the MTMF classification algorithm and suggest future researchers report a greater suite of accuracy statistics to affirm their classifications’ underlying efficacies.

Quantification of small stream contributions to global carbon cycling is key to understanding how freshwater systems transmit and transform carbon between terrestrial and atmospheric pools. To date, greenhouse gas emissions of carbon dioxide and methane from freshwaters, particularly in mountainous regions, remain poorly characterized due to a lack of direct field observations. Using a unique longitudinal approach, we conducted field surveys across two ecoregions (Middle Rockies and Great Plains) in the Clear Creek watershed, a subwatershed of Wyoming's Powder River Basin. We took direct measurements of stream gases using headspace sampling at 30 sites (8 June to 23 October). We observed the lowest and most variable concentrations in headwaters, which flow through a federally designated alpine wilderness area. By contrast, the Great Plains exhibited 1.45 and 4 times higher pCO2 and pCH4 concentrations and the relative contributions of methane increased downstream. Fluxes during snowmelt were 45% and 58% higher for CO2 and CH4 than during base flow but overall were lower than estimates for other systems. Variability for pCO2 was highest during late summer and in the uppermost sections of the headwaters. The high heterogeneity and common undersaturation observed through space and time, especially in the mountains, suggest that downscaled regional estimates may fail to capture variability in fluxes observed at these smaller scales. Based on these results, we strongly recommend higher resolution time series studies and increased scrutiny of systems at near equilibrium, inclusive of winter storage and ice‐off events, to improve our understanding of the effects of seasonal dynamics on these processes.

No abstract

No abstract

No abstract