Integrating Remotely Sensed Imagery and Existing Multiscale Field Data to Derive Rangeland Indicators: Application of Bayesian Additive Regression Trees

McCord, Sarah E.; Buenemann, Michaela; Karl, Jason W.; Browning, Dawn M.; Hadley, Brian

doi:10.1016/j.rama.2017.02.004

Cited by 31 publications

(21 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The errors are equivalent or lower than RMSEs from similar efforts to map continuous rangeland cover, where McCord et al. () used a Bayesian additive regression tree and reported RMSEs ranging from 11% to 14% for BG, herbaceous, and shrub classes, and Xian et al. () used regression tree modeling and reported errors ranging from 9.7% to 14.4% for AFG, SHR, and BG classes.…”

Section: Resultsmentioning

confidence: 93%

“…Examination of errors between the ranger and EE RF model implementations showed minimal disparity with no error difference greater than 0.5% between the two implementations. The errors are equivalent or lower than RMSEs from similar efforts to map continuous rangeland cover, where McCord et al (2017) used a Bayesian additive regression tree and reported RMSEs ranging from 11% to 14% for BG, herbaceous, and shrub classes, and Xian et al (2013) used regression tree modeling and reported errors ranging from 9.7% to 14.4% for AFG, SHR, and BG classes.…”

Section: Validation and Error Metricsmentioning

confidence: 82%

“…The integration of PFT maps into agency (i.e., BLM, NRCS, and USFS) specific programs and future strategies enhances broad‐scale evaluation of rangeland core indicators (McCord et al. ). Our work highlights the importance of large‐scale systematic monitoring programs like the NRCS NRI and BLM AIM, which provided essential field plot data in the creation of these cover maps; future support for additional field plot data will increase samples and likely improve overall model accuracy and prediction.…”

Section: Resultsmentioning

confidence: 99%

“…, McCord et al. ), but challenges have remained as the geographic area and time period of interest increased data volume and computational processing, both becoming significant barriers to implementation. The increased availability and use of high‐performance cloud computing, storage, and services removes such barriers.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Innovation in rangeland monitoring: annual, 30 m, plant functional type percent cover maps for U.S. rangelands, 1984–2017

et al. 2018

View full text Add to dashboard Cite

Innovations in machine learning and cloud‐based computing were merged with historical remote sensing and field data to provide the first moderate resolution, annual, percent cover maps of plant functional types across rangeland ecosystems to effectively and efficiently respond to pressing challenges facing conservation of biodiversity and ecosystem services. We utilized the historical Landsat satellite record, gridded meteorology, abiotic land surface data, and over 30,000 field plots within a Random Forests model to predict per‐pixel percent cover of annual forbs and grasses, perennial forbs and grasses, shrubs, and bare ground over the western United States from 1984 to 2017. Results were validated using three independent collections of plot‐level measurements, and resulting maps display land cover variation in response to changes in climate, disturbance, and management. The maps, which will be updated annually at the end of each year, provide exciting opportunities to expand and improve rangeland conservation, monitoring, and management. The data open new doors for scientific investigation at an unprecedented blend of temporal fidelity, spatial resolution, and geographic scale.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Validation and Error Metricsmentioning

confidence: 82%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Innovation in rangeland monitoring: annual, 30 m, plant functional type percent cover maps for U.S. rangelands, 1984–2017

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Representative networks inform more comprehensively on long term change over large areas without bias to particular systems. They have been implemented effectively to provide spatial surveys of above-and belowground biodiversity (Bastin et al 2017;Lemetre et al 2017;Baruch et al 2018), and to monitor ecosystem condition in relation to disturbance, land use and climate change (Hoekman et al, 2017;McCord et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Stocktaking the environmental coverage of a continental ecosystem observation network

Guerin

Williams

Sparrow

et al. 2020

Preprint

View full text Add to dashboard Cite

Field-based sampling of terrestrial habitats at continental scales is required to build ecosystem observation networks. However, a key challenge for detecting change in ecosystem composition, structure and function is to obtain a representative sample of habitats. Representative sampling contributes to ecological validity when analysing large spatial surveys, but field resources are limited and representativeness may differ markedly from purely practical sampling strategies to statistically rigorous ones. Here, we report a post hoc assessment of the coverage of environmental gradients as a surrogate for ecological coverage by a continental-scale survey of the Australian Terrestrial Ecosystem Research Network (TERN). TERN's surveillance program maintains a network of ecosystem observation plots that were init ially established in the rangelands through a stratification method (clustering of bioregions by environment) and Ausplots methodology. Subsequent site selection comprised gap filling combined with opportunistic sampling. Firstly, we confirmed that environmental coverage has been a good surrogate for ecological coverage. The cumulative sampling of environments and plant species composition over time were strongly correlated (based on mean multivariate dispersion; r = 0.93). We then compared the environmental sampling of Ausplots to 100,000 background points and a set of retrospective (virtual) sampling schemes: systematic grid, simple random, stratified random, and generalised random-tessellation stratified (GRTS). Differences were assessed according to sampling densities along environmental gradients, and multivariate dispersion (environmental space represented via multi-dimensional scaling). Ausplots outperformed systematic grid, simple random and GRTS in coverage of environmental space (Tukey HSD of mean dispersion, p < .001). GRTS site selection obtained similar coverage to Ausplots when employing the same bioregional stratification. Stratification by climatic zones generated the highest environmental coverage (p < .001), but the resulting sampling densities over-represented mesic coastal habitats. The Ausplots stratification by bioregions implemented under practical constraints represented complex environments well compared to statistically oriented or spatially even samples. However, potential statistical inference and power also depend on spatial and temporal replication, unbiased site selection, and accurate field measurements relative to the magnitude of change. A key conclusion is that environmental, rather than spatial, stratification is required to maximise ecological coverage across continental ecosystem observation networks.

show abstract

Pre‐fire vegetation drives post‐fire outcomes in sagebrush ecosystems: evidence from field and remote sensing data

et al. 2019

View full text Add to dashboard Cite

Understanding the factors that influence vegetation responses to disturbance is important because vegetation is the foundation of food resources, wildlife habitat, and ecosystem properties and processes. We integrated vegetation cover data derived from field plots and remotely sensed Landsat images in two focal areas over a 37-yr period to investigate how historical changes to community composition influence contemporary responses of vegetation to fire in sagebrush ecosystems in the Great Basin. Our objectives were (1) to quantify the magnitude and direction of change in the cover of native and exotic plant functional groups in relation to their exposure to fire; (2) to relate plant community changes to their historical composition, exposure to fire, and environmental conditions; and (3) to test for consistency of trends revealed by vegetation cover data derived from field plots and Landsat images. Historical (1979Historical ( -1981 field data originated from 298 locations, Landsat-derived data and contemporary (2011-2016) field data originated from 448 locations, and an expanded set of locations were included in some analyses of Landsat-derived data. We found that areas burned by fire since the 1980s had higher annual herbaceous cover than unburned areas both historically and contemporarily. Models revealed a significant interaction between historical community composition and exposure to fire, which suggests that plots with historically high herbaceous cover were more susceptible to burning. Trends revealed by field and Landsat-derived cover data were only partially consistent, potentially due in part to methods used to predict cover values from Landsat images, and the time period over which each data set was collected. Our results suggest that burned areas historically occupied by sagebrush-dominated plant communities may have been invaded by exotic annuals prior to burning, possibly because of prior land uses, and after burning, have now transitioned to a persistent herbaceous-dominated state. This type of state transition has important consequences for forage quality, wildlife habitat, soil nutrients, and future disturbances, such as drought and wildfire.

show abstract

Integrating Remotely Sensed Imagery and Existing Multiscale Field Data to Derive Rangeland Indicators: Application of Bayesian Additive Regression Trees

Cited by 31 publications

References 41 publications

Innovation in rangeland monitoring: annual, 30 m, plant functional type percent cover maps for U.S. rangelands, 1984–2017

Innovation in rangeland monitoring: annual, 30 m, plant functional type percent cover maps for U.S. rangelands, 1984–2017

Stocktaking the environmental coverage of a continental ecosystem observation network

Pre‐fire vegetation drives post‐fire outcomes in sagebrush ecosystems: evidence from field and remote sensing data

Contact Info

Product

Resources

About