Co-Burn: Combining dNBR Anchoring and Ordinal Learning for Cross-Event Fire Severity Mapping in New South Wales.
Saved in:
| Title: | Co-Burn: Combining dNBR Anchoring and Ordinal Learning for Cross-Event Fire Severity Mapping in New South Wales. |
|---|---|
| Authors: | Zhang, Yueying1,2 (AUTHOR), Shen, Jun2,3 (AUTHOR) jshen@uow.edu.au, Yang, Shuqing2,3 (AUTHOR), Srivastava, Ankur4,5 (AUTHOR), Wang, Fanggang5,6 (AUTHOR) |
| Source: | Remote Sensing. Sep2026, Vol. 18 Issue 17, p3019. 31p. |
| Subjects: | Remote sensing, Sequential learning, Wildfires, Fire ecology |
| Geographic Terms: | New South Wales |
| Abstract: | Highlights: What are the main findings? Co-Burn attaches the pre-to-post dNBR to the post-fire branch as a change anchor and uses a conditional ordinal head to sequence burned-footprint placement before high-severity assignment. Across 14 New South Wales fires with four complete external holdouts, Co-Burn ranked first among ten methods under both pixel-pooled and event-mean aggregation, giving the strongest performance on fires excluded from training, validation, and model selection. What are the implications of the main findings? For post-fire mapping of previously unseen forest wildfires, Co-Burn enables ordered three-class severity mapping without target-fire threshold calibration, using dNBR as a learned change anchor. Co-Burn delivers a more selective burned-footprint map, reducing false-burn expansion relative to the reflectance-only conditional variant, while reaching higher burned mIoU at the same false-burn budget. Cross-event fire-severity mapping requires a model to delineate the burned footprint and grade severity within it across wildfires whose spectral expression varies with vegetation and observation conditions. Nominal multiclass models treat the classes as parallel alternatives and leave the order implicit. We introduce Co-Burn, a bi-temporal Siamese model that adds a pre-to-post dNBR channel to the post-fire branch as an NIR-SWIR change anchor and uses a conditional ordinal head to estimate burn presence before high-severity assignment. Ten methods were compared across 14 New South Wales wildfires against a Sentinel-2 FESM-derived three-class target, with 4 complete fires held out from model development and selection. Co-Burn ranked first under both pixel-pooled and event-mean aggregation, reaching 0.520 ± 0.017 and 0.524 ± 0.028 external burned mIoU. Event-level factorial contrasts showed that burned-mIoU effects varied among fires, while dNBR anchoring reduced false-burn rate on all four external events. At the fixed operating point, Co-Burn assigned 19.9% of reference-unburned pixels to burned classes, against 28.9% for the reflectance-only nominal variant. On the hardest held-out fire, limited false-burn expansion coexisted with a downward shift across the ordered severity classes. Co-Burn supports ordered three-class mapping of previously unseen forest fires before target-fire labels become available. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 197043869 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Co-Burn: Combining dNBR Anchoring and Ordinal Learning for Cross-Event Fire Severity Mapping in New South Wales. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Yueying%22">Zhang, Yueying</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shen%2C+Jun%22">Shen, Jun</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<i> jshen@uow.edu.au</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Shuqing%22">Yang, Shuqing</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Srivastava%2C+Ankur%22">Srivastava, Ankur</searchLink><relatesTo>4,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Fanggang%22">Wang, Fanggang</searchLink><relatesTo>5,6</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Sep2026, Vol. 18 Issue 17, p3019. 31p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Sequential+learning%22">Sequential learning</searchLink><br /><searchLink fieldCode="DE" term="%22Wildfires%22">Wildfires</searchLink><br /><searchLink fieldCode="DE" term="%22Fire+ecology%22">Fire ecology</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22New+South+Wales%22">New South Wales</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? Co-Burn attaches the pre-to-post dNBR to the post-fire branch as a change anchor and uses a conditional ordinal head to sequence burned-footprint placement before high-severity assignment. Across 14 New South Wales fires with four complete external holdouts, Co-Burn ranked first among ten methods under both pixel-pooled and event-mean aggregation, giving the strongest performance on fires excluded from training, validation, and model selection. What are the implications of the main findings? For post-fire mapping of previously unseen forest wildfires, Co-Burn enables ordered three-class severity mapping without target-fire threshold calibration, using dNBR as a learned change anchor. Co-Burn delivers a more selective burned-footprint map, reducing false-burn expansion relative to the reflectance-only conditional variant, while reaching higher burned mIoU at the same false-burn budget. Cross-event fire-severity mapping requires a model to delineate the burned footprint and grade severity within it across wildfires whose spectral expression varies with vegetation and observation conditions. Nominal multiclass models treat the classes as parallel alternatives and leave the order implicit. We introduce Co-Burn, a bi-temporal Siamese model that adds a pre-to-post dNBR channel to the post-fire branch as an NIR-SWIR change anchor and uses a conditional ordinal head to estimate burn presence before high-severity assignment. Ten methods were compared across 14 New South Wales wildfires against a Sentinel-2 FESM-derived three-class target, with 4 complete fires held out from model development and selection. Co-Burn ranked first under both pixel-pooled and event-mean aggregation, reaching 0.520 ± 0.017 and 0.524 ± 0.028 external burned mIoU. Event-level factorial contrasts showed that burned-mIoU effects varied among fires, while dNBR anchoring reduced false-burn rate on all four external events. At the fixed operating point, Co-Burn assigned 19.9% of reference-unburned pixels to burned classes, against 28.9% for the reflectance-only nominal variant. On the hardest held-out fire, limited false-burn expansion coexisted with a downward shift across the ordered severity classes. Co-Burn supports ordered three-class mapping of previously unseen forest fires before target-fire labels become available. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=197043869 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18173019 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 31 StartPage: 3019 Subjects: – SubjectFull: Remote sensing Type: general – SubjectFull: Sequential learning Type: general – SubjectFull: Wildfires Type: general – SubjectFull: Fire ecology Type: general – SubjectFull: New South Wales Type: general Titles: – TitleFull: Co-Burn: Combining dNBR Anchoring and Ordinal Learning for Cross-Event Fire Severity Mapping in New South Wales. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhang, Yueying – PersonEntity: Name: NameFull: Shen, Jun – PersonEntity: Name: NameFull: Yang, Shuqing – PersonEntity: Name: NameFull: Srivastava, Ankur – PersonEntity: Name: NameFull: Wang, Fanggang IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 17 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
