Application of Landsat ETM+ and OLI Data for Foliage Fuel Load Monitoring Using Radiative Transfer Model and Machine Learning Method

Foliage fuel load (FFL) is a critical factor affecting crown fire intensity and rate of spread. Satellite observations provide the potential for monitoring FFL dynamics across large areas. Previous studies commonly used empirical methods to estimate FFL, which potentially lacks reproducibility. This study applied Landsat 7 ETM+ and 8 OLI data for FFL retrieval using radiative transfer model (RTM) and machine learning method. To this end, the GeoSail, SAIL, and PROSPECT RTMs were first coupled together to model the near-realistic scenario of a two-layered forest structure. Second, available ecological information was applied to constrain the coupled RTM modeling phases in order to decrease the probability of generating unrealistic simulations. Third, the coupled RTMs were linked to three machine learning models—random forest, support vector machine, and multilayer perceptron—as well as the traditional lookup table. Finally, the performance of each method was validated by FFL measurements from Southwest China and Sweden. The resulting multilayer perceptron (R2 = 0.77, RMSE = 0.13, and rRMSE = 0.43) outperformed the other three methods. The evaluation of the applicability of the FFL estimates was conducted in a southwest China forest where two occurred in 2014 and 2020. The FFL dynamics from 2013 through 2020 showed that the fire was likely to occur when the FFL accumulated to a critical point (around 27 × 106 kg), highlighting the relevance of remote sensing derived FFL estimates for understanding potential fire occurrence.

[1]  E. Chuvieco.  Wildland Fire Danger Estimation and Mapping: The Role of Remote Sensing Data , 2003 .

[2]  Marco Assis Borges,et al.  Fuel load mapping in the Brazilian Cerrado in support of integrated fire management , 2018, Remote Sensing of Environment.

[3]  R. Houborg,et al.  Combining vegetation index and model inversion methods for the extraction of key vegetation biophysical parameters using Terra and Aqua MODIS reflectance data , 2007 .

[4]  M. Schlerf,et al.  Inversion of a forest reflectance model to estimate structural canopy variables from hyperspectral remote sensing data , 2006 .

[5]  P. Bicheron.  A Method of Biophysical Parameter Retrieval at Global Scale by Inversion of a Vegetation Reflectance Model , 1999 .

[6]  W. Verhoef.  Light scattering by leaf layers with application to canopy reflectance modelling: The SAIL model , 1984 .

[7]  Emilio Chuvieco,et al.  Linking ecological information and radiative transfer models to estimate fuel moisture content in the Mediterranean region of Spain: Solving the ill-posed inverse problem , 2009 .

[8]  Luca Martino,et al.  Joint Gaussian Processes for Biophysical Parameter Retrieval , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[9]  S. Ustin,et al.  Estimating Vegetation Water content with Hyperspectral data for different Canopy scenarios: Relationships between AVIRIS and MODIS Indexes , 2006 .

[10]  T. Loboda,et al.  Mapping fractional cover of major fuel type components across Alaskan tundra , 2019, Remote Sensing of Environment.

[11]  N. Goel,et al.  Needle chlorophyll content estimation through model inversion using hyperspectral data from boreal conifer forest canopies , 2004 .

[12]  Emilio Chuvieco,et al.  Regional estimation of woodland moisture content by inverting Radiative Transfer Models , 2013 .

[13]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[14]  A. Dijk,et al.  Forest fire fuel through the lens of remote sensing: Review of approaches, challenges and future directions in the remote sensing of biotic determinants of fire behaviour , 2021 .

[15]  Xing Li,et al.  A radiative transfer model-based method for the estimation of grassland aboveground biomass , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[16]  Petar M. Djuric,et al.  Gaussian sum particle filtering , 2003, IEEE Trans. Signal Process..

[17]  S. Liang,et al.  Retrieving leaf area index using a genetic algorithm with a canopy radiative transfer model , 2003 .

[18]  Juan de la Riva,et al.  An insight into machine-learning algorithms to model human-caused wildfire occurrence , 2014, Environ. Model. Softw..

[19]  Ömer Küçük,et al.  Estimating crown fuel loading for calabrian pine and Anatolian black pine , 2008 .

[20]  Nicholas Skowronski,et al.  Remotely sensed measurements of forest structure and fuel loads in the Pinelands of New Jersey , 2007 .

[21]  Martha C. Anderson,et al.  Utility of an image-based canopy reflectance modeling tool for remote estimation of LAI and leaf chlorophyll content at the field scale , 2009 .

[22]  Laurie A. Chisholm,et al.  Monitoring live fuel moisture content of heathland, shrubland and sclerophyll forest in south-eastern Australia using MODIS data , 2012 .

[23]  C. E. Van Wagner,et al.  Conditions for the start and spread of crown fire , 1977 .

[24]  Ioannis Mitsopoulos,et al.  Allometric equations for crown fuel biomass of Aleppo pine (Pinus halepensis Mill.) in Greece , 2007 .

[25]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[26]  J. Storey,et al.  LANDSAT 7 SCAN LINE CORRECTOR-OFF GAP-FILLED PRODUCT DEVELOPMENT , 2005 .

[27]  Sassan Saatchi,et al.  Estimation of Forest Fuel Load From Radar Remote Sensing , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Bunkei Matsushita,et al.  Sensitivity of the Enhanced Vegetation Index (EVI) and Normalized Difference Vegetation Index (NDVI) to Topographic Effects: A Case Study in High-Density Cypress Forest , 2007, Sensors.

[29]  Thuy Le Toan,et al.  Biosar 2008: Data Acquisition and Processing Report , 2009 .

[30]  P. Zarco-Tejada,et al.  Chlorophyll content estimation in an open-canopy conifer forest with Sentinel-2A and hyperspectral imagery in the context of forest decline , 2019, Remote sensing of environment.

[31]  F. M. Danson,et al.  Multispectral and LiDAR data fusion for fuel type mapping using Support Vector Machine and decision rules , 2011 .

[32]  David Riaño,et al.  A fuel moisture content and flammability monitoring methodology for continental Australia based on optical remote sensing , 2018, Remote Sensing of Environment.

[33]  G. Camps-Valls,et al.  A Survey on Gaussian Processes for Earth-Observation Data Analysis: A Comprehensive Investigation , 2016, IEEE Geoscience and Remote Sensing Magazine.

[34]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[35]  A. Kuusk.  The Hot Spot Effect in Plant Canopy Reflectance , 1991 .

[36]  Hanyu Shi,et al.  Exploration of Machine Learning Techniques in Emulating a Coupled Soil–Canopy–Atmosphere Radiative Transfer Model for Multi-Parameter Estimation From Satellite Observations , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Craig S. T. Daughtry,et al.  Towards estimation of canopy foliar biomass with spectral reflectance measurements , 2011 .

[38]  M. Yebra,et al.  The Vegetation Structure Perpendicular Index (VSPI): A forest condition index for wildfire predictions , 2019, Remote Sensing of Environment.

[39]  F. M. Danson,et al.  Sensitivity of spectral reflectance to variation in live fuel moisture content at leaf and canopy level , 2004 .

[40]  Binbin He,et al.  Chlorophyll content estimation in arid grasslands from Landsat-8 OLI data , 2016 .

[41]  Giorgos Mallinis,et al.  Canopy Fuel Load Mapping of Mediterranean Pine Sites Based on Individual Tree-Crown Delineation , 2013, Remote. Sens..

[42]  E. Bilgili,et al.  Canopy Fuel Characteristics and Fuel Load in Young Black Pine Trees , 2007 .

[43]  P. Curran,et al.  LIBERTY—Modeling the Effects of Leaf Biochemical Concentration on Reflectance Spectra , 1998 .

[44]  Emilio Chuvieco,et al.  Short-term assessment of burn severity using the inversion of PROSPECT and GeoSail models , 2009 .

[45]  F. M. Danson,et al.  A global review of remote sensing of live fuel moisture content for fire danger assessment: Moving t , 2013 .

[46]  Jindi Wang,et al.  Development of the Adjoint Model of a Canopy Radiative Transfer Model for Sensitivity Study and Inversion of Leaf Area Index , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[47]  A. Skidmore,et al.  Inversion of a radiative transfer model for estimating vegetation LAI and chlorophyll in a heterogeneous grassland , 2008 .

[48]  M. Hardisky.  The Influence of Soil Salinity, Growth Form, and Leaf Moisture on-the Spectral Radiance of Spartina alterniflora Canopies , 2008 .

[49]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[50]  R. Keane,et al.  Mapping wildland fuels for fire management across multiple scales: Integrating remote sensing, GIS, and biophysical modeling , 2001 .

[51]  Sildomar T. Monteiro,et al.  Gaussian Processes for Vegetation Parameter Estimation from Hyperspectral Data with Limited Ground Truth , 2019, Remote. Sens..

[52]  Kate Brandis,et al.  Estimation of vegetative fuel loads using Landsat TM imagery in New South Wales, Australia , 2003 .

[53]  Francis Eng Hock Tay,et al.  Support vector machine with adaptive parameters in financial time series forecasting , 2003, IEEE Trans. Neural Networks.

[54]  S. Running,et al.  Global products of vegetation leaf area and fraction absorbed PAR from year one of MODIS data , 2002 .

[55]  Guang-Bin Huang,et al.  Extreme Learning Machine for Multilayer Perceptron , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[56]  Robin M. Reich,et al.  Spatial models for estimating fuel loads in the Black Hills, South Dakota, USA , 2004 .

[57]  D. Riaño,et al.  Estimation of live fuel moisture content from MODIS images for fire risk assessment , 2008 .

[58]  Sen Jin,et al.  Application of QuickBird imagery in fuel load estimation in the Daxinganling region, China , 2012 .

[59]  Pedro A. Hernandez-Leal,et al.  Fusion of WorldView-2 and LiDAR Data to Map Fuel Types in the Canary Islands , 2016, Remote. Sens..

[60]  Jan G. P. W. Clevers,et al.  Experimental Sentinel-2 LAI estimation using parametric, non-parametric and physical retrieval methods - A comparison , 2015 .

[61]  R. Myneni,et al.  Investigation of a model inversion technique to estimate canopy biophysical variables from spectral and directional reflectance data , 2000 .

[62]  Hang Zhou,et al.  Deep learning based multi-temporal crop classification , 2019, Remote Sensing of Environment.

[63]  Xin Jia,et al.  Stem, branch and leaf biomass-density relationships in forest communities , 2012, Ecological Research.

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

[65]  Pablo J. Zarco-Tejada,et al.  Estimation of fuel moisture content by inversion of radiative transfer models to simulate equivalent water thickness and dry matter content: analysis at leaf and canopy level , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[66]  Rocío Hernández-Clemente,et al.  Determination of forest fuels characteristics in mortality-affected Pinus forests using integrated hyperspectral and ALS data , 2018, International Journal of Applied Earth Observation and Geoinformation.

[67]  S. Ustin,et al.  Multi-temporal vegetation canopy water content retrieval and interpretation using artificial neural networks for the continental USA , 2008 .

[68]  S. Ustin,et al.  Estimation of water-related biochemical and biophysical vegetation properties using multitemporal airborne hyperspectral data and its comparison to MODIS spectral response , 2014 .

[69]  W. Verhoef.  Theory of radiative transfer models applied in optical remote sensing of vegetation canopies , 1998 .

[70]  Emilio Chuvieco,et al.  Generation of a Species-Specific Look-Up Table for Fuel Moisture Content Assessment , 2009, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[71]  Rafael Molina,et al.  Deep Gaussian processes for biogeophysical parameter retrieval and model inversion , 2020, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[72]  Futao Guo,et al.  What drives forest fire in Fujian, China? Evidence from logistic regression and Random Forests , 2016 .

[73]  S. Tarantola,et al.  Designing a spectral index to estimate vegetation water content from remote sensing data: Part 1 - Theoretical approach , 2002 .

[74]  Chuli Hu,et al.  Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach , 2019, Remote Sensing of Environment.

[75]  Shobha Kondragunta,et al.  Estimating forest biomass in the USA using generalized allometric models and MODIS land products , 2006 .

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

[77]  F. Baret,et al.  Improving canopy variables estimation from remote sensing data by exploiting ancillary information. Case study on sugar beet canopies , 2002 .

[78]  A. Gitelson,et al.  Vegetation and soil lines in visible spectral space: A concept and technique for remote estimation of vegetation fraction , 2002 .

[79]  John R. Miller,et al.  Assessing vineyard condition with hyperspectral indices: Leaf and canopy reflectance simulation in a row-structured discontinuous canopy , 2005 .

[80]  Hua Shi,et al.  Assessment of Fire Fuel Load Dynamics in Shrubland Ecosystems in the Western United States Using MODIS Products , 2020, Remote. Sens..

[81]  Yuri Knyazikhin,et al.  Retrieval of canopy biophysical variables from bidirectional reflectance Using prior information to solve the ill-posed inverse problem , 2003 .

[82]  Yu Li,et al.  Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network , 2019, Remote Sensing of Environment.

[83]  K. Huemmrich.  The GeoSail model: a simple addition to the SAIL model to describe discontinuous canopy reflectance , 2001 .

[84]  Roberta E. Martin,et al.  PROSPECT-4 and 5: Advances in the leaf optical properties model separating photosynthetic pigments , 2008 .

[85]  Gustau Camps-Valls,et al.  A global canopy water content product from AVHRR/Metop , 2020, 2012.10397.

[86]  Joe H. Scott,et al.  Assessing Crown Fire Potential by Linking Models of Surface and Crown Fire Behavior , 2003 .

[87]  W. Verhoef,et al.  Coupled soil–leaf-canopy and atmosphere radiative transfer modeling to simulate hyperspectral multi-angular surface reflectance and TOA radiance data , 2007 .

[88]  Luis Alonso,et al.  Optimizing LUT-Based RTM Inversion for Semiautomatic Mapping of Crop Biophysical Parameters from Sentinel-2 and -3 Data: Role of Cost Functions , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[89]  James S. Gould,et al.  Quantifying fine fuel dynamics and structure in dry eucalypt forest (Eucalyptus marginata) in Western Australia for fire management , 2011 .

[90]  E. Reinhardt,et al.  Analysis of algorithms for predicting canopy fuel , 2003 .

[91]  B. Pinty,et al.  GEMI: a non-linear index to monitor global vegetation from satellites , 1992, Vegetatio.

[92]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[93]  Xing Li,et al.  Retrieval of forest fuel moisture content using a coupled radiative transfer model , 2017, Environ. Model. Softw..

[94]  Luis Guanter,et al.  Estimating Crop Primary Productivity with Sentinel-2 and Landsat 8 using Machine Learning Methods Trained with Radiative Transfer Simulations , 2019, Remote Sensing of Environment.