Prediction Of Soil Properties Research Articles

Spatial prediction of soil properties using random forest, k-nearest neighbors and cubist approaches in the foothills of the Ural Mountains, Russia

Spatial prediction of soil properties using random forest, k-nearest neighbors and cubist approaches in the foothills of the Ural Mountains, Russia

A semi-empirical approach for estimating the lateral earth pressure on rigid retaining walls with EPS inclusions in cohesionless soils

Placing the expanded polystyrene (i.e. EPS) as inclusions between the rigid nonyielding wall and fill enables the lateral displacement of the fill and renders the lateral earth pressure from the at-rest state to the active state. This effectively alleviates the lateral load and facilitates cost-effective designs for rigid retaining walls. This study develops a semi-empirical approach to predict the lateral earth pressure on rigid retaining walls with EPS inclusions in cohesionless soils. This approach is simple and requires only conventional soil and EPS properties for prediction. Its performance is validated by the results of different physical and numerical modeling studies with EPS inclusions of various densities and thicknesses. It is demonstrated that (i) the lateral earth pressure depends on the stiffness of the EPS inclusions (i.e. the ratio of the elastic modulus to the thickness), and (ii) EPS inclusions with a single and proper thickness can fulfill the majority of load reduction purposes. Suggestions for the choices of (i) the EPS materials in terms of density and elastic modulus, (ii) the thickness of EPS inclusions, and (iii) the structure of the EPS inclusions are proposed for the use of EPS inclusions in cohesionless soils.

Towards Optimal Variable Selection Methods for Soil Property Prediction Using a Regional Soil Vis-NIR Spectral Library

Soil visible and near-infrared (Vis-NIR, 350–2500 nm) spectroscopy has been proven as an alternative to conventional laboratory analysis due to its advantages being rapid, cost-effective, non-destructive and environmentally friendly. Different variable selection methods have been used to deal with the high redundancy, heavy computation, and model complexity of using full spectra in spectral modelling. However, most previous studies used a linear algorithm in the variable selection, and the application of a non-linear algorithm remains poorly explored. To address the current knowledge gap, based on a regional soil Vis-NIR spectral library (1430 soil samples), we evaluated seven variable selection algorithms together with three predictive algorithms in predicting seven soil properties. Our results showed that Cubist overperformed partial least squares regression (PLSR) and random forests (RF) in most soil properties (R2 > 0.75 for soil organic matter, total nitrogen and pH) when using the full spectra. Most of variable selection can greatly reduce the number of spectral bands and therefore simplified predictive models without losing accuracy. The results also showed that there was no silver bullet for the optimal variable selection algorithm among different predictive algorithms: (1) competitive adaptive reweighted sampling (CARS) always performed best for the PLSR algorithm, followed by forward recursive feature selection (FRFS); (2) recursive feature elimination (RFE) and genetic algorithm (GA) generally had better accuracy than others for the Cubist algorithm; and (3) FRFS had the best model performance for the RF algorithm. In addition, the performance was generally better when the algorithm used in the variable selection matched the predictive algorithm. The outcome of this study provides a valuable reference for predicting soil information using spectroscopic techniques together with variable selection algorithms.

Evaluation of Mid-Infrared and X-ray Fluorescence Data Fusion Approaches for Prediction of Soil Properties at the Field Scale.

Previous studies investigating multi-sensor fusion for the collection of soil information have shown variable improvements, and the underlying prediction mechanisms are not sufficiently understood for spectrally-active and -inactive properties. Our objective was to study prediction mechanisms and benefits of model fusion by measuring mid-infrared (MIR) and X-ray fluorescence (XRF) spectra, texture, total and labile organic carbon (OC) and nitrogen (N) content, pH, and cation exchange capacity (CEC) for n = 117 soils from an arable field in Germany. Partial least squares regression models underwent a three-fold training/testing procedure using MIR spectra or elemental concentrations derived from XRF spectra. Additionally, two sequential hybrid and two high-level fusion approaches were tested. For the studied field, MIR was superior for organic properties (ratio of prediction to interquartile distance of validation (RPIQV) for total OC = 7.7 and N = 5.0)), while XRF was superior for inorganic properties (RPIQV for clay = 3.4, silt = 3.0, and sand = 1.8). Even the optimal fusion approach brought little to no accuracy improvement for these properties. The high XRF accuracy for clay and silt is explained by the large number of elements with variable importance in the projection scores >1 (Fe ≈ Ni > Si ≈ Al ≈ Mg > Mn ≈ K ≈ Pb (clay only) ≈ Cr) with strong spearman correlations (±0.57 < rs < ±0.90) with clay and silt. For spectrally-inactive properties relying on indirect prediction mechanisms, the relative improvements from the optimal fusion approach compared to the best single spectrometer were marginal for pH (3.2% increase in RPIQV versus MIR alone) but more pronounced for labile OC (9.3% versus MIR) and CEC (12% versus XRF). Dominance of a suboptimal spectrometer in a fusion approach worsened performance compared to the best single spectrometer. Granger-Ramanathan averaging, which weights predictions according to accuracy in training, is therefore recommended as a robust approach to capturing the potential benefits of multiple sensors.

Synergetic use of DEM derivatives, Sentinel-1 and Sentinel-2 data for mapping soil properties of a sloped cropland based on a two-step ensemble learning method

Understanding the spatial variability of soil organic matter (SOM), soil total nitrogen (STN), soil total phosphorus (STP), and soil total potassium (STK) is important to support site-specific agronomic management, food production, and climate change adaptation. High-resolution remote sensing imageries have emerged as an innovative solution to investigate the spatial variation in agricultural soils with machine learning (ML) algorithms. However, the predictive power of the individual and combined effects of Sentinel-1 (S1) synthetic aperture radar (SAR) and Sentinel-2 (S2) multispectral images for mapping soil properties, especially STN, STP, and STK, have rarely been investigated. Moreover, single ML model may achieve unstable performance for predicting multiple soil properties due to strong spatial heterogeneity. This study explored the combine use of S1, S2, and DEM derivatives to map SOM, STN, STP, and STK content of a sloped cropland of northeastern China. A two-step method with a weighted sum of four ML models was proposed to improve the accuracy and robustness in predicting multiple soil properties. Our results showed that single ML model has various performance in predicting the four soil properties. The optimal ML models could explain approximately 56 %, 53 %, 56 % and 37 % of the variability of SOM, STN, STP, and STK, respectively. Using the weights estimated through a 10-fold cross-validation procedure, the two-step ensemble learning model was retrained and showed more robust performance than the four ML models, in which the prediction accuracy was improved by 2.38 %, 1.40 %, 3.52 %, and 3.29 % for SOM, STN, STP, and STK, respectively. Our results also showed that the optical S2 derived features, especially the two S2 short-wave infrared bands, enhanced vegetation index, and soil adjusted vegetation index, were more important for soil property prediction than S1 data and DEM derivatives. Compared with individual sensor, a combination of S1 and S2 data yielded more accurate predictions of STN and STP but not for SOM and STK. The results of this study highlight the potential of high-resolution S1 and S2 data and the two-step method for soil property prediction at farmland scale.

Advancements in Soil Classification: An In-Depth Analysis of Current Deep Learning Techniques and Emerging Trends

Soil classification is essential to agriculture, environmental management, and civil engineering. In the recent past, deep-learning algorithms have had a profound effect on solving research challenges in various fields. Soil science has also benefited substantially from the implementation of time-saving and accurate deep-learning models. Deep learning techniques have demonstrated their potential for precisely classifying soil classes and predicting soil properties. In this paper, we provide a thorough analysis of the current techniques for classifying soil using deep learning models. We also discuss emerging trends in soil classification research, such as the use of lightweight models, multi-task learning models, and transfer learning. The advancements in soil classification were the focal point of this study. The study evaluates 12 research papers out of 150 publications initially retrieved from scholarly databases pertaining to the topic. The academic publications on deep learning models for soil classification were culled based on a set of predetermined criteria for obtaining the most profound understanding. To establish an effective method for soil identification, it is necessary to extract the features from the input images with care. This review suggests additional potential deep learning models that can be anticipated for improved soil identification results. The analysis concludes with an examination of the technical and non-technical errors made by scholars and a discussion of the ramifications for the future of soil identification. In addition, we emphasize the difficulties in soil classification, such as data imbalance, limited data availability, and the interpretability of models, and suggest potential solutions to resolve these issues. This in-depth analysis could support soil science researchers to propose more effective methods for soil identification.

Evaluating the Potentials of PLSR and SVR Models for Soil Properties Prediction Using Field Imaging, Laboratory VNIR Spectroscopy and Their Combination

Pedo-spectroscopy has the potential to provide valuable information about soil physical, chemical, and biological properties. Nowadays, we may predict soil properties using VNIR field imaging spectra (IS) such as Prisma satellite data or laboratory spectra (LS). The primary goal of this study is to investigate machine learning models namely Partial Least Squares Regression (PLSR) and Support Vector Regression (SVR) for the prediction of several soil properties, including clay, sand, silt, organic matter, nitrate NO3-, and calcium carbonate CaCO3, using five VNIR spectra dataset combinations (% IS, % LS) as follows: C1 (0% IS, 100% LS), C2 (20% IS, 80% LS), C3 (50% IS, 50% LS), C4 (80% IS, 20% LS) and C5 (100% IS, 0% LS). Soil samples were collected at bare soils and at the upper (0–30 cm) layer. The data set has been split into a training dataset 80% of the collected data (n = 248) and a validation dataset 20% of the collected data (n = 61). The proposed PLSR and SVR models were trained then tested for each dataset combination. According to our results, SVR outperforms PLSR for both: C1 (0% IS, 100% LS) and C5 (100% IS, 0% LS). For Soil Organic Matter (SOM) prediction, it achieves (R2 = 0.79%, RMSE = 1.42%) and (R2 = 0.76%, RMSE = 1.3%), respectively. The data fusion has improved the soil property prediction. The highest improvement was obtained for the SOM property (R2 = 0.80%, RMSE = 1.39) when using the SVR model and applying the second Combination C2 (20% of IS and 80% LS).

Rapid Detection of Soil Texture Attribute based on Mid-Infrared Spectral Library In Salt Affected Soils of Hungary

Quantifying among others the soil's physical properties is essential for the assessment of the diverse soil environmental functions including water balance of soils and pore structure, water erosion and various soil hydraulic properties. The mid-infrared (MIR) spectroscopy is a useful technique to predict soil attributes with high accuracy, efficiency and low cost. In this study, we examined the ability of our MIR soil spectral library in predicting the clay, silt, sand content of salt affected Hungarian soils. This research is part of a project to establish a MIR spectral library in the frame of the Hungarian Soil Information and Mentoring System (SIMS) survey. Salt affected soils type data was extracted from the spectral library then transformation of spectral reflectance values to absorbance values were performed. Moving average filtering method was applied to absorbance spectra before performing principal components analysis. To determine outlier samples and to select the proper samples for model calibration, Mahalanobis distance-based outlier detection method and Kennard-Stone Sampling selection method were applied on the principal component scores. Spectral and reference soil data were combined and split into training and testing datasets. MIR prediction models were built for sand, clay, and silt content using Partial Least Square Regression (PLSR) method. Coefficient determination, root mean square error and ratio performance to deviation were used to assess the models performance. The prediction accuracies of calibration sets for soil physical texture were excellent while the validation results were slightly lower but still with a good level of prediction.

A Novel Method of Combining Two-Dimensional Conversion Pre-Treatment with the Swin Transformer Model to Predict Soil Properties Based on Visual Near-Infrared Hyperspectra

A Novel Method of Combining Two-Dimensional Conversion Pre-Treatment with the Swin Transformer Model to Predict Soil Properties Based on Visual Near-Infrared Hyperspectra

Machine Learning Models for Prediction of Soil Properties in the Riparian Forests

Spatial variability of soil properties is a critical factor for the planning, management, and exploitation of soil resources. Thus, the use of different digital soil mapping models to provide accuracy plays a crucial role in providing soil physicochemical properties maps. Soil spatial variability in forest stands is not well-known in Iran. Meanwhile, riparian buffers are important for several services such as providing high water quality, nutrient recycling, and buffering agricultural production. Accordingly, in this research, 103 soil samples were taken using the Latin hypercubic method in the Maroon riparian forest of Behbahan and agricultural lands in the vicinity of the forest to evaluate the spatial variability of soil nitrogen, potassium, organic carbon, C:N ratio, pH, calcium carbonate, sand, silt, clay, and bulk density. Different machine learning models, including artificial neural networks, random forest, cubist regression tree, and k-nearest neighbor were used to compare the estimation of soil properties. Moreover, three main sources of spatial information including remote sensing images, digital elevation model, and climate parameters were used as ancillary data. Our results indicated that the random forest model has the best results in estimating soil pH, nitrogen, potassium, and bulk density. In contrast, the cubist regression tree indicated the best estimation for organic carbon, C:N ratio, phosphorous, and clay. Further, artificial neural networks showed the best estimation for calcium carbonate, sand, and silt contents. Our results revealed that geospatial information such as terrain parameters, climate parameters, and satellite images could be well used as ancillary data for the spatial mapping of soil physiochemical properties in riparian forests and agricultural lands. In conclusion, a specific machine learning model needs to be used for each soil property to provide highly accurate maps with less error.

Landscape Classification System Based on RKM Clustering for Soil Survey UAV Images–Case Study of the Small Hilly Areas in Jurong City

With the advantages of high accuracy, low cost, and flexibility, Unmanned Aerial Vehicle (UAV) images are now widely used in the fields of land survey, crop monitoring, and soil property prediction. Since the distribution of soil and landscape are closely related, this study makes use of the advantages of UAV images to classify the landscape to build a landscape classification system for soil investigation. Firstly, land use, object, and topographic factor were selected as landscape factors based on soil-forming factors. Then, based on multispectral images and Digital Elevation Models (DEM) acquired by UAV, object-oriented classification of different landscape factors was carried out. Additionally, we selected 432 sample data and validation data from the field survey. Finally, the landscape factor classification results were superimposed to obtain the landscape unit applicable to the system classification. The landscape classification system oriented to the soil survey was constructed by clustering 11,897 landscape units through the rough K-mean clustering algorithm. Compared to K-mean clustering, the rough K-mean clustering was better, with a Silhouette Coefficient of 0.26247 significantly higher than that of K-mean clustering. From the classification results, it can be found that the overall classification results are somewhat fragmented, but the landscape boundaries at the small area scale are consistent with the actual situation and the fragmented small spots are less. Comparing the small number of landscape boundaries obtained from the actual survey, we can find that the landscape boundaries in the landscape classification map are generally consistent with the actual landscape boundaries. In addition, through the analysis of two soil profile data within a landscape category, we found that the identified soil type of soil formation conditions and the landscape factor type of the landscape category is approximately the same. Therefore, this landscape classification system can be effectively used for soil surveys, and this landscape classification system is important for soil surveys to carry out the selection of survey routes, the setting of profile points, and the determination of soil boundaries.

Comparison of Machine Learning-Based Prediction of Qualitative and Quantitative Digital Soil-Mapping Approaches for Eastern Districts of Tamil Nadu, India

The soil–environmental relationship identified and standardised over the years has expedited the growth of digital soil-mapping techniques; hence, various machine learning algorithms are involved in predicting soil attributes. Therefore, comparing the different machine learning algorithms is essential to provide insights into the performance of the different algorithms in predicting soil information for Indian landscapes. In this study, we compared a suite of six machine learning algorithms to predict quantitative (Cubist, decision tree, k-NN, multiple linear regression, random forest, support vector regression) and qualitative (C5.0, k-NN, multinomial logistic regression, naïve Bayes, random forest, support vector machine) soil information separately at a regional level. The soil information, including the quantitative (pH, OC, and CEC) and qualitative (order, suborder, and great group) attributes, were extracted from the legacy soil maps using stratified random sampling procedures. A total of 4479 soil observations sampled were non-spatially partitioned and intersected with 39 environmental covariate parameters. The predicted maps depicted the complex soil–environmental relationships for the study area at a 30 m spatial resolution. The comparison was facilitated based on the evaluation metrics derived from the test datasets and visual interpretations of the predicted maps. Permutation feature importance analysis was utilised as the model-agnostic interpretation tool to determine the contribution of the covariate parameters to the model’s calibration. The R2 values for the pH, OC, and CEC ranged from 0.19 to 0.38; 0.04 to 0.13; and 0.14 to 0.40, whereas the RMSE values ranged from 0.75 to 0.86; 0.25 to 0.26; and 8.84 to 10.49, respectively. Irrespective of the algorithms, the overall accuracy percentages for the soil order, suborder, and great group class ranged from 31 to 67; 26 to 65; and 27 to 65, respectively. The tree-based ensemble random forest and rule-based tree models’ (Cubist and C5.0) algorithms efficiently predicted the soil properties spatially. However, the efficiency of the other models can be substantially increased by advocating additional parameterisation measures. The range and scale of the quantitative soil attributes, in addition to the sampling frequency and design, greatly influenced the model’s output. The comprehensive comparison of the algorithms can be utilised to support model selection and mapping at a varied scale. The derived digital soil maps will help farmers and policy makers to adopt precision information for making decisions at the farm level leading to productivity enhancements through the optimal use of nutrients and the sustainability of the agricultural ecosystem, ensuring food security.

Determination of Discrete Element Modelling Parameters of a Paddy Soil with a High Moisture Content (>40%)

Discrete element modelling (DEM) parameters are of great importance for the accurate prediction of soil properties and disturbance. This study aimed to provide an efficient method for accurately determining the DEM parameters of a paddy soil with a high moisture content (45.66%). The DEM parameters of the paddy soil modelled using the Hertz–Mindlin with JKR contact model were determined by using the Plackett–Burman (PB), steepest ascent, and central composite tests. The accuracies of the developed DEM models were evaluated using actual slumping tests. Based on the PB test, the surface energy of soil, coefficients of soil–soil rolling friction, and coefficients of soil–steel static friction exerted larger influences on the overall relative error (δZH). The optimization results showed that to achieve a minimum δZH (5.96%), the surface energy of soil, the coefficients of soil–soil rolling friction, and the coefficients of soil–steel static friction should be 0.808 J m−2, 0.11, and 0.6, respectively. The optimized DEM model had an overall relative error of 7.27% with a coefficient of variation of 1.32%, indicating that the DEM parameters of the calibrated paddy soil had good accuracy.

Assessing the Information Potential of MIR Spectral Signatures for Prediction of Multiple Soil Properties Based on Data from the AfSIS Phase I Project.

The aim of the study was to assess the predictive potential of mid-infrared (MIR) spectral response in the estimation of 60 soil properties. It is important to know the accuracy limitations in estimating various soil characteristics using various models in conditions of high spatial variability of the environment. To fully assess this potential, three types of algorithms were used in modeling, i.e., partial least squares (PLSR), one-dimensional convolutional neural network (1DCNN), and generalized regression neural network (GRNN). The research used data from 19 sub-Saharan African countries collected as part of the Africa Soil Information Service (AfSIS) Phase I project. The repositories provide 18,250 MIR reflectance recordings and nearly two thousand analytical data records from the determination of many soil properties by reference methods. The modeled subset of these properties included texture (three variables), bulk density, moisture content at soil water characteristic curves (SWCC, 4 variables), total and organic C and total N content (3 variables), total elemental content (32 variables), elemental content in bioavailable forms (12 variables), electrical conductivity, exchangeable acidity, exchangeable bases, pH, and phosphorus sorption index. It is not possible to indicate a universal optimal prediction model for all soil variables. The best prediction results are provided by all regression models for total and organic C, total Fe, total Al and bioavailable Al content, and pH. For bulk density, total N and total K content satisfactory results are provided by specific model type. Many other properties, i.e., texture, SWCC, total Ga, Rb, Na, Ca, Cu, Pb, Hg content, and bioavailable Ca and K content, can be predicted with accuracies sufficient for some less demanding tasks.

Combining mid infrared spectroscopy with stacked generalisation machine learning for prediction of key soil properties

AbstractAccurate assessment of key soil attributes such as soil organic carbon (OC), available phosphorus (P), and available potassium (K) using mid‐infrared spectroscopy (MIRS) is essential for better soil management in precision agriculture. However, the calibration of the portable version of MIRS is more challenging than the benchmark technologies, hence, demanding more efficient modelling methods to provide accurate outcomes. This research aims to use the stacked generalisation machine learning (SG–ML) framework, combining support vector machine (SVM), gradient boosted regression (GBR), and random forest (RF), using linear ridge regression as a meta learner, for predicting OC, P, and K using MIR spectra of 375 soil samples collected from four farms (Flanders, Belgium). The performance of the SG–ML models was compared with the multilayer perceptron (MLP) deep learning (DL) method. Results showed the superiority of the SG–ML method over the corresponding single ML and DL models. The predictive performance of SG–ML using the validation set was excellent for the three soil attributes, with coefficient of determination (R2) and root mean square error (RMSE) values of 0.88% and 0.10%, 0.85 and 4.53 mg 100 g−1, and 0.84 and 3.87 mg 100 g−1 for OC, K, and P, respectively. The performance of DL models were good for OC (R2 = 0.65, and RMSE = 0.17%), poor for K (R2 = 0.58 and RMSE = 7.59 mg 100 g−1), and very poor for P (R2 = 0.46, and RMSE = 6.57 mg 100 g−1). The SG–ML reduced the prediction RMSE by 10% to 31%, compared with the single ML (SVM, RF, and GBR) models. In summary, the proposed stacking method is a powerful modelling tool for the accurate prediction of key soil attributes using portable MIRS.Highlights Machine learning (ML) and deep learning (DL) models were developed based on mid‐infrared soil spectra. The stacked generalisation ML (SG–ML) was compared with ML and DL for predicting OC, P, and K. SG–ML models outperformed ML (GBR, RF, and SVM) and deep learning (DL) models. The SG–ML models significantly decreased RMSE by 10% to 31% compared with the single ML models.

Combining Proximal and Remote Sensors in Spatial Prediction of Five Micronutrients and Soil Texture in a Case Study at Farmland Scale in Southeastern Brazil

Despite the increasing adoption of proximal sensors worldwide, rare works have coupled proximal with remotely sensed data to spatially predict soil properties. This study evaluated the contribution of proximal and remotely sensed data to predict soil texture and available contents of micronutrients using portable X-ray fluorescence (pXRF) spectrometry, magnetic susceptibility (MS), and terrain attributes (TA) via random forest algorithm. Samples were collected in Brazil from soils with high, moderate, and low weathering degrees (Oxisols, Ultisols, Inceptisols, respectively), and analyzed by pXRF and MS and for texture and available micronutrients. Seventeen TA were generated from a digital elevation model of 12.5 m spatial resolution. Predictions were made via: (i) TA; (ii) TA + pXRF; (iii) TA + MS; (iv) TA + MS + pXRF; (v) MS + pXRF; and (vi) pXRF; and validated via root mean square error (RMSE) and coefficient of determination (R2). The best predictions were achieved by: pXRF dataset alone for available Cu (R² = 0.80) and clay (R2 = 0.67) content; MS + pXRF dataset for available Fe (R2 = 0.68) and sand (R2 = 0.69) content; TA + pXRF + MS dataset for available Mn (R2 = 0.87) content. PXRF data were key to the best predictions. Soil property maps created from these predictions supported the adoption of sustainable soil management practices.

Vis–NIR spectroscopy and machine learning methods to diagnose chemical properties in Colombian sugarcane soils

Knowing chemical soil properties could determine crop management and total production. Traditional analytical tests are time-consuming, preventing farmers from promptly taking action to achieve optimal plant and soil nutrition. The estimation of chemical properties from its spectral signal, Vis–NIRS (range from 400 to 2500 nm), is a low-cost, non-invasive, non-destructive, and fast alternative. We tested and compared four regression and six classification techniques to estimate soil chemical properties using soil samples vis–NIR spectra from the highest production region of Non-Centrifugal Sugarcane (NCS) in Colombia. The regressors models were Linear Regression (LR), Support Vector Regression (SVR), Least Absolute Shrinkage and Selection Operator (LASSO), and Cubist. The classifiers were binary trees, linear and quadratic discriminant, Naive Bayes, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Ensemble-based architectures. Estimated properties were pH, soil organic matter and exchangeable Ca, Na, K, and Mg. We compared performance in soil property prediction, both numerical values and category labels obtained from regressors and classifiers, respectively. We obtained acceptable predictions using a regression for pH (R2=0.81, ρ=0.9), OM (R2=0.37, ρ=0.63), Ca (R2=0.55, ρ=0.75), Mg (R2=0.44, ρ=0.67), confirming the predictive performance reported in the literature. Additionally, we labeled pH (Acc = 0.87), OM (Acc = 0.73), Ca (Acc = 0.72), and Na (Acc = 0.99) with acceptable accuracy.The variability of the soil matrix of the sampling area is an important and valuable limitation for the construction of models. Our results suggest that labeled soil samples and machine learning classifiers might help as a potential tool for supporting decision-making processes in soil and plant nutrition for agriculture.

Spectral assessment of soil properties in semi-arid tropical regions of southern Karnataka Plateau

ABSTRACT The present study assessed the visible and short wave infrared (VNIR-SWIR) laboratory spectroscopy coupled random forest regression (RF) technique for predicting soil properties in the southern Karnataka Plateau, India. The spectral data acquired for about 228 profile samples were used to predict key soil properties. The RF model fits well for the spectral prediction of clay (R2 = 0.65), sand (R2 = 0.60), cation exchange capacity (R2 = 0.74), field capacity (R2 = 0.65) and permanent wilting point (R2 = 0.72). Wherein soil organic carbon was poorly predicted with an R2 of 0.22 and RPD of 1.2 due to its lower content and narrow range (0.8 to 20 g kg−1). The spectral assessment by PCA showed that the first (50%) and third (34%) components had high spectral variation and significantly correlated with soil properties such as pH, CEC, clay, FC, and PWP related to wavelengths indicating clay minerals and iron oxides. However, the second component had less spectral variation (13%) that is related to wavelengths indicating various organic components and correlated well with SOC. Thus, the VNIR-SWIR spectroscopy could be a suitable supplementary method for rapidly predicting soil properties related to clay minerals and iron oxides.

Prediction of the soil properties of Malagasy rice soils based on the soil color and magnetic susceptibility

ABSTRACT Accurate assessments of soil properties are required to improve fertilizer management practices for crop production. Conventional chemical analysis in the laboratory is costly and time-consuming. Soil color is related to different soil compositions, while soil magnetic susceptibility (MS) has been found to reflect the abundance of magnetic minerals relevant to soil properties. Improving proximal sensing techniques for the analysis of soil color and MS provides opportunities for affordable and rapid assessments of soil properties. The aim of this study was to evaluate the potential use of soil color parameters and MS values to predict soil properties using stepwise multiple linear regression (SMLR), random forest (RF), and nonlinear regression approaches in lowland and upland fields in the central highlands of Madagascar. The target properties included the contents of soil organic carbon (SOC), total nitrogen (TN), oxalate-extractable phosphorus and iron (Feox), and the soil texture. The model prediction accuracy was assessed using the coefficient of determination (R2), root-mean-square error (RMSE), and the ratio of performance to interquartile distance (RPIQ). The use of soil color parameters yielded an acceptable prediction accuracy of the Feox content (loge Feox) for all rice fields (R2 = 0.54, RMSE = 0.55, RPIQ = 1.70) using the RF algorithm, while the SMLR approach gave the most accurate prediction for upland fields with acceptable reliabilities for SOC, Feox, and clay and sand content prediction, with R2 ranging from 0.43 to 0.67 and RPIQ from 1.63 to 1.77. In lowland fields, TN content was predicted with acceptable accuracy (R2 = 0.34, RMSE = 0.49, RPIQ = 1.71) using SMLR with the color parameter. The combination of the soil color parameters with the MS value as predictor variables increased SOC prediction for lowland fields using the RF approach (R2 = 0.57, RMSE = 6.37, RPIQ = 1.96). Use of the soil color and MS parameters was revealed to be a promising way to simplify the assessment of soil properties in upland and lowland ecosystems by using RF and SMLR approaches. A combined use of the soil color and MS parameters improved the prediction accuracy for the SOC content.

Spatial prediction of soil properties through hybridized random forest model and combination of reflectance spectroscopy and environmental covariates

Spatial information on land and soil resources are critical towards addressing land degradation for ensuring sustainable soil and crop management. To address these needs, digital soil mapping techniques have emerged as an efficient and low-cost solution. Although digital soil mapping has typically leveraged geospatial environmental variables (e.g. remote sensing), the application and integration of spectroscopic data with those environmental variables remain limited. Hence, this study combines visible and near-infrared (Vis-NIR) spectroscopy, remote sensing, and topographic data and applies random forests, hybridized with particle swarm optimization algorithm (RF + PSO), to predict the spatial variability of soil clay content, electrical conductivity (EC), and calcium carbonate equivalent (CCE) for 370 km2 of agricultural land in western Iran. Using a conditioned Latin hypercube approach, 220 soil samples at the 0–20 cm depth increment were acquired throughout the study area. Three sets of environmental covariates were tested: Scenario A (Vis-NIR spectroscopy data), Scenario B (environmental data), and Scenario C (Vis-NIR spectroscopy + environmental data). According to the 10-fold cross-validation procedure with 100 replications, the RF + PSO model showed an acceptable level accuracy for all scenarios, although the accuracy of the RF + PSO model using the Scenario C data was higher than all other scenarios: the Lin’s Concordance Correlation Coefficient values were 0.77, 0.83, and 0.74 for the clay contents, EC, and CCE, respectively. The results demonstrated that the combination of Vis-NIR spectroscopic data and commonly available environmental covariates provided the best input data for the hybridized model and enhanced its performance.