MODIS-Based Estimation of Grassland Gross Primary Productivity in Inner Mongolia Using a ConvTransformer Deep Learning Model.
Saved in:
| Title: | MODIS-Based Estimation of Grassland Gross Primary Productivity in Inner Mongolia Using a ConvTransformer Deep Learning Model. |
|---|---|
| Authors: | Shi, Dingqi1,2 (AUTHOR), Yao, Yunjun1,2 (AUTHOR) yaoyunjun@bnu.edu.cn, Li, Yufu3 (AUTHOR), Zhang, Xueyi1,2,4 (AUTHOR), Zhang, Xiaotong1,2,5 (AUTHOR), Jiang, Bo1,2 (AUTHOR), Yu, Ruiyang2,5 (AUTHOR), Liu, Lu1,2,3 (AUTHOR), Xie, Zijing1,2,4 (AUTHOR), Fan, Jiahui1,2,5 (AUTHOR), Qiu, Fei1,2 (AUTHOR) |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p2016. 22p. |
| Subjects: | Transformer models, MODIS (Spectroradiometer), Deep learning, Spatiotemporal processes, Environmental monitoring, Carbon cycle |
| Geographic Terms: | Inner Mongolia (China) |
| Abstract: | Highlights: What are the main findings? A ConvTransformer framework was developed for estimating grassland GPP in Inner Mongolia. The model outperformed RF, GBRT, SVR, and EC-LUE, generating a daily 1 km GPP dataset (2003–2018). What are the implications of the main findings? The framework improves the representation of spatiotemporal dynamics in arid and semi-arid grasslands and enhances regional GPP estimation accuracy. The generated long-term high-resolution GPP dataset provides valuable support for carbon cycle research, ecological monitoring, and sustainable grassland management. Understanding ecosystem carbon processes relies heavily on the reliable assessment of gross primary productivity (GPP) yet remains challenging in the Inner Mongolia grasslands due to data scarcity and high uncertainty among existing products. We developed a ConvTransformer-based framework that exploits complementary information from satellite observations and meteorological datasets to enhance the representation of complex spatiotemporal dependencies in grassland ecosystems. Grounded in leave-one-site-out cross-validation across six eddy covariance sites, the model achieved average performance metrics of R2 = 0.59, RMSE = 1.40 g C m−2 d−1, Bias = −0.31 g C m−2 d−1, and KGE = 0.46, outperforming traditional machine learning models (RF, GBRT, and SVR) as well as the light use efficiency model (EC-LUE) in both accuracy and robustness. Using this framework, we generated a daily GPP dataset at spatial granularity of 1 km for the Inner Mongolia grasslands from 2003 to 2018. The results reveal a clear spatial gradient, with GPP decreasing from southeast to northwest. Comparisons with established products, including FLUXCOM, BESS V2, and PML V2, show strong spatial consistency and reduced discrepancies, supporting the reliability of the estimates. Overall, the proposed framework provides an effective approach for characterizing regional carbon dynamics and supports long-term ecological monitoring in semi-arid regions. [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.
|
|
| Abstract: | Highlights: What are the main findings? A ConvTransformer framework was developed for estimating grassland GPP in Inner Mongolia. The model outperformed RF, GBRT, SVR, and EC-LUE, generating a daily 1 km GPP dataset (2003–2018). What are the implications of the main findings? The framework improves the representation of spatiotemporal dynamics in arid and semi-arid grasslands and enhances regional GPP estimation accuracy. The generated long-term high-resolution GPP dataset provides valuable support for carbon cycle research, ecological monitoring, and sustainable grassland management. Understanding ecosystem carbon processes relies heavily on the reliable assessment of gross primary productivity (GPP) yet remains challenging in the Inner Mongolia grasslands due to data scarcity and high uncertainty among existing products. We developed a ConvTransformer-based framework that exploits complementary information from satellite observations and meteorological datasets to enhance the representation of complex spatiotemporal dependencies in grassland ecosystems. Grounded in leave-one-site-out cross-validation across six eddy covariance sites, the model achieved average performance metrics of R2 = 0.59, RMSE = 1.40 g C m−2 d−1, Bias = −0.31 g C m−2 d−1, and KGE = 0.46, outperforming traditional machine learning models (RF, GBRT, and SVR) as well as the light use efficiency model (EC-LUE) in both accuracy and robustness. Using this framework, we generated a daily GPP dataset at spatial granularity of 1 km for the Inner Mongolia grasslands from 2003 to 2018. The results reveal a clear spatial gradient, with GPP decreasing from southeast to northwest. Comparisons with established products, including FLUXCOM, BESS V2, and PML V2, show strong spatial consistency and reduced discrepancies, supporting the reliability of the estimates. Overall, the proposed framework provides an effective approach for characterizing regional carbon dynamics and supports long-term ecological monitoring in semi-arid regions. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18122016 |
