EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Differentiable Physical Modeling for Forest Above-Ground Biomass Retrieval by Unifying a Water Cloud Model and Deep Learning

Cui Zhao, Rui Shi, Yongjie Ji, Wei Zhang, Wangfei Zhang, Xiahong He, Han Zhao

Remote Sensing · 17.03.2026 · 18 (6) · 912

DOI: 10.3390/rs18060912 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 17.03.2026. Verfasst von Cui Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Yunnan Fundamental Research Projects, Yunnan International Joint Innovation Platform for South Asia and Southeast Asia Science and Technology Innovation Center.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the limitations of traditional forest above-ground biomass (AGB) retrieval methods—namely, the restricted accuracy of physical models and the limited generalization ability of purely data-driven models—this study proposes a differentiable physical modeling (DPM) approach for forest AGB estimation. The method adopts the water cloud model (WCM) as a physics-based framework, grounded in radiative transfer theory, and integrates C-band synthetic aperture radar (SAR) data with multispectral imagery. Within the PyTorch tensor computation framework, automatic differentiation (AD) is employed to seamlessly couple the WCM with the deep fully connected neural network (DFCNN), enabling a differentiable implementation of the WCM. Using mean squared error (MSE) as the loss function, the neural network parameters are optimized through backpropagation and gradient descent, thereby constructing an end-to-end trainable DPM model that effectively retrieves forest AGB while preserving physical interpretability and generalization capability. To validate the proposed method, two representative test sites were selected: Simao in Pu’er, Yunnan Province, and Genhe in Inner Mongolia. GF-3 PolSAR and RADARSAT-2 data were used to extract backscattering coefficients and compute the radar vegetation index (RVI), while Landsat 8 OLI imagery was employed to calculate the normalized difference vegetation index (NDVI), difference vegetation index (DVI), and soil-adjusted vegetation index (SAVI). These datasets, together with ASTER GDEM, field-measured biomass, and other relevant datasets, were integrated to construct a multisource dataset combining remote sensing and ground observations. The performance of the DPM model was then compared with the traditional WCM and several data-driven models, including the fully connected neural network (FNN), generalized regression neural network (GRNN), RF, and Adaptive Boosting (AdaBoost). The results indicate that the DPM model achieved R2 = 0.60, RMSE = 24.23 Mg/ha, Bias = 0.4 Mg/ha, and ubRMSE = 22.43 Mg/ha in Simao, and R2 = 0.48, RMSE = 33.29 Mg/ha, Bias = 0.87 Mg/ha, and ubRMSE = 33.28 Mg/ha in Genhe, demonstrating consistently better performance than both the WCM and all tested data-driven models. The DPM model demonstrated consistent performance across ecologically contrasting forest regions. It alleviated the systematic overestimation bias of purely data-driven models and overcame the limitations in predictive accuracy resulting from the simplified structure of the WCM. The differentiability of the WCM enables the loss function errors to be backpropagated through the neural network, thereby allowing the optimization of the physical model parameters. Overall, the DPM framework integrates the advantages of both physical models and data-driven approaches, providing an estimation method with acceptable accuracy for forest AGB retrieval. It also offers theoretical and practical insights for the integration of deep learning and physical knowledge in other research fields.

Förderung

  • National Natural Science Foundation of China
  • Yunnan Fundamental Research Projects
  • Yunnan International Joint Innovation Platform for South Asia and Southeast Asia Science and Technology Innovation Center
  • National Key R&D Program
  • China Agriculture Research System

Zitieren

APA

Zhao, C., Shi, R., Ji, Y., Zhang, W., Zhang, W., He, X., & Zhao, H. (2026). Differentiable Physical Modeling for Forest Above-Ground Biomass Retrieval by Unifying a Water Cloud Model and Deep Learning. Remote Sensing, 18(6), 912. https://doi.org/10.3390/rs18060912

Vancouver

Zhao C, Shi R, Ji Y, Zhang W, Zhang W, He X, et al. Differentiable Physical Modeling for Forest Above-Ground Biomass Retrieval by Unifying a Water Cloud Model and Deep Learning. Remote Sensing. 2026;18(6):912. doi:10.3390/rs18060912

BibTeX
@article{Zhao2026,
  author = {Zhao, Cui and Shi, Rui and Ji, Yongjie and Zhang, Wei and Zhang, Wangfei and He, Xiahong and Zhao, Han},
  title = {Differentiable Physical Modeling for Forest Above-Ground Biomass Retrieval by Unifying a Water Cloud Model and Deep Learning},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {6},
  pages = {912},
  doi = {10.3390/rs18060912}
}
Kostenlos starten →