Diversity of Algorithm and Spectral Band Inputs Improves Landsat Monitoring of Forest Disturbance

Disturbance monitoring is an important application of the Landsat times series, both to monitor forest dynamics and to support wise forest management at a variety of spatial and temporal scales. In the last decade, there has been an acceleration in the development of approaches designed to put the Landsat archive to use towards these causes. Forest disturbance mapping has moved from using individual change-detection algorithms, which implement a single set of decision rules that may not apply well to a range of scenarios, to compiling ensembles of such algorithms. One approach that has greatly reduced disturbance detection error has been to combine individual algorithm outputs in Random Forest (RF) ensembles trained with disturbance reference data, a process called stacking (or secondary classification). Previous research has demonstrated more robust and sensitive detection of disturbance using stacking with both multialgorithm ensembles and multispectral ensembles (which make use of a single algorithm applied to multiple spectral bands). In this paper, we examined several additional dimensions of this problem, including: (1) type of algorithm (represented by processes using one image per year vs. all historical images); (2) spectral band choice (including both the basic Landsat reflectance bands and several popular indices based on those bands); (3) number of algorithm/spectral-band combinations needed; and (4) the value of including both algorithm and spectral band diversity in the ensembles. We found that ensemble performance substantially improved per number of model inputs if those inputs were drawn from a diversity of both algorithms and spectral bands. The best models included inputs from both algorithms, using different variants of shortwave-infrared (SWIR) and near-infrared (NIR) reflectance. Further disturbance detection improvement may depend upon the development of algorithms which either interrogate SWIR and NIR in new ways or better highlight disturbance signals in the visible wavelengths.

[1]  Suming Jin,et al.  Completion of the 2011 National Land Cover Database for the Conterminous United States – Representing a Decade of Land Cover Change Information , 2015 .

[2]  Makoto Inoue,et al.  Valuing forest ecosystem services: What we know and what we don't , 2013 .

[3]  Ernawati,et al.  Protective functions and ecosystem services of global forests in the past quarter-century , 2015 .

[4]  Hideki Kobayashi,et al.  Relationship between spatio-temporal characteristics of leaf-fall phenology and seasonal variations in near surface- and satellite-observed vegetation indices in a cool-temperate deciduous broad-leaved forest in Japan , 2014 .

[5]  Nicholas C. Coops,et al.  Imaging Phenology; Scaling From Camera Plots to Landscapes , 2016 .

[6]  Martha C. Anderson,et al.  Landsat-8: Science and Product Vision for Terrestrial Global Change Research , 2014 .

[7]  C. Woodcock,et al.  Continuous change detection and classification of land cover using all available Landsat data , 2014 .

[8]  Jan Pisek,et al.  Separating overstory and understory leaf area indices for global needleleaf and deciduous broadleaf forests by fusion of MODIS and MISR data , 2016 .

[9]  Valerie A. Thomas,et al.  On-the-Fly Massively Multitemporal Change Detection Using Statistical Quality Control Charts and Landsat Data , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[10]  W. Cohen,et al.  Spatial and temporal patterns of forest disturbance and regrowth within the area of the Northwest Forest Plan , 2012 .

[11]  Zhiqiang Yang,et al.  Continuous monitoring of land disturbance based on Landsat time series , 2020, Remote Sensing of Environment.

[12]  Mark A. Friedl,et al.  Multi-criteria evaluation of the suitability of growth functions for modeling remotely sensed phenology , 2016 .

[13]  Martha C. Anderson,et al.  Free Access to Landsat Imagery , 2008, Science.

[14]  Zhiqiang Yang,et al.  Detecting trends in forest disturbance and recovery using yearly Landsat time series: 1. LandTrendr — Temporal segmentation algorithms , 2010 .

[15]  Zhe Zhu,et al.  Mapping forest change using stacked generalization: An ensemble approach , 2018 .

[16]  Heiko Balzter,et al.  Forest fire scar detection in the boreal forest with multitemporal SPOT-VEGETATION data , 2003, IEEE Trans. Geosci. Remote. Sens..

[17]  P. Beck,et al.  Understanding the temporal dimension of the red-edge spectral region for forest decline detection using high-resolution hyperspectral and Sentinel-2a imagery , 2018, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[18]  Chengquan Huang,et al.  Conservation policy and the measurement of forests , 2016 .

[19]  Teng-Chiu Lin,et al.  Remote sensing assessment of forest damage in relation to the 1996 strong typhoon Herb at Lienhuachi Experimental Forest, Taiwan , 2008 .

[20]  Samia Boukir,et al.  Exploring diversity in ensemble classification: Applications in large area land cover mapping , 2017 .

[21]  Miina Rautiainen,et al.  Seasonal changes in canopy leaf area index and MODIS vegetation products for a boreal forest site in central Finland , 2012 .

[22]  Zhe Zhu,et al.  Change detection using landsat time series: A review of frequencies, preprocessing, algorithms, and applications , 2017 .

[23]  M. Ozdogan.  A Practical and Automated Approach to Large Area Forest Disturbance Mapping with Remote Sensing , 2014, PloS one.

[24]  Robert E. Wolfe,et al.  A Landsat surface reflectance dataset for North America, 1990-2000 , 2006, IEEE Geoscience and Remote Sensing Letters.

[25]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[26]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[27]  R. Houghton,et al.  A role for tropical forests in stabilizing atmospheric CO 2 , 2015 .

[28]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[29]  Chengquan Huang,et al.  Forest disturbance across the conterminous United States from 1985-2012: The emerging dominance of forest decline , 2016 .

[30]  Claire Stewart,et al.  The exceptional value of intact forest ecosystems , 2018, Nature Ecology & Evolution.

[31]  Zhiqiang Yang,et al.  A LandTrendr multispectral ensemble for forest disturbance detection , 2018 .

[32]  Eric P. Crist,et al.  A Physically-Based Transformation of Thematic Mapper Data---The TM Tasseled Cap , 1984, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Evan B. Brooks,et al.  How Similar Are Forest Disturbance Maps Derived from Different Landsat Time Series Algorithms , 2017 .

[34]  Joanne C. White,et al.  Forest Monitoring Using Landsat Time Series Data: A Review , 2014 .

[35]  Warren B. Cohen,et al.  Detecting trends in forest disturbance and recovery using yearly Landsat time series: 2. TimeSync — Tools for calibration and validation , 2010 .

[36]  S. Frolking,et al.  Forest disturbance and recovery: A general review in the context of spaceborne remote sensing of impacts on aboveground biomass and canopy structure , 2009 .

[37]  P. Atkinson,et al.  Remote sensing of mangrove forest phenology and its environmental drivers , 2018 .

[38]  C. J. Whitaker,et al.  Ten measures of diversity in classifier ensembles: limits for two classifiers , 2001 .

[39]  Zhe Zhu,et al.  Automated cloud, cloud shadow, and snow detection in multitemporal Landsat data: An algorithm designed specifically for monitoring land cover change , 2014 .

[40]  Zhe Zhu,et al.  Current status of Landsat program, science, and applications , 2019, Remote Sensing of Environment.

[41]  Sassan Saatchi,et al.  Remote Sensing Assessment of Forest Disturbance across Complex Mountainous Terrain: The Pattern and Severity of Impacts of Tropical Cyclone Yasi on Australian Rainforests , 2014, Remote. Sens..