Landsat-8 and Sentinel-2 based Forest fire burn area mapping using machine learning algorithms on GEE cloud platform over Uttarakhand, Western Himalaya

Abstract The accurate quantitative and qualitative estimation of burn-area are crucial to analyze the impact of fire on forest. The medium resolution optical-satellite imagery of Landsat-8 and Sentinel-2 are employed covering the period 2016 to 2019 for forest fire patches identification on Google Earth Engine (GEE). The most indispensable season of Forest Fire (FF) is pre-monsoon in Uttarakhand, western Himalaya, India. Bi-temporal (pre and post fire) reflectance contrast of burn-sensitive spectral bands was used to compute differential spectral indices, namely, Normalized Burn Ratio (dNBR), Normalized Difference Vegetation Index (dNDVI), Normalized Difference Water Index (dNDWI), and Short-Wave Infrared (dSWIR). The differential spectral-indices composite is further used as an input to unsupervised Weka clustering algorithms for capturing the shape and pattern of fire patches. Sample training-data of burn and unburn classes were collected with reference to thermal and optical spectral principle. Classification Regression Tree (CART), Random Forest (RF), and Support Vector Machine (SVM) algorithms have been employed to identify FF. The key findings revealed that CART and RF algorithms displayed similar forest fire patches with an overall accuracy of 97–100%. The classification accuracy is slightly lower in SVM and its underestimating forest fire patches detections. Landsat-8 OLI derived burn area was fitted better with fire product of Climate Change Initiative (Fire-CCI of ESA) and MCD64A1 of MODIS burn area product with R-square of 0.71–0.93 and 0.62–0.91, respectively which attributed to better spectral bands of Landsat-8 than the Sentinel-2. However, Sentinel-2 bands have the potential to capture fire patches during post-fire events. This study has demonstrated the potential utilities of combined effort of unsupervised and supervised algorithms on Landsat-8 and Sentinel-2 on GEE to identify fire patches.

[1]  S. Escuin,et al.  Fire severity assessment by using NBR (Normalized Burn Ratio) and NDVI (Normalized Difference Vegetation Index) derived from LANDSAT TM/ETM images , 2008 .

[2]  P. Roy.  FOREST FIRE AND DEGRADATION ASSESSMENT USING SATELLITE REMOTE SENSING AND GEOGRAPHIC INFORMATION SYSTEM , 2005 .

[3]  M. Murthy,et al.  Forest fire in India: a review of the knowledge base , 2009, Journal of Forest Research.

[4]  Modes of operation in continuous flow sedimentation of erythrocytes , 1975, Annals of Biomedical Engineering.

[5]  David P. Roy,et al.  Landsat-8 and Sentinel-2 burned area mapping - A combined sensor multi-temporal change detection approach , 2019, Remote Sensing of Environment.

[6]  J. Randerson,et al.  Global fire emissions and the contribution of deforestation, savanna, forest, agricultural, and peat fires (1997-2009) , 2010 .

[7]  B. Gao.  NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space , 1996 .

[8]  B. Wylie,et al.  On the terminology of the spectral vegetation index (NIR − SWIR)/(NIR + SWIR) , 2011 .

[9]  Ana C. L. Sá,et al.  Comparison of burned area estimates derived from SPOT-VEGETATION and Landsat ETM+ data in Africa: Influence of spatial pattern and vegetation type , 2005 .

[10]  Suraj Mal,et al.  Trends and variability of monsoon and other rainfall seasons in Western Himalaya, India , 2014 .

[11]  Tao Dai,et al.  Exploring Weighted Dual Graph Regularized Non-Negative Matrix Tri-Factorization Based Collaborative Filtering Framework for Multi-Label Annotation of Remote Sensing Images , 2019, Remote. Sens..

[12]  A. Kumar,et al.  Forest Fire Burnt Area Assessment in the Biodiversity Rich Regions Using Geospatial Technology: Uttarakhand Forest Fire Event 2016 , 2018, Journal of the Indian Society of Remote Sensing.

[13]  Graeme Newell,et al.  The utility of Random Forests for wildfire severity mapping , 2018, Remote Sensing of Environment.

[14]  M. Wooster,et al.  Fire radiative energy for quantitative study of biomass burning: derivation from the BIRD experimental satellite and comparison to MODIS fire products. , 2003 .

[15]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[16]  Emilio Chuvieco,et al.  A data mining approach for global burned area mapping , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[17]  W. Schroeder,et al.  Assessment of VIIRS 375 m active fire detection product for direct burned area mapping , 2015 .

[18]  P. Baker,et al.  Fire behavior and fire effects across the forest landscape of continental Southeast Asia , 2009 .

[19]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[20]  Emilio Chuvieco,et al.  Earth observation of wildland fires in Mediterranean ecosystems , 2009 .

[21]  David P. Roy,et al.  Separability Analysis of Sentinel-2A Multi-Spectral Instrument (MSI) Data for Burned Area Discrimination , 2016, Remote. Sens..

[22]  S. Plummer,et al.  Generation and analysis of a new global burned area product based on MODIS 250 m reflectance bands and thermal anomalies , 2018, Earth System Science Data.

[23]  Arijit Roy,et al.  Forest fire risk modeling in Uttarakhand Himalaya using TERRA satellite datasets , 2016 .

[24]  C. Justice,et al.  Trends in Vegetation fires in South and Southeast Asian Countries , 2019, Scientific Reports.

[25]  Martin Wild,et al.  Inaugural Article by a Recently Elected Academy Member , 2003 .

[26]  Pascal Lecomte,et al.  The ESA Climate Change Initiative (CCI): A European contribution to the generation of the Global Climate Observing System , 2017 .

[27]  A. Bijalwan,et al.  Forest fire in western Himalayas of India: A Review , 2017 .

[28]  Robert E. Keane,et al.  Challenges of assessing fire and burn severity using field measures, remote sensing and modelling , 2014 .

[29]  W. Parton,et al.  Long- and short-term effects of fire on nitrogen cycling in tallgrass prairie , 1994 .

[30]  Alexei Novikov,et al.  Exploring Google Earth Engine Platform for Big Data Processing: Classification of Multi-Temporal Satellite Imagery for Crop Mapping , 2017, Front. Earth Sci..

[31]  C. Justice,et al.  The quantity of biomass burned in southern Africa , 1996 .

[32]  Baofeng Su,et al.  Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications , 2017, J. Sensors.

[33]  G. Mallinis,et al.  Evaluating and comparing Sentinel 2A and Landsat-8 Operational Land Imager (OLI) spectral indices for estimating fire severity in a Mediterranean pine ecosystem of Greece , 2018 .

[34]  S. Mal,et al.  Changing glacial lakes and associated outburst floods risks in Nanda Devi Biosphere Reserve, Indian Himalaya , 2014 .

[35]  Fusun Balik Sanli,et al.  Comparative Evaluation of the Spectral and Spatial Consistency of Sentinel-2 and Landsat-8 OLI Data for Igneada Longos Forest , 2019, ISPRS Int. J. Geo Inf..

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

[37]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[38]  Frédéric Achard,et al.  Comparing Sentinel-2 MSI and Landsat 8 OLI Imagery for Monitoring Selective Logging in the Brazilian Amazon , 2019, Remote. Sens..

[39]  D. Roy,et al.  The Collection 6 MODIS burned area mapping algorithm and product , 2018, Remote sensing of environment.

[40]  Atul K. Jain,et al.  Development of Decadal (1985-1995-2005) Land Use and Land Cover Database for India , 2015, Remote. Sens..

[41]  Xiaomei Zhang,et al.  30m resolution Global Annual Burned Area Mapping based on Landsat images and Google Earth Engine , 2018, Remote. Sens..

[42]  E. Chuvieco,et al.  Development of a Sentinel-2 burned area algorithm: Generation of a small fire database for sub-Saharan Africa , 2019, Remote Sensing of Environment.

[43]  S. A. Lewis,et al.  Remote sensing techniques to assess active fire characteristics and post-fire effects , 2006 .

[44]  Wen Xiao,et al.  Evaluating the Best Spectral Indices for the Detection of Burn Scars at Several Post-Fire Dates in a Mountainous Region of Northwest Yunnan, China , 2018, Remote. Sens..

[45]  J. Randerson,et al.  Analysis of daily, monthly, and annual burned area using the fourth‐generation global fire emissions database (GFED4) , 2013 .

[46]  B. Duncan,et al.  Vegetation fire emissions and their impact on air pollution and climate , 2009 .

[47]  P. Crutzen,et al.  Biomass burning as a source of atmospheric gases CO, H2, N2O, NO, CH3Cl and COS , 1979, Nature.

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

[49]  M. A. Belenguer-Plomer,et al.  Burned area detection and mapping using Sentinel-1 backscatter coefficient and thermal anomalies , 2019, Remote Sensing of Environment.

[50]  Christopher I. Roos,et al.  Fire in the Earth System , 2009, Science.

[51]  Deborah Lawrence,et al.  Environmental Consequences of the Demise in Swidden Cultivation in Southeast Asia: Carbon Storage and Soil Quality , 2009 .