Projecting live fuel moisture content via deep learning
Lynn Miller
A * , Liujun Zhu B , Marta Yebra C D , Christoph Rüdiger E F and Geoffrey I. Webb A G
+ Author Affiliations
- Author Affiliations
A Department of Data Science and Artificial Intelligence, Monash University, Clayton, Vic. 3800, Australia.
B Yangtze Institute for Conservation and Development, Hohai University, Nanjing, 210024, China.
C Fenner School of Environment & Society, Australian National University, ACT 2601, Australia.
D School of Engineering, Australian National University, ACT 2601, Australia.
E Department of Civil Engineering, Monash University, Clayton, Vic. 3800, Australia.
F Science and Innovation Group, Bureau of Meteorology, Melbourne, Vic. 3008, Australia.
G Monash Data Futures Institute, Monash University, Clayton, Vic. 3800, Australia.
* Correspondence to: lynn.miller1@monash.edu
International Journal of Wildland Fire 32(5) 709-727 https://doi.org/10.1071/WF22188
Submitted: 23 August 2022 Accepted: 23 February 2023 Published: 20 March 2023
© 2023 The Author(s) (or their employer(s)). Published by CSIRO Publishing on behalf of IAWF. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND)
Abstract
Background: Live fuel moisture content (LFMC) is a key environmental indicator used to monitor for high wildfire risk conditions. Many statistical models have been proposed to predict LFMC from remotely sensed data; however, almost all these estimate current LFMC (nowcasting models). Accurate modelling of LFMC in advance (projection models) would provide wildfire managers with more timely information for assessing and preparing for wildfire risk.
Aims: The aim of this study was to investigate the potential for deep learning models to predict LFMC across the continental United States 3 months in advance.
Method: Temporal convolutional networks were trained and evaluated using a large database of field measured samples, as well as year-long time series of MODerate resolution Imaging Spectroradiometer (MODIS) reflectance data and Parameter-elevation Relationships on Independent Slopes Model (PRISM) meteorological data.
Key results: The proposed 3-month projection model achieved an accuracy (root mean squared error (RMSE) 27.52%; R2 0.47) close to that of the nowcasting model (RMSE 26.52%; R2 0.51).
Conclusions: The study is the first to predict LFMC with a 3-month lead-time, demonstrating the potential for deep learning models to make reliable LFMC projections.
Implications: These findings are beneficial for wildfire management and risk assessment, showing proof-of-concept for providing advance information useful to help mitigate the effect of catastrophic wildfires.
Keywords: convolutional neural network, deep learning ensembles, fire danger, live fuel moisture content, meteorological data, MODIS, remote sensing, time series analysis.
References
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mané D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viégas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X, Google Research (2015) TensorFlow: large-scale machine learning on heterogeneous distributed systems. Available at www.tensorflow.orgAllen RB, Peet RK, Baker WL (1991) Gradient analysis of latitudinal variation in southern Rocky Mountain forests. Journal of Biogeography 18, 123–139.
| Gradient analysis of latitudinal variation in southern Rocky Mountain forests.Crossref | GoogleScholarGoogle Scholar |
Argañaraz JP, Landi MA, Scavuzzo CM, Bellis LM (2018) Determining fuel moisture thresholds to assess wildfire hazard: a contribution to an operational early warning system. PLoS One 13, e0204889
| Determining fuel moisture thresholds to assess wildfire hazard: a contribution to an operational early warning system.Crossref | GoogleScholarGoogle Scholar |
Ash A, McIntosh P, Cullen B, Carberry P, Smith MS (2007) Constraints and opportunities in applying seasonal climate forecasts in agriculture. Australian Journal of Agricultural Research 58, 952–965.
| Constraints and opportunities in applying seasonal climate forecasts in agriculture.Crossref | GoogleScholarGoogle Scholar |
Beck HE, Zimmermann NE, McVicar TR, Vergopolan N, Berg A, Wood EF (2018) Present and future Köppen–Geiger climate classification maps at 1-km resolution. Scientific Data 5, 180214
| Present and future Köppen–Geiger climate classification maps at 1-km resolution.Crossref | GoogleScholarGoogle Scholar |
Bedia J, Golding N, Casanueva A, Iturbide M, Buontempo C, Gutiérrez JM (2018) Seasonal predictions of Fire Weather Index: paving the way for their operational applicability in Mediterranean Europe. Climate Services 9, 101–110.
| Seasonal predictions of Fire Weather Index: paving the way for their operational applicability in Mediterranean Europe.Crossref | GoogleScholarGoogle Scholar |
Brut A, Rüdiger C, Lafont S, Roujean J-L, Calvet J-C, Jarlan L, Gibelin A-L, Albergel C, Le Moigne P, Soussana J-F, Klumpp K, Guyon D, Wigneron J-P, Ceschia E (2009) Modelling LAI at a regional scale with ISBA-A-gs: comparison with satellite-derived LAI over southwestern France. Biogeosciences 6, 1389–1404.
| Modelling LAI at a regional scale with ISBA-A-gs: comparison with satellite-derived LAI over southwestern France.Crossref | GoogleScholarGoogle Scholar |
Buban MS, Lee TR, Baker CB (2020) A comparison of the U.S. Climate Reference Network precipitation data to the Parameter–Elevation Regressions on Independent Slopes Model (PRISM). Journal of Hydrometeorology 21, 2391–2400.
| A comparison of the U.S. Climate Reference Network precipitation data to the Parameter–Elevation Regressions on Independent Slopes Model (PRISM).Crossref | GoogleScholarGoogle Scholar |
Carroll M, DiMiceli C, Wooten M, Hubbard A, Sohlberg R, Townshend J (2017) MOD44W MODIS/Terra Land Water Mask Derived from MODIS and SRTM L3 Global 250m SIN Grid V006. United States Geological Survey, Sioux Falls, SD, USA.
| Crossref |
Catchpole E, Catchpole W (1991) Modelling moisture damping for fire spread in a mixture of live and dead fuels. International Journal of Wildland Fire 1, 101–106.
| Modelling moisture damping for fire spread in a mixture of live and dead fuels.Crossref | GoogleScholarGoogle Scholar |
Chollet F, et al. (2015) Keras. Available at https://keras.io
Chuvieco E, Aguado I, Dimitrakopoulos AP (2004) Conversion of fuel moisture content values to ignition potential for integrated fire danger assessment. Canadian Journal of Forest Research 34, 2284–2293.
| Conversion of fuel moisture content values to ignition potential for integrated fire danger assessment.Crossref | GoogleScholarGoogle Scholar |
Chuvieco E, Aguado I, Salas J, García M, Yebra M, Oliva P (2020) Satellite remote sensing contributions to wildland fire science and management. Current Forestry Reports 6, 81–96.
| Satellite remote sensing contributions to wildland fire science and management.Crossref | GoogleScholarGoogle Scholar |
Daly C, Halbleib M, Smith JI, Gibson WP, Doggett MK, Taylor GH, Curtis J, Pasteris PP (2008) Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States. International Journal of Climatology 28, 2031–2064.
| Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States.Crossref | GoogleScholarGoogle Scholar |
Daly C, Smith JI, Olson KV (2015) Mapping atmospheric moisture climatologies across the conterminous United States. PLoS One 10, e0141140
| Mapping atmospheric moisture climatologies across the conterminous United States.Crossref | GoogleScholarGoogle Scholar |
Danson FM, Bowyer P (2004) Estimating live fuel moisture content from remotely sensed reflectance. Remote Sensing of Environment 92, 309–321.
| Estimating live fuel moisture content from remotely sensed reflectance.Crossref | GoogleScholarGoogle Scholar |
Dasgupta S, Qu J, Hao X, Bhoi S (2007) Evaluating remotely sensed live fuel moisture estimations for fire behavior predictions in Georgia, USA. Remote Sensing of Environment 108, 138–150.
| Evaluating remotely sensed live fuel moisture estimations for fire behavior predictions in Georgia, USA.Crossref | GoogleScholarGoogle Scholar |
Dennison PE, Moritz MA (2009) Critical live fuel moisture in chaparral ecosystems: a threshold for fire activity and its relationship to antecedent precipitation. International Journal of Wildland Fire 18, 1021–1027.
| Critical live fuel moisture in chaparral ecosystems: a threshold for fire activity and its relationship to antecedent precipitation.Crossref | GoogleScholarGoogle Scholar |
Dennison PE, Moritz MA, Taylor RS (2008) Evaluating predictive models of critical live fuel moisture in the Santa Monica Mountains, California. International Journal of Wildland Fire 17, 18–27.
| Evaluating predictive models of critical live fuel moisture in the Santa Monica Mountains, California.Crossref | GoogleScholarGoogle Scholar |
Dimitrakopoulos AP, Papaioannou KK (2001) Flammability assessment of Mediterranean forest fuels. Fire Technology 37, 143–152.
| Flammability assessment of Mediterranean forest fuels.Crossref | GoogleScholarGoogle Scholar |
European Space Agency (2019) Sentinel Online. European Space Agency, Paris, France. Available at https://sentinel.esa.int/web/sentinel/home
Fox-Hughes P, Yebra M, Kumar V, Dowdy AJ, Hope P, Peace M, Narsey S, Shokirov S, Delage F, Zhang H (2021) Soil and fuel moisture precursors of fire activity during the 2019-20 fire season, in comparison to previous seasons. Bushfire and Natural Hazards CRC, Melbourne, Vic., Australia. Available at https://www.naturalhazards.com.au/research/research-projects/soil-and-fuel-moisture-precursors-fire-activity-during-2019-20-fire
Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R (2017) Google Earth Engine: planetary-scale geospatial analysis for everyone. Remote Sensing of Environment 202, 18–27.
| Google Earth Engine: planetary-scale geospatial analysis for everyone.Crossref | GoogleScholarGoogle Scholar |
Jackson TJ (1993) III. Measuring surface soil moisture using passive microwave remote sensing. Hydrological Processes 7, 139–152.
| III. Measuring surface soil moisture using passive microwave remote sensing.Crossref | GoogleScholarGoogle Scholar |
Jia S, Kim SH, Nghiem SV, Kafatos M (2019) Estimating live fuel moisture using SMAP L-band radiometer soil moisture for Southern California, USA. Remote Sensing 11, 1575
| Estimating live fuel moisture using SMAP L-band radiometer soil moisture for Southern California, USA.Crossref | GoogleScholarGoogle Scholar |
Jurdao S, Chuvieco E, Arevalillo JM (2012) Modelling fire ignition probability from satellite estimates of live fuel moisture content. Fire Ecology 8, 77–97.
| Modelling fire ignition probability from satellite estimates of live fuel moisture content.Crossref | GoogleScholarGoogle Scholar |
Konings AG, Rao K, Steele‐Dunne SC (2019) Macro to micro: microwave remote sensing of plant water content for physiology and ecology. New Phytologist 223, 1166–1172.
| Macro to micro: microwave remote sensing of plant water content for physiology and ecology.Crossref | GoogleScholarGoogle Scholar |
Köppen W (2011) The thermal zones of the Earth according to the duration of hot, moderate and cold periods and to the impact of heat on the organic world. Meteorologische Zeitschrift 20, 351–360.
| The thermal zones of the Earth according to the duration of hot, moderate and cold periods and to the impact of heat on the organic world.Crossref | GoogleScholarGoogle Scholar |
Kottek M, Grieser J, Beck C, Rudolf B, Rubel F (2006) World map of the Köppen–Geiger climate classification updated. Meteorologische Zeitschrift 15, 259–263.
| World map of the Köppen–Geiger climate classification updated.Crossref | GoogleScholarGoogle Scholar |
Lu Y, Wei C (2021) Evaluation of microwave soil moisture data for monitoring live fuel moisture content (LFMC) over the coterminous United States. Science of the Total Environment 771, 145410
| Evaluation of microwave soil moisture data for monitoring live fuel moisture content (LFMC) over the coterminous United States.Crossref | GoogleScholarGoogle Scholar |
Marino E, Yebra M, Guillén-Climent M, Algeet N, Tomé JL, Madrigal J, Guijarro M, Hernando C (2020) Investigating live fuel moisture content estimation in fire-prone shrubland from remote sensing using empirical modelling and RTM simulations. Remote Sensing 12, 2251
| Investigating live fuel moisture content estimation in fire-prone shrubland from remote sensing using empirical modelling and RTM simulations.Crossref | GoogleScholarGoogle Scholar |
McVicar TR, Van Niel TG, Li L, Hutchinson MF, Mu X, Liu Z (2007) Spatially distributing monthly reference evapotranspiration and pan evaporation considering topographic influences. Journal of Hydrology 338, 196–220.
| Spatially distributing monthly reference evapotranspiration and pan evaporation considering topographic influences.Crossref | GoogleScholarGoogle Scholar |
Miller L, Zhu L, Yebra M, Rüdiger C, Webb GI (2022) Multi-modal temporal CNNs for live fuel moisture content estimation. Environmental Modelling & Software 156, 105467
| Multi-modal temporal CNNs for live fuel moisture content estimation.Crossref | GoogleScholarGoogle Scholar |
NASA JPL (2013) NASA Shuttle Radar Topography Mission Global 1 arc second. United States Geological Survey, Sioux Falls, SD, USA.
| Crossref |
NOAA National Centers for Environmental Information (2014) State of the Climate: Monthly National Climate Report for March 2014. National Centers for Environmental Information, Asheville, NC, USA. Available at https://www.ncei.noaa.gov/access/monitoring/monthly-report/national/201403
NOAA National Centers for Environmental Information (2016) State of the Climate: National Climate Report for Annual 2015. National Centers for Environmental Information, Asheville, NC, USA. Available at https://www.ncdc.noaa.gov/sotc/national/201513
NOAA National Centers for Environmental Information (2018a) National Temperature and Precipitation Maps, 2017 anomalies. National Centers for Environmental Information, Asheville, NC, USA. Available at https://www.ncei.noaa.gov/access/monitoring/us-maps/ytd/201712?products[]=tmax-anom&products[]=tmin-anom&products[]=tave-anom&products[]=prcp-diff
NOAA National Centers for Environmental Information (2018b) National Temperature and Precipitation Maps, July – September 2018 anomalies. National Centers for Environmental Information, Asheville, NC, USA. Available at https://www.ncei.noaa.gov/access/monitoring/us-maps/3/201809?products[]=tmax-anom&products[]=tmin-anom&products[]=tave-anom&products[]=prcp-diff
Nolan RH, Foster B, Griebel A, Choat B, Medlyn BE, Yebra M, Younes N, Boer MM (2022) Drought-related leaf functional traits control spatial and temporal dynamics of live fuel moisture content. Agricultural and Forest Meteorology 319, 108941
| Drought-related leaf functional traits control spatial and temporal dynamics of live fuel moisture content.Crossref | GoogleScholarGoogle Scholar |
Park I, Fauss K, Moritz MA (2022) Forecasting live fuel moisture of Adenostema fasciculatum and its relationship to regional wildfire dynamics across Southern California shrublands. Fire 5, 110
| Forecasting live fuel moisture of Adenostema fasciculatum and its relationship to regional wildfire dynamics across Southern California shrublands.Crossref | GoogleScholarGoogle Scholar |
Peel MC, Finlayson BL, McMahon TA (2007) Updated world map of the Köppen–Geiger climate classification. Hydrology and Earth System Sciences 11, 1633–1644.
| Updated world map of the Köppen–Geiger climate classification.Crossref | GoogleScholarGoogle Scholar |
Pelletier C, Webb G, Petitjean F (2019) Temporal convolutional neural network for the classification of satellite image time series. Remote Sensing 11, 523
| Temporal convolutional neural network for the classification of satellite image time series.Crossref | GoogleScholarGoogle Scholar |
Pimont F, Ruffault J, Martin-StPaul NK, Dupuy J-L (2019) Why is the effect of live fuel moisture content on fire rate of spread underestimated in field experiments in shrublands? International Journal of Wildland Fire 28, 127–137.
| Why is the effect of live fuel moisture content on fire rate of spread underestimated in field experiments in shrublands?Crossref | GoogleScholarGoogle Scholar |
Rao K, Williams AP, Flefil JF, Konings AG (2020) SAR-enhanced mapping of live fuel moisture content. Remote Sensing of Environment 245, 111797
| SAR-enhanced mapping of live fuel moisture content.Crossref | GoogleScholarGoogle Scholar |
Roe GH (2005) Orographic precipitation. Annual Review of Earth and Planetary Sciences 33, 645–671.
| Orographic precipitation.Crossref | GoogleScholarGoogle Scholar |
Schaaf C, Wang Z (2015) MCD43A4 MODIS/Terra+Aqua BRDF/Albedo Nadir BRDF-Adjusted Ref Daily L3 Global 500m V006. NASA EOSDIS L. Process. DAAC. United States Geological Survey, Sioux Falls, SD, USA.
| Crossref |
Sharma S, Dhakal K (2021) Boots on the ground and eyes in the sky: a perspective on estimating fire danger from soil moisture content. Fire 4, 45
| Boots on the ground and eyes in the sky: a perspective on estimating fire danger from soil moisture content.Crossref | GoogleScholarGoogle Scholar |
Strahler A, Gopal S, Lambin E, Moody A (1999) MODIS Land Cover Product Algorithm Theoretical Basis Document (ATBD) MODIS Land Cover and Land-Cover Change. National Aeronautics and Space Administration, Washington, DC, USA. Available at http://modis.gsfc.nasa.gov/data/atbd/atbd_mod12.pdf
Swain DL (2021) A shorter, sharper rainy season amplifies California wildfire risk. Geophysical Research Letters 48, e2021GL092843
| A shorter, sharper rainy season amplifies California wildfire risk.Crossref | GoogleScholarGoogle Scholar |
Turco M, Marcos-Matamoros R, Castro X, Canyameras E, Llasat MC (2019) Seasonal prediction of climate-driven fire risk for decision-making and operational applications in a Mediterranean region. Science of the Total Environment 676, 577–583.
| Seasonal prediction of climate-driven fire risk for decision-making and operational applications in a Mediterranean region.Crossref | GoogleScholarGoogle Scholar |
Vinodkumar V, Dharssi I, Yebra M, Fox-Hughes P (2021) Continental-scale prediction of live fuel moisture content using soil moisture information. Agricultural and Forest Meteorology 307, 108503
| Continental-scale prediction of live fuel moisture content using soil moisture information.Crossref | GoogleScholarGoogle Scholar |
Walton D, Hall A (2018) An assessment of high-resolution gridded temperature datasets over California. Journal of Climate 31, 3789–3810.
| An assessment of high-resolution gridded temperature datasets over California.Crossref | GoogleScholarGoogle Scholar |
Weisheimer A, Palmer TN (2014) On the reliability of seasonal climate forecasts. Journal of the Royal Society Interface 11, 20131162
| On the reliability of seasonal climate forecasts.Crossref | GoogleScholarGoogle Scholar |
Westerling AL, Gershunov A, Brown TJ, Cayan DR, Dettinger MD (2003) Climate and wildfire in the Western United States. Bulletin of the American Meteorological Society 84, 595–604.
| Climate and wildfire in the Western United States.Crossref | GoogleScholarGoogle Scholar |
Yebra M, Chuvieco E, Riaño D (2008) Estimation of live fuel moisture content from MODIS images for fire risk assessment. Agricultural and Forest Meteorology 148, 523–536.
| Estimation of live fuel moisture content from MODIS images for fire risk assessment.Crossref | GoogleScholarGoogle Scholar |
Yebra M, Dennison PE, Chuvieco E, Riaño D, Zylstra P, Hunt ER, Danson FM, Qi Y, Jurdao S (2013) A global review of remote sensing of live fuel moisture content for fire danger assessment: moving towards operational products. Remote Sensing of Environment 136, 455–468.
| A global review of remote sensing of live fuel moisture content for fire danger assessment: moving towards operational products.Crossref | GoogleScholarGoogle Scholar |
Yebra M, Quan X, Riaño D, Rozas Larraondo P, van Dijk AIJM, Cary GJ (2018) A fuel moisture content and flammability monitoring methodology for continental Australia based on optical remote sensing. Remote Sensing of Environment 212, 260–272.
| A fuel moisture content and flammability monitoring methodology for continental Australia based on optical remote sensing.Crossref | GoogleScholarGoogle Scholar |
Yebra M, Scortechini G, Badi A, Beget ME, Boer MM, Bradstock R, Chuvieco E, Danson FM, Dennison P, Resco de Dios V, Di Bella CM, Forsyth G, Frost P, Garcia M, Hamdi A, He B, Jolly M, Kraaij T, Martín MP, Mouillot F, Newnham G, Nolan RH, Pellizzaro G, Qi Y, Quan X, Riaño D, Roberts D, Sow M, Ustin S (2019) Globe-LFMC, a global plant water status database for vegetation ecophysiology and wildfire applications. Scientific Data 6, 155
| Globe-LFMC, a global plant water status database for vegetation ecophysiology and wildfire applications.Crossref | GoogleScholarGoogle Scholar |
Zhu L, Webb GI, Yebra M, Scortechini G, Miller L, Petitjean F (2021) Live fuel moisture content estimation from MODIS: a deep learning approach. ISPRS Journal of Photogrammetry and Remote Sensing 179, 81–91.
| Live fuel moisture content estimation from MODIS: a deep learning approach.Crossref | GoogleScholarGoogle Scholar |
