Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model.
In response to the limited number and distribution of in-situ carbon flux observations, remote sensing-based methods are increasingly relied upon for the estimation of Gross Primary Productivity (GPP) at regional to global scales. These remote sensing-informed estimates are commonly derived through...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125001177 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725326343536640 |
|---|---|
| author | Ramon Melser Nicholas C. Coops Michael A. Wulder Chris Derksen Sara H. Knox Tongli Wang |
| author_facet | Ramon Melser Nicholas C. Coops Michael A. Wulder Chris Derksen Sara H. Knox Tongli Wang |
| author_sort | Ramon Melser |
| collection | DOAJ |
| description | In response to the limited number and distribution of in-situ carbon flux observations, remote sensing-based methods are increasingly relied upon for the estimation of Gross Primary Productivity (GPP) at regional to global scales. These remote sensing-informed estimates are commonly derived through process-based modelling frameworks which prescribe functional relationships between model inputs and target GPP. Across highly heterogeneous landscapes like the Canadian boreal, these parameters are difficult to constrain and often site-specific. Recent work has determined that parameterization alone may not improve model performance, instead requiring additional model inputs to capture the complex drivers of vegetation productivity across land cover types. In response to these challenges, we applied the remote sensing-based CAN-TG framework to estimate boreal GPP, leveraged through a random forest (RF) machine learning approach that does not assume linear or functional relationships between input variables and productivity. Stratified by land cover, fire disturbance history, and topography, models were assessed for their ability to capture reference GPP from NASA's complex, process-based Soil Moisture Active Passive (SMAP) GPP product. Across all boreal strata, model r2 values ranged from 0.93 to 0.96, demonstrating that the variability in substantially more complex models can be successfully captured using a simple, interpretable remote sensing-based framework. Through the addition of remote sensing variables capturing freeze/thaw and soil moisture dynamics to surface temperature and greenness, the CAN-TG model demonstrated an improved ability to capture GPP compared to a benchmark GPP model. Seasonal RF models across key boreal land cover, fire disturbance history and topographic strata further demonstrated varying and complex non-linear relationships between model variables and GPP. Spring and fall models generally outperformed winter and summer models, reaffirming model strengths whilst also highlighting remaining uncertainty and areas for future model improvement. |
| format | Article |
| id | doaj-art-36bdcb19968b4366982e69baa0da3eed |
| institution | DOAJ |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-36bdcb19968b4366982e69baa0da3eed2025-08-20T03:10:29ZengElsevierEcological Informatics1574-95412025-07-018710310810.1016/j.ecoinf.2025.103108Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model.Ramon Melser0Nicholas C. Coops1Michael A. Wulder2Chris Derksen3Sara H. Knox4Tongli Wang5Department of Forest Resources Management, Faculty of Forestry, University of British Columbia, Vancouver, BC V6T 1Z4, Canada; Corresponding author at: 2424 Main Mall, Vancouver, BC, V6T 1Z4, Canada.Department of Forest Resources Management, Faculty of Forestry, University of British Columbia, Vancouver, BC V6T 1Z4, CanadaCanadian Forest Service, Natural Resources Canada, Victoria, BC V8Z 1M5, CanadaEnvironment and Climate Change Canada, Climate Research Division, Toronto, ON M3H 5T4, CanadaDepartment of Geography, Faculty of Science, McGill University, Montreal, QB H3A 0B9, Canada; Department of Geography, Faculty of Arts, University of British Columbia, Vancouver, BC V6T 1Z2, CanadaDepartment of Forest and Conservation Sciences, University of British Columbia, Vancouver, BC V6T 1Z4, CanadaIn response to the limited number and distribution of in-situ carbon flux observations, remote sensing-based methods are increasingly relied upon for the estimation of Gross Primary Productivity (GPP) at regional to global scales. These remote sensing-informed estimates are commonly derived through process-based modelling frameworks which prescribe functional relationships between model inputs and target GPP. Across highly heterogeneous landscapes like the Canadian boreal, these parameters are difficult to constrain and often site-specific. Recent work has determined that parameterization alone may not improve model performance, instead requiring additional model inputs to capture the complex drivers of vegetation productivity across land cover types. In response to these challenges, we applied the remote sensing-based CAN-TG framework to estimate boreal GPP, leveraged through a random forest (RF) machine learning approach that does not assume linear or functional relationships between input variables and productivity. Stratified by land cover, fire disturbance history, and topography, models were assessed for their ability to capture reference GPP from NASA's complex, process-based Soil Moisture Active Passive (SMAP) GPP product. Across all boreal strata, model r2 values ranged from 0.93 to 0.96, demonstrating that the variability in substantially more complex models can be successfully captured using a simple, interpretable remote sensing-based framework. Through the addition of remote sensing variables capturing freeze/thaw and soil moisture dynamics to surface temperature and greenness, the CAN-TG model demonstrated an improved ability to capture GPP compared to a benchmark GPP model. Seasonal RF models across key boreal land cover, fire disturbance history and topographic strata further demonstrated varying and complex non-linear relationships between model variables and GPP. Spring and fall models generally outperformed winter and summer models, reaffirming model strengths whilst also highlighting remaining uncertainty and areas for future model improvement.http://www.sciencedirect.com/science/article/pii/S1574954125001177Boreal carbon dynamicsNon-parametric modellingRandom forestVariable contributionSeasonal uncertaintyLand cover |
| spellingShingle | Ramon Melser Nicholas C. Coops Michael A. Wulder Chris Derksen Sara H. Knox Tongli Wang Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model. Ecological Informatics Boreal carbon dynamics Non-parametric modelling Random forest Variable contribution Seasonal uncertainty Land cover |
| title | Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model. |
| title_full | Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model. |
| title_fullStr | Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model. |
| title_full_unstemmed | Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model. |
| title_short | Capturing constraints on boreal gross primary productivity using the remote sensing-based CAN-TG model. |
| title_sort | capturing constraints on boreal gross primary productivity using the remote sensing based can tg model |
| topic | Boreal carbon dynamics Non-parametric modelling Random forest Variable contribution Seasonal uncertainty Land cover |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125001177 |
| work_keys_str_mv | AT ramonmelser capturingconstraintsonborealgrossprimaryproductivityusingtheremotesensingbasedcantgmodel AT nicholasccoops capturingconstraintsonborealgrossprimaryproductivityusingtheremotesensingbasedcantgmodel AT michaelawulder capturingconstraintsonborealgrossprimaryproductivityusingtheremotesensingbasedcantgmodel AT chrisderksen capturingconstraintsonborealgrossprimaryproductivityusingtheremotesensingbasedcantgmodel AT sarahknox capturingconstraintsonborealgrossprimaryproductivityusingtheremotesensingbasedcantgmodel AT tongliwang capturingconstraintsonborealgrossprimaryproductivityusingtheremotesensingbasedcantgmodel |