Fully Automated Countrywide Monitoring of Fuel Break Maintenance Operations

Fuel break (FB) networks are strategic locations for fire control and suppression. In order to be effective for wildfire control, they need to be maintained through regular interventions to reduce fuel loads. In this paper, we describe a monitoring system relying on Earth observations to detect fuel reduction inside the FB network being implemented in Portugal. Two fast automated pixel-based methodologies for monthly monitoring of fuel removals in FB are developed and compared. The first method (M1) is a classical supervised classification using the difference and postdisturbance image of monthly image composites. To take into account the impact of different land cover and phenology in the detection of fuel treatments, a second method (M2) based on an innovative statistical change detection approach was developed. M2 explores time series of vegetation indices and does not require training data or user-defined thresholds. The two algorithms were applied to Sentinel-2 10 m bands and fully processed in the cloud-based platform Google Earth Engine. Overall, the unsupervised M2, which is based on a Welch t-test of two moving window averages, gives better results than the supervised M1 and is suitable for an automated countrywide fuel treatment detection. For both methods, two vegetation indices, the Modified Excess of Green and the Normalized Difference Vegetation Index, were compared and exhibited similar performances.

[1]  Camia Andrea,et al.  Modeling the impacts of climate change on forest fire danger in Europe: Sectorial results of the PESETA II Project , 2017 .

[2]  José M. C. Pereira,et al.  A patch-based algorithm for global and daily burned area mapping , 2019, Remote Sensing of Environment.

[3]  Alan A. Ager,et al.  Assessing the effect of a fuel break network to reduce burnt area and wildfire risk transmission , 2016 .

[4]  Stuart R. Phinn,et al.  Mapping woody vegetation clearing in Queensland, Australia from Landsat imagery using the Google Earth Engine , 2015 .

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

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

[7]  Olga Viedma,et al.  Changes in landscape fire-hazard during the second half of the 20th century: Agriculture abandonment and the changing role of driving factors , 2015 .

[8]  Edward Jones,et al.  A survey of image processing techniques for plant extraction and segmentation in the field , 2016, Comput. Electron. Agric..

[9]  Christian Ginzler,et al.  Regional Scale Mapping of Grassland Mowing Frequency with Sentinel-2 Time Series , 2018, Remote. Sens..

[10]  Duarte Oom,et al.  Spatiotemporal trends of area burnt in the Iberian Peninsula, 1975–2013 , 2018, Regional Environmental Change.

[11]  Alexandra D. Syphard,et al.  Factors affecting fuel break effectiveness in the control of large fires on the Los Padres National Forest, California , 2011 .

[12]  João M. N. Silva,et al.  Temporal dynamics of spectral bioindicators evidence biological and ecological differences among functional types in a cork oak open woodland , 2016, International Journal of Biometeorology.

[13]  Xavier P. Burgos-Artizzu,et al.  Real-time image processing for crop / weed discrimination in maize fields , 2012 .

[14]  B. Holben.  Characteristics of maximum-value composite images from temporal AVHRR data , 1986 .

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

[16]  Nicholas J. Tate,et al.  A critical synthesis of remotely sensed optical image change detection techniques , 2015 .

[17]  Rita Almeida Ribeiro,et al.  Semi-Automatic Methodology for Fire Break Maintenance Operations Detection with Sentinel-2 Imagery and Artificial Neural Network , 2020, Remote. Sens..

[18]  Marijke Elisabeth Bekkema,et al.  Mapping Grassland Management Intensity Using Sentinel-2 Satellite Data , 2018 .

[19]  Trevor Hastie,et al.  A statistical explanation of MaxEnt for ecologists , 2011 .

[20]  Guiying Li,et al.  Current situation and needs of change detection techniques , 2014 .

[21]  Liangyun Liu,et al.  Continuous Change Detection of Forest/Grassland and Cropland in the Loess Plateau of China Using All Available Landsat Data , 2018, Remote. Sens..