Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates

Zeraatpisheh, Mojtaba; Garosi, Younes; Owliaie, Hamidreza; Ayoubi, Shamsollah; Taghizadeh–Mehrjardi, Ruhollah; Scholten, Thomas; Xu, Ming

doi:10.1016/j.catena.2021.105723

Cited by 92 publications

(32 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This study showed that MRVBF, temperature, rainfall, and TWI were the most important covariates for soil mapping (Figure 3). Mosleh et al [62] concluded that terrain attributes were the main predictors for predicting soil properties, while other studies demonstrated the importance of remotely sensed vegetation parameters in the semiarid regions of Iran [9,17].…”

Section: Variable Importance Analysismentioning

confidence: 99%

“…Machine learning (ML) techniques have increasingly been compared for identifying the best performing model for predicting soil variability [11]. Of the many ML algorithms currently used in DSM, studies have included the use of multiple linear regression [12], logistic regression [13], Random Forests [14][15][16][17], classification trees [18], support vector machines [17,19], and artificial neural networks [20]. However, with increasing computational power, more sophisticated and complex algorithms, such as convolutional neural networks, which are based on data-hungry, deep learning approaches, have been used to solve highly complex soil-landscape problems and to improve the prediction accuracy and decrease the uncertainty of digital soil maps [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

et al. 2022

Self Cite

View full text Add to dashboard Cite

This study tested and evaluated a suite of nine individual base learners and seven model averaging techniques for predicting the spatial distribution of soil properties in central Iran. Based on the nested-cross validation approach, the results showed that the artificial neural network and Random Forest base learners were the most effective in predicting soil organic matter and electrical conductivity, respectively. However, all seven model averaging techniques performed better than the base learners. For example, the Granger–Ramanathan averaging approach resulted in the highest prediction accuracy for soil organic matter, while the Bayesian model averaging approach was most effective in predicting sand content. These results indicate that the model averaging approaches could improve the predictive accuracy for soil properties. The resulting maps, produced at a 30 m spatial resolution, can be used as valuable baseline information for managing environmental resources more effectively.

show abstract

Section: Variable Importance Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…This data can describe the earth's surface with 3D (e.g., digital elevation models, digital surface model) or in the 2D data type (e.g., spectral bands, composites) acquired by sensors located on various platforms, e.g., satellite, airplane, or UAV. The acquired data can be used to produce various crucial remote sensing data such as [82]:…”

Section: Remote Sensing Datamentioning

confidence: 99%

“…A total of twelve relevant covariates for the P 2 O 5 and K 2 O prediction used as the basis of the modern prediction approach are presented in Table 4. These were defined with accordance to the specifications of soil mapping by Hengl and MacMillan [98] and which were used in similar soil prediction studies recently [66,73,82]. Six covariates were derived from a digital elevation model and six from Landsat 8 images, fully based on freely and widely available data.…”

Section: A Representative Overview Of Modern and Conventional Approac...mentioning

confidence: 99%

The Role of Remote Sensing Data and Methods in a Modern Approach to Fertilization in Precision Agriculture

2022

View full text Add to dashboard Cite

The precision fertilization system is the basis for upgrading conventional intensive agricultural production, while achieving both high and quality yields and minimizing the negative impacts on the environment. This research aims to present the application of both conventional and modern prediction methods in precision fertilization by integrating agronomic components with the spatial component of interpolation and machine learning. While conventional methods were a cornerstone of soil prediction in the past decades, new challenges to process larger and more complex data have reduced their viability in the present. Their disadvantages of lower prediction accuracy, lack of robustness regarding the properties of input soil sample values and requirements for extensive cost- and time-expensive soil sampling were addressed. Specific conventional (ordinary kriging, inverse distance weighted) and modern machine learning methods (random forest, support vector machine, artificial neural networks, decision trees) were evaluated according to their popularity in relevant studies indexed in the Web of Science Core Collection over the past decade. As a shift towards increased prediction accuracy and computational efficiency, an overview of state-of-the-art remote sensing methods for improving precise fertilization was completed, with the accent on open-data and global satellite missions. State-of-the-art remote sensing techniques allowed hybrid interpolation to predict the sampled data supported by remote sensing data such as high-resolution multispectral, thermal and radar satellite or unmanned aerial vehicle (UAV)-based imagery in the analyzed studies. The representative overview of conventional and modern approaches to precision fertilization was performed based on 121 samples with phosphorous pentoxide (P2O5) and potassium oxide (K2O) in a common agricultural parcel in Croatia. It visually and quantitatively confirmed the superior prediction accuracy and retained local heterogeneity of the modern approach. The research concludes that remote sensing data and methods have a significant role in improving fertilization in precision agriculture today and will be increasingly important in the future.

show abstract

“…The accumulation of SOC is affected by climatic conditions [8,9], topography [10], soil management, agricultural practices, land cover [11,12], and land-use changes [13,14]. Land-use change will lead to a change in the vegetation type and quantity and will affect the physical and chemical properties of the soil [15].…”

Section: Introductionmentioning

confidence: 99%

Deforestation for Agriculture Temporarily Improved Soil Quality and Soil Organic Carbon Stocks

Wang

Myo

et al. 2022

Forests

View full text Add to dashboard Cite

Deforestation for agricultural development or extension is a common land-use problem that may cause a series of changes in the ecological environment and soil carbon stock in planting systems. However, the response of soil physical, chemical properties and carbon stocks in agricultural systems in the initial period after deforestation have not been thoroughly examined, especially in the subsoil. We investigated the variations in the soil physicochemical properties and organic carbon stocks to a depth of 100 cm in a poplar (Populus deltoides cv. 35) plantation, a summer maize (Zea mays L.) followed by winter wheat (Triticum aestivum L.) field after 1 year of deforestation of a poplar plantation, and a wheat–maize rotation field used for decades. The soil bulk density and pH decreased, and the soil total nitrogen (TN), total phosphorus, and total potassium contents increased considerably. The soil organic carbon (SOC) content and stocks (to 100 cm) increased by 32.8% and 20.1%, respectively. The soil TN content was significantly (p < 0.001) positively correlated with the SOC content, and the C:N ratio increased for the field following deforestation. Furthermore, the nitrogen in the poplar plantation and the field following deforestation was limited. We recommend increasing the amount of nitrogen fertilizer following deforestation to improve fertility and this will be beneficial to SOC storage.

show abstract

Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates

Cited by 92 publications

References 75 publications

A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

A Comparison of Model Averaging Techniques to Predict the Spatial Distribution of Soil Properties

The Role of Remote Sensing Data and Methods in a Modern Approach to Fertilization in Precision Agriculture

Deforestation for Agriculture Temporarily Improved Soil Quality and Soil Organic Carbon Stocks

Contact Info

Product

Resources

About