%0 Journal Article
%@archivingpolicy denypublisher denyfinaldraft24
%@secondarytype PRE PI
%@issn 0924-2716
%@dissemination WEBSCI; PORTALCAPES; COMPENDEX; SCOPUS.
%@nexthigherunit 8JMKD3MGPCW/3ER446E
%@nexthigherunit 8JMKD3MGPCW/3F3NU5S
%2 sid.inpe.br/mtc-m21c/2020/09.14.11.48.59
%4 sid.inpe.br/mtc-m21c/2020/09.14.11.48
%3 doblas_stabilization.pdf
%8 Aug.
%9 conference paper
%A Doblas, Juan Prieto,
%A Carneiro, Arian,
%A Shimabukuro, Yosio Edemir,
%A Sant'Anna, Sidnei João Siqueira,
%A Aragão, Luiz Eduardo Oliveira e Cruz de,
%A Pereira, Francisca Rocha de Souza,
%B ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
%D 2020
%K Remote Sensing, Time-series Data, SAR, Modelling, Deforestation Detection, Change Detection.
%N 3
%O 2020 24th ISPRS Congress on Technical Commission III; Nice, Virtual; France; 31 August 2020 through 2 September 2020;
%P 89-96
%T Stabilization of sentinel-1 sar time-series using climate and forest structure data for early tropical deforestation detection
%V 5
%X In this study we analyse the factors of variability of Sentinel-1 C-band radar backscattering over tropical rainforests, and propose a method to reduce the effects of this variability on deforestation detection algorithms. To do so, we developed a random forest regression model that relates Sentinel-1 gamma nought values with local climatological data and forest structure information. The model was trained using long time-series of 26 relevant variables, sampled over 6 undisturbed tropical forests areas. The resulting model explained 71.64% and 73.28% of the SAR signal variability for VV and VH polarizations, respectively. Once the best model for every polarization was selected, it was used to stabilize extracted pixel-level data of forested and non-deforested areas, which resulted on a 10 to 14% reduction of time-series variability, in terms of standard deviation. Then a statistically robust deforestation detection algorithm was applied to the stabilized time-series. The results show that the proposed method reduced the rate of false positives on both polarizations, especially on VV (from 21% to 2%, α=0.01). Meanwhile, the omission errors increased on both polarizations (from 27% to 37% in VV and from 27% to 33% on VV, α=0.01). The proposed method yielded slightly better results when compared with an alternative state-of-the-art approach (spatial normalization).
%@area SRE
%@electronicmailaddress juan.doblas@inpe.br
%@electronicmailaddress arian.carneiro@inpe.br
%@electronicmailaddress yosio.shimabukuro@inpe.br
%@electronicmailaddress sidnei.santanna@inpe.br
%@electronicmailaddress luiz.aragao@inpe.br
%@electronicmailaddress francisca.pereira@inpe.br
%@documentstage not transferred
%@group SER-SRE-SESPG-INPE-MCTIC-GOV-BR
%@group SER-SRE-SESPG-INPE-MCTIC-GOV-BR
%@group DIDSR-CGOBT-INPE-MCTIC-GOV-BR
%@group DIDSR-CGOBT-INPE-MCTIC-GOV-BR
%@group DIDSR-CGOBT-INPE-MCTIC-GOV-BR
%@group DIDSR-CGOBT-INPE-MCTIC-GOV-BR
%@usergroup simone
%@resumeid
%@resumeid
%@resumeid 8JMKD3MGP5W/3C9JJCQ
%@resumeid 8JMKD3MGP5W/3C9JJ8N
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@versiontype publisher
%@holdercode {isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}
%@doi 10.5194/isprs-Annals-V-3-2020-89-2020