Investigating permafrost carbon dynamics in Alaska with artificial intelligence
Positive feedbacks between permafrost degradation and the release of soil carbon into the atmosphere impact land–atmosphere interactions, disrupt the global carbon cycle, and accelerate climate change. The widespread distribution of thawing permafrost is causing a cascade of geophysical and biochemi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Environmental Research Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/1748-9326/ad0607 |
| _version_ | 1797626837270003712 |
|---|---|
| author | B A Gay N J Pastick A E Züfle A H Armstrong K R Miner J J Qu |
| author_facet | B A Gay N J Pastick A E Züfle A H Armstrong K R Miner J J Qu |
| author_sort | B A Gay |
| collection | DOAJ |
| description | Positive feedbacks between permafrost degradation and the release of soil carbon into the atmosphere impact land–atmosphere interactions, disrupt the global carbon cycle, and accelerate climate change. The widespread distribution of thawing permafrost is causing a cascade of geophysical and biochemical disturbances with global impacts. Currently, few earth system models account for permafrost carbon feedback (PCF) mechanisms. This research study integrates artificial intelligence (AI) tools and information derived from field-scale surveys across the tundra and boreal landscapes in Alaska. We identify and interpret the permafrost carbon cycling links and feedback sensitivities with GeoCryoAI, a hybridized multimodal deep learning (DL) architecture of stacked convolutionally layered, memory-encoded recurrent neural networks (NN). This framework integrates in-situ measurements and flux tower observations for teacher forcing and model training. Preliminary experiments to quantify, validate, and forecast permafrost degradation and carbon efflux across Alaska demonstrate the fidelity of this data-driven architecture. More specifically, GeoCryoAI logs the ecological memory and effectively learns covariate dynamics while demonstrating an aptitude to simulate and forecast PCF dynamics—active layer thickness (ALT), carbon dioxide flux (CO _2 ), and methane flux (CH _4 )—with high precision and minimal loss (i.e. ALT ^RMSE : 1.327 cm [1969–2022]; CO _2 ^RMSE : 0.697 µ molCO _2 m ^−2 s ^−1 [2003–2021]; CH _4 ^RMSE : 0.715 nmolCH _4 m ^−2 s ^−1 [2011–2022]). ALT variability is a sensitive harbinger of change, a unique signal characterizing the PCF, and our model is the first characterization of these dynamics across space and time. |
| first_indexed | 2024-03-11T10:15:53Z |
| format | Article |
| id | doaj.art-8d7581f4f5b94609a3506841240e25bb |
| institution | Directory Open Access Journal |
| issn | 1748-9326 |
| language | English |
| last_indexed | 2024-03-11T10:15:53Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Environmental Research Letters |
| spelling | doaj.art-8d7581f4f5b94609a3506841240e25bb2023-11-16T09:37:16ZengIOP PublishingEnvironmental Research Letters1748-93262023-01-01181212500110.1088/1748-9326/ad0607Investigating permafrost carbon dynamics in Alaska with artificial intelligenceB A Gay0https://orcid.org/0000-0003-2617-2559N J Pastick1https://orcid.org/0000-0002-4321-6739A E Züfle2https://orcid.org/0000-0001-7001-4123A H Armstrong3https://orcid.org/0000-0002-9123-8924K R Miner4https://orcid.org/0000-0002-1006-1283J J Qu5https://orcid.org/0000-0002-6978-2018George Mason University, Department of Geography and Geoinformation Science , Fairfax, VA, United States of America; NASA Jet Propulsion Laboratory, California Institute of Technology , Pasadena, CA, United States of AmericaUnited States Geological Survey, Earth Resources Observation and Science Center , Sioux Falls, SD, United States of AmericaGeorge Mason University, Department of Geography and Geoinformation Science , Fairfax, VA, United States of America; Emory University, Department of Computer Science , Atlanta, GA, United States of AmericaUniversity of Maryland, Earth System Science Interdisciplinary Center , College Park, MD, United States of AmericaNASA Jet Propulsion Laboratory, California Institute of Technology , Pasadena, CA, United States of AmericaGeorge Mason University, Department of Geography and Geoinformation Science , Fairfax, VA, United States of AmericaPositive feedbacks between permafrost degradation and the release of soil carbon into the atmosphere impact land–atmosphere interactions, disrupt the global carbon cycle, and accelerate climate change. The widespread distribution of thawing permafrost is causing a cascade of geophysical and biochemical disturbances with global impacts. Currently, few earth system models account for permafrost carbon feedback (PCF) mechanisms. This research study integrates artificial intelligence (AI) tools and information derived from field-scale surveys across the tundra and boreal landscapes in Alaska. We identify and interpret the permafrost carbon cycling links and feedback sensitivities with GeoCryoAI, a hybridized multimodal deep learning (DL) architecture of stacked convolutionally layered, memory-encoded recurrent neural networks (NN). This framework integrates in-situ measurements and flux tower observations for teacher forcing and model training. Preliminary experiments to quantify, validate, and forecast permafrost degradation and carbon efflux across Alaska demonstrate the fidelity of this data-driven architecture. More specifically, GeoCryoAI logs the ecological memory and effectively learns covariate dynamics while demonstrating an aptitude to simulate and forecast PCF dynamics—active layer thickness (ALT), carbon dioxide flux (CO _2 ), and methane flux (CH _4 )—with high precision and minimal loss (i.e. ALT ^RMSE : 1.327 cm [1969–2022]; CO _2 ^RMSE : 0.697 µ molCO _2 m ^−2 s ^−1 [2003–2021]; CH _4 ^RMSE : 0.715 nmolCH _4 m ^−2 s ^−1 [2011–2022]). ALT variability is a sensitive harbinger of change, a unique signal characterizing the PCF, and our model is the first characterization of these dynamics across space and time.https://doi.org/10.1088/1748-9326/ad0607permafrostartificial intelligencepermafrost carbon feedbackcarbon cycleclimate changeAlaska |
| spellingShingle | B A Gay N J Pastick A E Züfle A H Armstrong K R Miner J J Qu Investigating permafrost carbon dynamics in Alaska with artificial intelligence Environmental Research Letters permafrost artificial intelligence permafrost carbon feedback carbon cycle climate change Alaska |
| title | Investigating permafrost carbon dynamics in Alaska with artificial intelligence |
| title_full | Investigating permafrost carbon dynamics in Alaska with artificial intelligence |
| title_fullStr | Investigating permafrost carbon dynamics in Alaska with artificial intelligence |
| title_full_unstemmed | Investigating permafrost carbon dynamics in Alaska with artificial intelligence |
| title_short | Investigating permafrost carbon dynamics in Alaska with artificial intelligence |
| title_sort | investigating permafrost carbon dynamics in alaska with artificial intelligence |
| topic | permafrost artificial intelligence permafrost carbon feedback carbon cycle climate change Alaska |
| url | https://doi.org/10.1088/1748-9326/ad0607 |
| work_keys_str_mv | AT bagay investigatingpermafrostcarbondynamicsinalaskawithartificialintelligence AT njpastick investigatingpermafrostcarbondynamicsinalaskawithartificialintelligence AT aezufle investigatingpermafrostcarbondynamicsinalaskawithartificialintelligence AT aharmstrong investigatingpermafrostcarbondynamicsinalaskawithartificialintelligence AT krminer investigatingpermafrostcarbondynamicsinalaskawithartificialintelligence AT jjqu investigatingpermafrostcarbondynamicsinalaskawithartificialintelligence |