Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: A review

Lamichhane, Sushil; Kumar, Lalit; Wilson, Brian

doi:10.1016/j.geoderma.2019.05.031

Cited by 287 publications

(146 citation statements)

References 188 publications

Supporting

Mentioning

106

Contrasting

Unclassified

Order By: Relevance

“…Together precipitation and temperature (MAT) explain 18.9% of the variation in SOC contents demonstrating the high dependencies of SOC contents in the province-scale to the climatic variables. Lamichhane et al [14] reviewed several studies and pointed out that climate is the most influential factor for the variation of SOC at large extents. The high precipitation is mostly combined with lower temperatures and slower SOC decomposition rates at higher altitudes [102,103].…”

Section: Selected Auxiliary Datamentioning

confidence: 99%

“…Due to the global importance of SOC, digital soil mapping (DSM) approaches have become more focused on SOC mapping in the last decade [4,[9][10][11][12]. DSM describes the spatial variation of SOC by taking the relations between SOC and environmental auxiliary variables into account [13][14][15]. The auxiliary variables correlated with SOC are often obtained from digital elevation models [11,16], remotely sensed data [16,17] and climatic data [18,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

et al. 2020

View full text Add to dashboard Cite

Estimation of the soil organic carbon (SOC) content is of utmost importance in understanding the chemical, physical, and biological functions of the soil. This study proposes machine learning algorithms of support vector machines (SVM), artificial neural networks (ANN), regression tree, random forest (RF), extreme gradient boosting (XGBoost), and conventional deep neural network (DNN) for advancing prediction models of SOC. Models are trained with 1879 composite surface soil samples, and 105 auxiliary data as predictors. The genetic algorithm is used as a feature selection approach to identify effective variables. The results indicate that precipitation is the most important predictor driving 14.9% of SOC spatial variability followed by the normalized difference vegetation index (12.5%), day temperature index of moderate resolution imaging spectroradiometer (10.6%), multiresolution valley bottom flatness (8.7%) and land use (8.2%), respectively. Based on 10-fold cross-validation, the DNN model reported as a superior algorithm with the lowest prediction error and uncertainty. In terms of accuracy, DNN yielded a mean absolute error of 0.59%, a root mean squared error of 0.75%, a coefficient of determination of 0.65, and Lin’s concordance correlation coefficient of 0.83. The SOC content was the highest in udic soil moisture regime class with mean values of 3.71%, followed by the aquic (2.45%) and xeric (2.10%) classes, respectively. Soils in dense forestlands had the highest SOC contents, whereas soils of younger geological age and alluvial fans had lower SOC. The proposed DNN (hidden layers = 7, and size = 50) is a promising algorithm for handling large numbers of auxiliary data at a province-scale, and due to its flexible structure and the ability to extract more information from the auxiliary data surrounding the sampled observations, it had high accuracy for the prediction of the SOC base-line map and minimal uncertainty.

show abstract

Section: Selected Auxiliary Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A few studies (less than five) use boosted regression tree (Yang et al, 2016;Beguin et al, 2017). In addition, a number of studies use neural networks (Lamichhane et al, 2019) algorithms (Aitkenhead & Coull, 2016;Guevara et al, 2018), such as artificial neural networks (Dai et al, 2014). A relatively small number of studies use alternative algorithms such as support vector machines (Guevara et al, 2018), k -nearest neighbours (Mansuy et al, 2014) or generalized boosted regression (Tziachris et al, 2019;Gomes et al, 2019).…”

Section: Machine Learning Modelsmentioning

confidence: 99%

Machine learning for digital soil mapping: applications, challenges and suggested solutions

Wadoux¹,

Minasny²,

McBratney³

2020

Preprint

View full text Add to dashboard Cite

The uptake of machine learning (ML) algorithms in digital soil mapping (DSM) is transforming the way soil scientists produce their maps. Machine learning is currently applied to mapping soil properties or classes much in the same way as other unrelated fields of science. Mapping of soil, however, has unique aspects which require adaptations of the ML algorithms. These features are for example, but not limited to, the inclusion of pedological knowledge into the ML algorithm, the accounting of spatial structure present in the soil data, or the desire to increase our scientific understanding of the distribution and genesis of soil from a calibrated ML model. Tackling these challenges is critical for machine learning to gain credibility and scientific consistency in soil science. In this article, we review the current applications of machine learning in digital soil mapping and suggest improvements. We found a growing interest of the use of ML in DSM. Most studies focus on obtaining accurate maps and disregard the characteristics of soil data, such as spatial autocorrelation. Only a few studies account for existing soil knowledge or quantify the uncertainty of the predicted maps. We then discuss the challenges related to the application of ML for soil mapping and offer solutions from existing studies in the natural sciences. The challenges are organized as follows: sampling, resampling, accounting for the spatial information, multivariate mapping, uncertainty analysis, validation, integration of pedological knowledge and, interpretation of the models. We conclude that for future developments, machine learning should incorporate three core elements: plausibility, interpretability, and explainability, which will trigger soil scientists to move beyond model prediction and towards explanation of soil processes.

show abstract

“…Since the processes driving pedogenesis are generally complex, there is a general trend in DSM studies to increase the complexity of the models. More advanced models such as tree-like models, neural networks, etc., tend to deal better with the complex non-linearities present in the data, usually outperforming more traditional methods such as generalised linear models (Lamichhane et al, 2019;Padarian et al, 2020). By 1 https://doi.org/10.5194/soil-2020-17 Preprint.…”

Section: Introductionmentioning

confidence: 99%

Game theory interpretation of digital soil mapping convolutional neural networks

Padarian¹,

McBratney²,

Minasny³

2020

Preprint

View full text Add to dashboard Cite

Abstract. The use of complex models such as deep neural networks has yielded large improvements in predictive tasks in many fields including digital soil mapping. Once of the concerns about using these models is that they are perceived as black boxes with low interpretability. In this paper we introduce the use of game theory, specifically SHAP values, in order to interpret a digital soil mapping model. SHAP values represent the contribution of a covariate to the final model predictions. We applied this method to a multi-task convolutional neural network trained to predict soil organic carbon of Chile. The results show the contribution of each covariate to the model predictions in three different contexts: (a) at a local level, showing the contribution of the various covariates for a single prediction, (b) a global understanding of the covariate contribution, and (c) a spatial interpretation of their contributions. The latter constitutes a novel application of SHAP values and also the first detailed analysis of a model in a spatial context. The analysis of a SOC model in Chile corroborated that the model is capturing sensible relationships between SOC and rainfall, temperature, elevation, slope and topographic wetness index. The results agree with commonly reported relationships, highlighting environmental thresholds that coincide with significant areas within the study area. This contribution addresses the limitations of the current interpretation of models in digital soil mapping, especially in a spatial context. We believe that SHAP values are a valuable tool that should be included within the DSM framework since they address the important concerns regarding the interpretability of more complex models. The model interpretation is a crucial step that could lead to generating new knowledge to improve our understanding of soils.

show abstract

Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: A review

Cited by 287 publications

References 188 publications

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran

Machine learning for digital soil mapping: applications, challenges and suggested solutions

Game theory interpretation of digital soil mapping convolutional neural networks

Contact Info

Product

Resources

About