Using deep learning for digital soil mapping
Open accessThe DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
An Introduction to the Bootstrap
Efron, B., & Tibshirani, R. J. (1994) · doi:10.1201/9780429246593 · Cited by 40,500
(2014) · Cited by 33,419
An Introduction to the Bootstrap
Efron, B., & Tibshirani, R. J. (1993) · doi:10.1007/978-1-4899-4541-9 · Cited by 21,230
Very high resolution interpolated climate surfaces for global land areas
Hijmans, R. J., Cameron, S. E., Parra, J. L., Jones, P. G., & Jarvis, A. (2005) · International Journal of Climatology · doi:10.1002/joc.1276 · Cited by 19,825
Deep learning in agriculture: A survey
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2018.02.016 · Cited by 5,133
Chui, C. K., & Heil, C. (1992) · Computers in Physics · doi:10.1063/1.4823126 · Cited by 4,732
McBratney, A. B., Mendonça Santos, M. L., & Minasny, B. (2003) · Geoderma · doi:10.1016/s0016-7061(03)00223-4 · Cited by 3,651
Self-citationBest practices for convolutional neural networks applied to visual document analysis
Simard, P. Y., Steinkraus, D., & Platt, J. C. (2005) · Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. · doi:10.1109/icdar.2003.1227801 · Cited by 2,741
System for Automated Geoscientific Analyses (SAGA) v. 2.1.4
Conrad, O., Bechtel, B., Bock, M., Dietrich, H., Fischer, E., Gerlitz, L., Wehberg, J., Wichmann, V., & Böhner, J. (2015) · Geoscientific Model Development · doi:10.5194/gmd-8-1991-2015 · Cited by 2,614
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
Perez, L., & Wang, J. (2017) · arXiv · doi:10.48550/arxiv.1712.04621 · Cited by 2,499
New Global Hydrography Derived from Spaceborne Elevation Data
Lehner, B., Verdin, K., & Jarvis, A. (2008) · Eos, Transactions American Geophysical Union · doi:10.1029/2008eo100001 · Cited by 2,411 · cited 2×
“The formalisation of the DSM methodology was done by the publication of McBratney et al. (2003). Following the ideas of Dokuchaev (1883) and Jenny (1941), they described the scorpan model as the empirical quantitative relationship of a soil attribute and its spatially implicit forming factors.”
MethodAn Overview of Multi-Task Learning in Deep Neural Networks
Ruder, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05098 · Cited by 2,265
Zur Theorie der orthogonalen Funktionensysteme: Erste Mitteilung
Haar, A. (1910) · Mathematische Annalen · doi:10.1007/bf01456326 · Cited by 2,138
Jenny, H. (1941) · Soil Science · doi:10.1097/00010694-194111000-00009 · Cited by 1,855
Factors of Soil Formation: A System of Quantitative Pedology
Pendleton, R. L., & Jenny, H. (1945) · Geographical Review · doi:10.2307/211491 · Cited by 1,748
Going Deeper With Contextual CNN for Hyperspectral Image Classification
Lee, H., & Kwon, H. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2725580 · Cited by 983
Using deep learning to predict soil properties from regional spectral data
Padarian, J., Minasny, B., & McBratney, A. B. (2019) · Geoderma Regional · doi:10.1016/j.geodrs.2018.e00198 · Cited by 451
Self-citationMassively Multitask Networks for Drug Discovery
Ramsundar, B., Kearnes, S. M., Riley, P., Webster, D. R., Konerding, D. E., & Pande, V. S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.02072 · Cited by 378
Digital Mapping of Soil Organic Carbon Contents and Stocks in Denmark
Adhikari, K., Hartemink, A. E., Minasny, B., Bou Kheir, R., Greve, M. B., & Greve, M. H. (2014) · PLoS ONE · doi:10.1371/journal.pone.0105519 · Cited by 364
Self-citationDemattê, J. A. M., Fongaro, C. T., Rizzo, R., & Safanelli, J. L. (2018) · Remote Sensing of Environment · doi:10.1016/j.rse.2018.04.047 · Cited by 349
Sun, B., Zhou, S., & Zhao, Q. (2003) · Geoderma · doi:10.1016/s0016-7061(03)00078-8 · Cited by 330
An efficient realization of deep learning for traffic data imputation
Duan, Y., Lv, Y., Liu, Y.-L., & Wang, F.-Y. (2016) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2016.09.015 · Cited by 316
Localizing and Orienting Street Views Using Overhead Imagery
Vo, N. N., & Hays, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_30 · Cited by 283
Don, A., Schumacher, J., Scherer-Lorenzen, M., Scholten, T., & Schulze, E.-D. (2007) · Geoderma · doi:10.1016/j.geoderma.2007.06.003 · Cited by 244 · cited 1×
“…al. (2006) and Sun et al. (2003) whom reported a medium-15 scale spatial correlation range for SOC in China of around 300 m and 550 m, respectively; Rossi et al. (2009) and the 190 m reported for a Coastal forest in Tanzania; and Don et al. (2007) of around 200 m in two grassland sites in Germany.”
BackgroundTotal soil organic carbon and carbon sequestration potential in Nigeria
Akpa, S. I. C., Odeh, I. O. A., Bishop, T. F. A., Hartemink, A. E., & Amapu, I. Y. (2016) · Geoderma · doi:10.1016/j.geoderma.2016.02.021 · Cited by 210
GlobalSoilMap France: High-resolution spatial modelling the soils of France up to two meter depth
Mulder, V. L., Lacoste, M., Richer-de-Forges, A. C., & Arrouays, D. (2016) · Science of The Total Environment · doi:10.1016/j.scitotenv.2016.07.066 · Cited by 196
Fine resolution map of top- and subsoil carbon sequestration potential in France
Chen, S., Martin, M. P., Saby, N. P. A., Walter, C., Angers, D. A., & Arrouays, D. (2018) · Science of The Total Environment · doi:10.1016/j.scitotenv.2018.02.209 · Cited by 174
Regression kriging as a workhorse in the digital soil mapper's toolbox
Keskin, H., & Grunwald, S. (2018) · Geoderma · doi:10.1016/j.geoderma.2018.04.004 · Cited by 173
Song, X., Zhang, G., Liu, F., Li, D., Zhao, Y., & Yang, J. (2016) · Journal of Arid Land · doi:10.1007/s40333-016-0049-0 · Cited by 160
Hyper-scale digital soil mapping and soil formation analysis
Behrens, T., Schmidt, K., Ramírez-López, L., Gallant, J., Zhu, A., & Scholten, T. (2013) · Geoderma · doi:10.1016/j.geoderma.2013.07.031 · Cited by 132
Somarathna, P. D. S. N., Minasny, B., & Malone, B. (2017) · Soil Science Society of America Journal · doi:10.2136/sssaj2016.11.0376 · Cited by 122
Self-citationChile and the Chilean soil grid: A contribution to GlobalSoilMap
Padarian, J., Minasny, B., & McBratney, A. B. (2016) · Geoderma Regional · doi:10.1016/j.geodrs.2016.12.001 · Cited by 120
Self-citationThe ConMap approach for terrain‐based digital soil mapping
Behrens, T., Schmidt, K., Zhu, A., & Scholten, T. (2009) · European Journal of Soil Science · doi:10.1111/j.1365-2389.2009.01205.x · Cited by 94
Revealing the Controls of Soil Water Storage at Different Scales in a Hummocky Landscape
Biswas, A., & Si, B. (2011) · Soil Science Society of America Journal · doi:10.2136/sssaj2010.0131 · Cited by 92
Spatial structures of soil organic carbon in tropical forests—A case study of Southeastern Tanzania
Rossi, J., Govaerts, A., Vos, B. D., Verbist, B., Vervoort, A., Poesen, J., Muys, B., & Deckers, J. (2009) · CATENA · doi:10.1016/j.catena.2008.12.003 · Cited by 90
Multiscale contextual spatial modelling with the Gaussian scale space
Behrens, T., Schmidt, K., MacMillan, R. A., & Rossel, R. A. V. (2017) · Geoderma · doi:10.1016/j.geoderma.2017.09.015 · Cited by 77
Poggio, L., & Gimona, A. (2016) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2016.11.078 · Cited by 69
Including spatial correlation in structural equation modelling of soil properties
Angelini, M. E., & Heuvelink, G. B. M. (2018) · Spatial Statistics · doi:10.1016/j.spasta.2018.04.003 · Cited by 23
Cited by
Machine learning for digital soil mapping: Applications, challenges and suggested solutions
Wadoux, A. M. J.-C., Minasny, B., & McBratney, A. B. (2020) · Earth-Science Reviews · doi:10.1016/j.earscirev.2020.103359 · Cited by 731
Self-citationMachine learning and soil sciences: a review aided by machine learning tools
Padarian, J., Minasny, B., & McBratney, A. B. (2020) · SOIL · doi:10.5194/soil-6-35-2020 · Cited by 514
Self-citationDigital mapping of GlobalSoilMap soil properties at a broad scale: A review
Chen, S., Arrouays, D., Leatitia Mulder, V., Poggio, L., Minasny, B., Roudier, P., Libohova, Z., Lagacherie, P., Shi, Z., Hannam, J., et al. (2022) · Geoderma · doi:10.1016/j.geoderma.2021.115567 · Cited by 511
Self-citationLamichhane, S., Kumar, L., & Wilson, B. (2019) · Geoderma · doi:10.1016/j.geoderma.2019.05.031 · Cited by 509
Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran
Emadi, M., Taghizadeh-Mehrjardi, R., Cherati, A., Danesh, M., Mosavi, A., & Scholten, T. (2020) · Remote Sensing · doi:10.3390/rs12142234 · Cited by 278
Metadata
- Authors
- Padarian, J., Minasny, B., & McBratney, A. B.
- Venue
- SOIL
- Publisher
- Copernicus GmbH
- Published
- 2019-02-26
- Volume
- 5
- Issue
- 1
- Pages
- 79-89
- ISSN
- 2199-3971 (ISSN-L)
- 2199-398X
- OpenAlex
- W2890650850
- Cited by
- 326
- References
- 39
- FWCI
- 13.16
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.