Skip to main content
SpringerLink
Log in

Probabilistic Biomass Estimation with Conditional Generative Adversarial Networks

  • Conference paper
  • First Online:
Pattern Recognition (DAGM GCPR 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13485))

Included in the following conference series:

  • 1588 Accesses

Abstract

Biomass is an important variable for our understanding of the terrestrial carbon cycle, facilitating the need for satellite-based global and continuous monitoring. However, current machine learning methods used to map biomass can often not model the complex relationship between biomass and satellite observations or cannot account for the estimation’s uncertainty. In this work, we exploit the stochastic properties of Conditional Generative Adversarial Networks for quantifying aleatoric uncertainty. Furthermore, we use generator Snapshot Ensembles in the context of epistemic uncertainty and show that unlabeled data can easily be incorporated into the training process. The methodology is tested on a newly presented dataset for satellite-based estimation of biomass from multispectral and radar imagery, using lidar-derived maps as reference data. The experiments show that the final network ensemble captures the dataset’s probabilistic characteristics, delivering accurate estimates and well-calibrated uncertainties.

This work was partly funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - SFB 1502/1-2022 - Projektnummer: 450058266, by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy - EXC 2070 - 390732324 and by the German Federal Ministry of Education and Research (BMBF) in the framework of the international future AI lab “AI4EO - Artificial Intelligence for Earth Observation: Reasoning, Uncertainties, Ethics and Beyond” (grant number: 01DD20001).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Adler, J., Öktem, O.: Deep Bayesian Inversion (2018). arXiv e-Print arXiv:1811.05910

  2. Amini, J., Sumantyo, J.T.S.: Employing a method on SAR and optical images for forest biomass estimation. IEEE Trans. Geosci. Remote Sens. 47(12), 4020–4026 (2009)

    Article  Google Scholar 

  3. Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: International Conference on Learning Representations (2016)

    Google Scholar 

  4. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)

    Google Scholar 

  5. Ashton, M.S., Tyrrell, M.L., Spalding, D., Gentry, B.: Managing Forest Carbon in a Changing Climate. Springer, Dordrecht (2012). https://doi.org/10.1007/978-94-007-2232-3

    Book  Google Scholar 

  6. Bihlo, A.: A generative adversarial network approach to (ensemble) weather prediction. Neural Netw. 139, 1–16 (2021)

    Article  Google Scholar 

  7. Björk, S., Anfinsen, S.N., Næsset, E., Gobakken, T., Zahabu, E.: Generation of lidar-predicted forest biomass maps from radar backscatter with conditional generative adversarial networks. In: International Geoscience and Remote Sensing Symposium, pp. 4327–4330 (2020)

    Google Scholar 

  8. Dong, L., et al.: Application of convolutional neural network on lei bamboo above-ground-biomass (AGB) estimation using worldview-2. Remote Sens. 12(6), 958 (2020)

    Article  Google Scholar 

  9. Fekety, P.A., Hudak, A.T.: LiDAR Derived Forest Aboveground Biomass Maps, Northwestern USA, 2002–2016. Oak Ridge National Laboratory Distributed Active Archive Center (2020)

    Google Scholar 

  10. Foody, G.M., Boyd, D.S., Cutler, M.E.J.: Predictive relations of tropical forest biomass from Landsat TM data and their transferability between regions. Remote Sens. Environ. 85(4), 463–474 (2003)

    Article  Google Scholar 

  11. Foody, G.M., et al.: Mapping the biomass of Bornean tropical rain forest from remotely sensed data. Glob. Ecol. Biogeogr. 10(4), 379–387 (2001)

    Article  Google Scholar 

  12. Gal, Y., Ghahramani, Z.: Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In: International Conference on Machine Learning. pp. 1050–1059 (2016)

    Google Scholar 

  13. Gawlikowski, J., et al.: A survey of uncertainty in deep neural networks (2021). arXiv e-Print arXiv:2107.03342

  14. Goodfellow, I., et al.: Generative adversarial nets. In: Conference on Neural Information Processing Systems, pp. 2672–2680 (2014)

    Google Scholar 

  15. Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321–1330 (Jul 2017)

    Google Scholar 

  16. Houghton, R.A., Hall, F., Goetz, S.J.: Importance of biomass in the global carbon cycle. J. Geophys. Res. 114, G00E03 (2009)

    Google Scholar 

  17. Huang, G., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J.E., Weinberger, K.Q.: Snapshot ensembles: train 1, get M for free. In: International Conference on Learning Representations (2017)

    Google Scholar 

  18. Hüllermeier, E., Waegeman, W.: Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods. Mach. Learn. 110(3), 457–506 (2021). https://doi.org/10.1007/s10994-021-05946-3

    Article  MathSciNet  MATH  Google Scholar 

  19. Joshi, N., et al.: Understanding ‘saturation’ of radar signals over forests. Sci. Rep. 7(1), 3505 (2017)

    Article  Google Scholar 

  20. Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Conference on Neural Information Processing Systems, pp. 5580–5590 (2017)

    Google Scholar 

  21. Koochali, A., Schichtel, P., Dengel, A., Ahmed, S.: Probabilistic forecasting of sensory data with generative adversarial networks - ForGAN. IEEE Access 7, 63868–63880 (2019)

    Article  Google Scholar 

  22. Kosaraju, V., Sadeghian, A., Martín-Martín, R., Reid, I., Rezatofighi, S.H., Savarese, S.: Social-BiGAT: multimodal trajectory forecasting using bicycle-GAN and graph attention networks. In: Conference on Neural Information Processing Systems, pp. 137–146 (2019)

    Google Scholar 

  23. Lakshminarayanan, B., Pritzel, A., Blundell, C.: Simple and scalable predictive uncertainty estimation using deep ensembles. In: Conference on Neural Information Processing Systems, pp. 6405–6416 (2017)

    Google Scholar 

  24. Lang, N., Jetz, W., Schindler, K., Wegner, J.D.: A high-resolution canopy height model of the earth (2022). arXiv e-Print arXiv:2204.08322

  25. Lang, N., Kalischek, N., Armston, J., Schindler, K., Dubayah, R., Wegner, J.D.: Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles. Remote Sens. Environ. 268, 112760 (2022)

    Article  Google Scholar 

  26. Le Toan, T., et al.: The BIOMASS mission: mapping global forest biomass to better understand the terrestrial carbon cycle. Remote Sens. Environ. 115(11), 2850–2860 (2011)

    Article  Google Scholar 

  27. Lee, M., Seok, J.: Estimation with uncertainty via conditional generative adversarial networks. Sensors 21(18), 6194 (2021)

    Article  Google Scholar 

  28. Leinonen, J., Guillaume, A., Yuan, T.: Reconstruction of cloud vertical structure with a generative adversarial network. Geophys. Res. Lett. 46(12), 7035–7044 (2019)

    Article  Google Scholar 

  29. Li, Y., Li, M., Li, C., Liu, Z.: Forest aboveground biomass estimation using Landsat 8 and Sentinel-1A data with machine learning algorithms. Sci. Rep. 10, 9952 (2020)

    Article  Google Scholar 

  30. Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2016)

    Google Scholar 

  31. Maselli, F., Chiesi, M.: Evaluation of statistical methods to estimate forest volume in a mediterranean region. IEEE Trans. Geosci. Remote Sens. 44(8), 2239–2250 (2006)

    Article  Google Scholar 

  32. Mermoz, S., Réjou-Méchain, M., Villard, L., Le Toan, T., Rossi, V., Gourlet-Fleury, S.: Decrease of L-band SAR backscatter with biomass of dense forests. Remote Sens. Environ. 159, 307–317 (2015)

    Article  Google Scholar 

  33. Mescheder, L., Geiger, A., Nowozin, S.: Which training methods for GANs do actually converge? In: International Conference on Machine Learning, pp. 3481–3490 (2018)

    Google Scholar 

  34. Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014). arXiv e-Print arXiv:1411.1784

  35. Mutanga, O., Adam, E., Cho, M.A.: High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. Int. J. Appl. Earth Obs. Geoinf. 18, 399–406 (2012)

    Google Scholar 

  36. Neal, R.M.: Bayesian learning for neural networks. Ph.D. thesis, University of Toronto (1995)

    Google Scholar 

  37. Nix, D., Weigend, A.: Estimating the mean and variance of the target probability distribution. In: International Conference on Neural Networks, pp. 55–60 (1994)

    Google Scholar 

  38. Pang, Y., Liu, Y.: Conditional generative adversarial networks (CGAN) for aircraft trajectory prediction considering weather effects. In: AIAA Scitech Forum (2020)

    Google Scholar 

  39. Pearce, T., Brintrup, A., Zaki, M., Neely, A.: High-quality prediction intervals for deep learning: a distribution-free, ensembled approach. In: International Conference on Machine Learning, pp. 4075–4084 (2018)

    Google Scholar 

  40. Ravuri, S., et al.: Skilful precipitation nowcasting using deep generative models of radar. Nature 597(7878), 672–677 (2021)

    Article  Google Scholar 

  41. Rodríguez-Veiga, P., Wheeler, J., Louis, V., Tansey, K., Balzter, H.: Quantifying forest biomass carbon stocks from space. Curr. Forestry Rep. 3(1), 1–18 (2017). https://doi.org/10.1007/s40725-017-0052-5

    Article  Google Scholar 

  42. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  43. Roy, P.S., Ravan, S.A.: Biomass estimation using satellite remote sensing data-An investigation on possible approaches for natural forest. J. Biosci. 21(4), 535–561 (1996)

    Article  Google Scholar 

  44. Shimada, M., Ohtaki, T.: Generating large-scale high-quality SAR mosaic datasets: application to PALSAR data for global monitoring. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 3(4), 637–656 (2010)

    Article  Google Scholar 

  45. Wang, Y., Zhang, L., van de Weijer, J.: Ensembles of generative adversarial networks. In: Conference on Neural Information Processing Systems (2016). Workshop on Adversarial Training

    Google Scholar 

  46. Wilson, A.G., Izmailov, P.: Bayesian deep learning and a probabilistic perspective of generalization. In: Conference on Neural Information Processing Systems, pp. 4697–4708 (2020)

    Google Scholar 

  47. Zhang, C., Jin, B.: Probabilistic residual learning for aleatoric uncertainty in image restoration (2019). arXiv e-Print arXiv:1908.01010v1

  48. Zolkos, S.G., Goetz, S.J., Dubayah, R.: A meta-analysis of terrestrial aboveground biomass estimation using lidar remote sensing. Remote Sens. Environ. 128, 289–298 (2013)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Remote Sensing Group, University of Bonn, Bonn, Germany

    Johannes Leonhardt, Lukas Drees & Ribana Roscher

  2. AI4EO Future Lab, Technical University of Munich and German Aerospace Center, Munich, Germany

    Johannes Leonhardt & Ribana Roscher

  3. Communications and Information Theory Chair, Technical University Berlin, Berlin, Germany

    Peter Jung

Authors
  1. Johannes Leonhardt
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lukas Drees
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peter Jung
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ribana Roscher
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Johannes Leonhardt .

Editor information

Editors and Affiliations

  1. TU Dresden, Dresden, Germany

    Björn Andres

  2. University of Bonn, Bonn, Germany

    Florian Bernard

  3. Technical University of Munich, Munich, Germany

    Daniel Cremers

  4. University of Hamburg, Hamburg, Germany

    Simone Frintrop

  5. University of Konstanz, Konstanz, Germany

    Bastian Goldlücke

  6. University of Siegen, Siegen, Germany

    Ivo Ihrke

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Leonhardt, J., Drees, L., Jung, P., Roscher, R. (2022). Probabilistic Biomass Estimation with Conditional Generative Adversarial Networks. In: Andres, B., Bernard, F., Cremers, D., Frintrop, S., Goldlücke, B., Ihrke, I. (eds) Pattern Recognition. DAGM GCPR 2022. Lecture Notes in Computer Science, vol 13485. Springer, Cham. https://doi.org/10.1007/978-3-031-16788-1_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-16788-1_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-16787-4

  • Online ISBN: 978-3-031-16788-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation