Burned Area Mapping of an Escaped Fire into Tropical Dry Forest in Western Madagascar Using Multi-Season Landsat OLI Data

Axel, Anne C.

doi:10.3390/rs10030371

Cited by 26 publications

(28 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MODIS data with 1-km spatial resolution were processed by geometric correction to the map projection of transverse Mercator and to obtain the geographic location information. Then we carried out radiometric calibration [28] and atmospheric correction [47] to obtain the data of reflectance and emissivity using ENVI software. Afterward, brightness temperature (BT) and LST data were generated by the split-window algorithm [48].…”

Section: Data Pre-processingmentioning

confidence: 99%

“…In comparison to manual field measurement of a burned area after wildfires, satellite remote sensing is more convenient, safe and applicable with fast response capability. So far, the satellite sensors applied to burned area research mainly consist of the VEGETATION (VEG) [8][9][10], Advanced Very High Resolution Radiometer (AVHRR) [2,[11][12][13][14][15], Moderate Resolution Imaging Spectroradiometer (MODIS) [1,[16][17][18][19], Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) [20][21][22], Visible Infrared Imaging Radiometer Suite (VIIRS) [7], Thematic Mapper (TM) [5,23,24], Enhanced Thematic Mapper plus (ETM+) [24][25][26][27], and Operational Land Imager (OLI) [28]. Besides, the availability of Synthetic Aperture Radar (SAR) for burned area mapping has also been investigated [25,29,30].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integration of Multiple Spectral Indices and a Neural Network for Burned Area Mapping Based on MODIS Data

Song

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Since wildfires have occurred frequently in recent years, accurate burned area mapping is required for wildfire severity assessment and burned land reconstruction. Satellite remote sensing is an effective technology that can provide valuable information for wildfire assessment. However, the common approaches based on using a single satellite image to promptly detect the burned areas have low accuracy and limited applicability. This paper develops a new burned area mapping method that surpasses the detection accuracy of previous methods, while still using a single Moderate Resolution Imaging Spectroradiometer (MODIS) sensor image. The key innovation is integrating optimal spectral indices and a neural network algorithm. We used the traditional empirical formula method, multi-threshold method and visual interpretation method to extract the sample sets of five typical types (burned area, vegetation, cloud, bare soil, and cloud shadow) from the MODIS data of several wildfires in the American states of Nevada, Washington and California in 2016. Afterward, the separability index M was adopted to assess the capacity of seven spectral bands and 13 spectral indices to distinguish the burned area from four unburned land cover types. Based on the separability analysis between the burned area and unburned areas, the spectral indices with an M value higher than 1.0 were employed to generate the training sample sets that were assessed to have an overall accuracy of 98.68% and Kappa coefficient of 97.46%. Finally, we utilized a back-propagation neural network (BPNN) to learn the spectral differences of different types from the training sample sets and obtain the output burned area map. The proposed method was applied to three wildfire cases in the American states of Idaho, Nevada and Oregon in 2017. A comparison of detection results between the new MODIS-based burned area map and the reference burned area map compiled from Landsat-8 Operational Land Imager (OLI) data indicates that the proposed method can effectively exploit the spectral characteristics of various land cover types. Also, this new method can achieve higher accuracy with the reduction of commission error (CE, >10%) and omission error (OE, >6%) compared to the traditional empirical formula method. The new burned area mapping method could help managers and the public perform more effective wildfire assessments and emergency management.

show abstract

Section: Data Pre-processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Integration of Multiple Spectral Indices and a Neural Network for Burned Area Mapping Based on MODIS Data

Song

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Therefore, we select the MODIS data as our data source, and it can be acquired from our remote sensing platform located in Hefei, China and the Level-1 and Atmosphere Archive & Distribution System (LAADS) Distributed Active Archive Center (DAAC) located in the Goddard Space Flight Center in Greenbelt, Maryland, USA (https://ladsweb.nascom.nasa.gov/). The original MODIS Level 1B data were pre-processed in ENVI software by geometric correction to the universal transverse mercator (UTM) projection, and by radiometric calibration [56] to the data of reflectance and radiance. The MODIS bands 1, 4, and 3 can be used as the red, green, and blue channels to yield the true-color RGB images [10,14].…”

Section: Data Sourcementioning

confidence: 99%

SmokeNet: Satellite Smoke Scene Detection Using Convolutional Neural Network with Spatial and Channel-Wise Attention

et al. 2019

View full text Add to dashboard Cite

A variety of environmental analysis applications have been advanced by the use of satellite remote sensing. Smoke detection based on satellite imagery is imperative for wildfire detection and monitoring. However, the commonly used smoke detection methods mainly focus on smoke discrimination from a few specific classes, which reduces their applicability in different regions of various classes. To this end, in this paper, we present a new large-scale satellite imagery smoke detection benchmark based on Moderate Resolution Imaging Spectroradiometer (MODIS) data, namely USTC_SmokeRS, consisting of 6225 satellite images from six classes (i.e., cloud, dust, haze, land, seaside, and smoke) and covering various areas/regions over the world. To build a baseline for smoke detection in satellite imagery, we evaluate several state-of-the-art deep learning-based image classification models. Moreover, we propose a new convolution neural network (CNN) model, SmokeNet, which incorporates spatial and channel-wise attention in CNN to enhance feature representation for scene classification. The experimental results of our method using different proportions (16%, 32%, 48%, and 64%) of training images reveal that our model outperforms other approaches with higher accuracy and Kappa coefficient. Specifically, the proposed SmokeNet model trained with 64% training images achieves the best accuracy of 92.75% and Kappa coefficient of 0.9130. The model trained with 16% training images can also improve the classification accuracy and Kappa coefficient by at least 4.99% and 0.06, respectively, over the state-of-the-art models.

show abstract

“…Landsat data have been computed [23,[47][48][49][50], the Normalized Burned Ratio (NBR) [51] (1) and the Normalized Burned Ratio 2 [52] (2). They are defined as • [25].…”

Section: Study Area and Datamentioning

confidence: 99%

Mapping Burned Areas in Latin America from Landsat-8 with Google Earth Engine

Bastarrika¹,

Barrett²,

Roteta³

et al. 2018

Preprint

View full text Add to dashboard Cite

A burned area product was generated from Landsat 8 OLI based three-month composites for the whole territory of Latin America using the processing power of Google earth engine. The product covers the year 2016, and it is guided by thermal anomalies recorded by the, Suomi-NPP satellite Visible Infrared Imaging Radiometer Suite (VIIRS) sensor. The BA algorithm takes into account the spectral contrast between the fire affected areas and the unburned background, using a dedicated thresholding technique. Several spectral indices/bands were used to detect burned pixels by using the spectral signatures extracted at the hotspots. Results showed ~518K km 2 of burned areas for 2016, in comparison with the ~318K km 2 of the MODIS MCD64A1 c6 product. The comparison of the automatic method with manually obtained burned perimeters in 40 validation sites showed a very high overall accuracy. Aggregated commission and omission errors for the burned category were found below 20%. The most problematic areas were found related to the low temporal resolution of the sensor and the persistence of the cloud cover, as well as to the confusion with croplands, particularly with regards to commission errors.

show abstract

Burned Area Mapping of an Escaped Fire into Tropical Dry Forest in Western Madagascar Using Multi-Season Landsat OLI Data

Cited by 26 publications

References 83 publications

Integration of Multiple Spectral Indices and a Neural Network for Burned Area Mapping Based on MODIS Data

Integration of Multiple Spectral Indices and a Neural Network for Burned Area Mapping Based on MODIS Data

SmokeNet: Satellite Smoke Scene Detection Using Convolutional Neural Network with Spatial and Channel-Wise Attention

Mapping Burned Areas in Latin America from Landsat-8 with Google Earth Engine

Contact Info

Product

Resources

About