Using deep learning for digital soil mapping
Author:
Padarian JoséORCID, Minasny Budiman, McBratney Alex B.ORCID
Abstract
Abstract. Digital soil mapping (DSM) has been widely used as a cost-effective
method for generating soil maps. However, current DSM data representation
rarely incorporates contextual information of the landscape. DSM models are
usually calibrated using point observations intersected with spatially
corresponding point covariates. Here, we demonstrate the use of the
convolutional neural network (CNN) model that incorporates contextual information
surrounding an observation to significantly improve the prediction accuracy
over conventional DSM models. We describe a CNN model that takes inputs as images of covariates and explores spatial
contextual information by finding non-linear local spatial relationships of
neighbouring pixels. Unique features of the proposed model include input
represented as a 3-D stack of images, data augmentation to reduce overfitting,
and the simultaneous prediction of multiple outputs. Using a soil mapping example
in Chile, the CNN model was trained to simultaneously predict soil organic
carbon at multiples depths across the country. The results showed that, in
this study, the CNN model reduced the error by 30 % compared with
conventional techniques that only used point information of covariates. In
the example of country-wide mapping at 100 m resolution, the neighbourhood
size from 3 to 9 pixels is more effective than at a point location and larger
neighbourhood sizes. In addition, the CNN model produces less prediction
uncertainty and it is able to predict soil carbon at deeper soil layers more
accurately. Because the CNN model takes the covariate represented as images, it
offers a simple and effective framework for future DSM models.
Publisher
Copernicus GmbH
Reference57 articles.
1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado,
G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp,
A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M.,
Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C.,
Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P.,
Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P.,
Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale
Machine Learning on Heterogeneous Systems, available at:
https://www.tensorflow.org/ (last access: 22 February 2019), 2015. a 2. Adhikari, K., Hartemink, A. E., Minasny, B., Kheir, R. B., Greve, M. B., and
Greve, M. H.: Digital mapping of soil organic carbon contents and stocks in
Denmark, PloS one, 9, e105519, https://doi.org/10.1371/journal.pone.0105519, 2014. a, b 3. Akpa, S. I., Odeh, I. O., Bishop, T. F., Hartemink, A. E., and Amapu, I. Y.:
Total soil organic carbon and carbon sequestration potential in Nigeria,
Geoderma, 271, 202–215, 2016. a, b 4. Angelini, M. E. and Heuvelink, G. B.: Including spatial correlation in
structural equation modelling of soil properties, Spat. Stat.-Nath., 25,
35–51, 2018. a 5. Angelini, M., Heuvelink, G., and Kempen, B.: Multivariate mapping of soil
with
structural equation modelling, Eur. J. Soil Sci., 68,
575–591, 2017. a
Cited by
144 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|