Assessing Nebraska playa wetland inundation status during 1985–2015 using Landsat data and Google Earth Engine

Tang, Zhenghong; Li, Yao; Gu, Yue; Jiang, Weiguo; Xue, Yuan; Qiao, Huijie; LaGrange, Ted; Bishop, Andy; Drahota, Jeff; Li, Ruopu

doi:10.1007/s10661-016-5664-x

Cited by 74 publications

(41 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NDWI was selected as a complementary model input to the NDVI. Because of its sensitivity to open water [49], the NDWI has been included numerous times in wetland characterization as a means of detecting inundation or separating land from water (e.g., [52][53][54]). …”

Section: Optical Datamentioning

confidence: 99%

Google Earth Engine, Open-Access Satellite Data, and Machine Learning in Support of Large-Area Probabilistic Wetland Mapping

et al. 2017

View full text Add to dashboard Cite

Modern advances in cloud computing and machine-leaning algorithms are shifting the manner in which Earth-observation (EO) data are used for environmental monitoring, particularly as we settle into the era of free, open-access satellite data streams. Wetland delineation represents a particularly worthy application of this emerging research trend, since wetlands are an ecologically important yet chronically under-represented component of contemporary mapping and monitoring programs, particularly at the regional and national levels. Exploiting Google Earth Engine and R Statistical software, we developed a workflow for predicting the probability of wetland occurrence using a boosted regression tree machine-learning framework applied to digital topographic and EO data. Working in a 13,700 km 2 study area in northern Alberta, our best models produced excellent results, with AUC (area under the receiver-operator characteristic curve) values of 0.898 and explained-deviance values of 0.708. Our results demonstrate the central role of high-quality topographic variables for modeling wetland distribution at regional scales. Including optical and/or radar variables into the workflow substantially improved model performance, though optical data performed slightly better. Converting our wetland probability-of-occurrence model into a binary Wet-Dry classification yielded an overall accuracy of 85%, which is virtually identical to that derived from the Alberta Merged Wetland Inventory (AMWI): the contemporary inventory used by the Government of Alberta. However, our workflow contains several key advantages over that used to produce the AMWI, and provides a scalable foundation for province-wide monitoring initiatives.

show abstract

Section: Optical Datamentioning

confidence: 99%

Google Earth Engine, Open-Access Satellite Data, and Machine Learning in Support of Large-Area Probabilistic Wetland Mapping

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The Rainwater Basin region in south-central Nebraska has experienced some of the largest losses of wetlands in the Great Plains (Schildman and Hurt 1984;Bishop and Vrtiska 2008;Nugent et al 2015;Tang et al 2016). Spanning * 15,800 km 2 , the Rainwater Basin region once harbored * 12,000 shallow predominantly wind-formed playa wetlands, ranging from \ 1 to 400 ha, that together formed a complex network of high-density, but spatially-isolated wetlands ( Fig.…”

Section: Introductionmentioning

confidence: 99%

“…1; Frye 1950;Kuzila and Lewis 1993;LaGrange 2005;LaGrange et al 2011). Due to anthropogenic activities, about 80-90% of the historical wetlands in the Rainwater Basin region have been lost or highly altered since European settlement (Schildman and Hurt 1984;Nugent et al 2015;Tang et al 2016). As a result of these wetland losses, wildlife populations in the Rainwater Basin might have become more isolated and could face increased local extinction rates.…”

Section: Introductionmentioning

confidence: 99%

Effects of large-scale wetland loss on network connectivity of the Rainwater Basin, Nebraska

Verheijen

Varner²,

Haukos

2018

Landscape Ecol

View full text Add to dashboard Cite

Context The Rainwater Basin region in south-central Nebraska supports a complex network of spatiallyisolated wetlands that harbor diverse floral and faunal communities. Since European settlement, many wetlands have been lost from the network, which has increased distances among remaining wetlands. As a result, populations of wildlife species with limited dispersal capabilities may have become isolated and face greater local extinction risks. Objectives We compared the pre-European settlement and current extent of the Rainwater Basin network to assess the effects of wetland losses on network connectivity for a range of maximum dispersal distances. Methods We constructed network models for a range of maximum dispersal distances and calculated network metrics to assess changes in network connectivity and the relative importance of individual wetlands in regulating flow. Results Since European settlement, the number of wetlands in the Rainwater Basin has decreased by [ 90%. The average distance to the nearest neighboring wetland has increased by 150% to * 1.2 km, and the dispersal distance necessary to travel throughout the whole network has increased from 3.5 to 10.0 km. Last, relative importance of individual wetlands depended on the maximum dispersal distance. Which wetlands to preserve to maintain connectivity might therefore depend on the dispersal capabilities of the species or taxa of interest. Conclusions To preserve a broad range of biodiversity, conservation efforts should focus on preserving dense clusters of wetlands at fine spatial scales to maintain current levels of network connectivity, and restoring connections between clusters to facilitate long-range dispersal of species with limited dispersal capabilities.

show abstract

“…The LWC was retrieved from the normalized difference spectral indices (NDSI 1370 ), 54 difference spectral indices (DSI 1100 and DSI 1940 ), 54 and modified normalized difference water index (NDWI * ), which is obtained by multiplying the enhanced vegetation index (EVI) and normalized difference water index (NDWI 2500 ). [55][56][57] Specific definitions of the vegetation indices and evaluation indices used are as follows:…”

Section: Evaluation Criteriamentioning

confidence: 99%

Denoising vegetation spectra by combining mathematical-morphology and wavelet-transform-based filters

Zhang

et al. 2019

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Denoising vegetation spectra by combining mathematical-morphology and wavelet-transform-based filters,"Abstract. Spectral noise causes distorted spectra, shifting the central wavelength and thus reducing the accuracy of surface parameter retrieval. A hybrid method combining mathematical-morphology and wavelet-transform (WB)-based filters was used to remove spectral noise. First, a generalized mathematical-morphology (GM) filter was used to remove large-amplitude noise, and then the processed spectra were smoothed using the WT-based filter to remove smallamplitude noise. The simulated noise spectrum and 76 measured canopy spectra for winter wheat were denoised with three filters: the combination filter (CF), GM, and WT. In the simulated experiments, five evaluation indices were calculated to evaluate the denoising effects. For measured spectra, qualitative analyses were performed based on spectral characteristics. Quantitative evaluations were conducted by deriving various vegetation indices from denoised spectra to retrieve wheat's biophysical and biochemical parameters. The results indicated that the CF removed both large-and small-amplitude noise efficiently, improving signal-to-noise ratio and peak signal-to-noise ratio of simulated noise spectrum and retrieval accuracy of leaf water content (LWC) significantly. Meanwhile, it better maintained the waveform and smoothness of spectrum, improving the retrieval accuracies of leaf area index and chlorophyll data slightly. The coefficient of determination (R 2 ) of developed model between the modified normalized difference water index and LWC was improved from 0.428 to 0.622 using the CF, 0.555 using the GM, and 0.549 using the WT. The R 2 and root mean square error between the measured and retrieval LWC were improved from 0.364 and 0.027 to 0.611 and 0.018 using the CF, whereas the corresponding values were 0.504 and 0.022 for the GM, and 0.478 and 0.023 for the WT. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Assessing Nebraska playa wetland inundation status during 1985–2015 using Landsat data and Google Earth Engine

Cited by 74 publications

References 29 publications

Google Earth Engine, Open-Access Satellite Data, and Machine Learning in Support of Large-Area Probabilistic Wetland Mapping

Google Earth Engine, Open-Access Satellite Data, and Machine Learning in Support of Large-Area Probabilistic Wetland Mapping

Effects of large-scale wetland loss on network connectivity of the Rainwater Basin, Nebraska

Denoising vegetation spectra by combining mathematical-morphology and wavelet-transform-based filters

Contact Info

Product

Resources

About