气候变化领域集成服务门户(CCPortal): Mapping thins to identify active forest management in southern pine plantations using Landsat time series stacks

CCPortal

DOI	10.1016/j.rse.2020.112127
	Mapping thins to identify active forest management in southern pine plantations using Landsat time series stacks
	Thomas V.A.; Wynne R.H.; Kauffman J.; McCurdy W.; Brooks E.B.; Thomas R.Q.; Rakestraw J.
发表日期	2021
ISSN	00344257
卷号	252
英文摘要	The southeastern United States is unique in terms of both the intensity and scale of forest management, which includes substantial thinning and other forms of harvesting. Because thinning is not a land use transition, and the disturbance signal is relatively subtle compared to a clear cut, there is a dearth of studies that attempt to detect thinning over large areas. Our goal was to detect pine thins as an indicator of active forest management using Landsat data. Areas which undergo thinning are indicative of active forest management in the region. Our approach uses a machine learning method which combines first-order harmonics and metrics from 3-year Fourier regression of Landsat time series stacks, layers from the Global Forest Change product, and other vetted national products into a random forests model to classify forest thins in the southeastern US. Forest Harvest Inspection Records for Virginia were used for training and validation. Models were successful separating thins from clear cuts and non-harvested pines (overall accuracy 86%, clear cut accuracy 90%, thin accuracy 83% for a simplified 10-predictor variable model). Examination of variable importance illustrates the physical meaning behind the models. The curve fit statistics (R2 or RMSE) of the NDVI, Pan, and SWIR1 harmonic curve fits, which are an indication of a departure from typical vegetation phenology caused by thinning or other disturbances, were consistently among the top predictors. The harmonic regression constant, sine and cosine from the Landsat 8 panchromatic band were also important. These describe the visible reflectance (500–680 nm) phenology over the time period at a high spatial resolution (15 m). The Loss Year from the Global Forest Change product, which is an indication of stand replacing disturbance, was also consistently among the most important variables in the classifiers. High performance computing, such as Google Earth Engine, and analysis-ready data are important for this approach. This work has importance for quantification of actively managed forests in a region of the world where production forestry is the dominant land disturbance signal and a significant economic engine. © 2020 Elsevier Inc.
英文关键词	Forest management monitoring; Harmonic regression; Land cover; Land management; Mitigation; Multitemporal; Silviculture
语种	英语
scopus关键词	Biology; Curve fitting; Decision trees; Engines; Fourier series; Harmonic analysis; Harvesting; Land use; Learning systems; Time series; Turing machines; Harmonic regression; High performance computing; High spatial resolution; Landsat time series; Machine learning methods; Variable importances; Vegetation phenology; Visible reflectance; Forestry; coniferous tree; forest management; Landsat; mapping method; phenology; satellite imagery; spatial resolution; time series analysis; Accuracy; Biology; Engines; Forest Management; Forestry; Harvesting; Land Use; Thinning; United States; Virginia; Pinus echinata
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/179073
作者单位	Department of Forest Resources and Environmental Conservation, Virginia Tech, Blacksburg, VA 24061, United States; Conservation Management Institute, Department of Fish and Wildlife Conservation, Virginia Tech, Blacksburg, VA 24061, United States; International Paper, Inc., 6400 Poplar Ave, Memphis, TN 38197, United States
推荐引用方式 GB/T 7714	Thomas V.A.,Wynne R.H.,Kauffman J.,et al. Mapping thins to identify active forest management in southern pine plantations using Landsat time series stacks[J],2021,252.
APA	Thomas V.A..,Wynne R.H..,Kauffman J..,McCurdy W..,Brooks E.B..,...&Rakestraw J..(2021).Mapping thins to identify active forest management in southern pine plantations using Landsat time series stacks.Remote Sensing of Environment,252.
MLA	Thomas V.A.,et al."Mapping thins to identify active forest management in southern pine plantations using Landsat time series stacks".Remote Sensing of Environment 252(2021).