In the last two decades, machine learning (ML) methods have been widely used in digital soil mapping (DSM), but the regression kriging (RK) model which combines the advantages of the ML and kriging methods has rarely been used in DSM. In addition, due to the limitation of a single-model structure, many ML methods have poor prediction accuracy in undulating terrain areas. In this study, we collected the SOC content of 115 soil samples in a hilly farming area with continuous undulating terrain. According to the theory of soil-forming factors in pedogenesis, we selected 10 topographic indices, 7 vegetation indices, and 2 soil indices as environmental covariates, and according to the law of geographical similarity, we used ML and RK methods to mine the relationship between SOC and environmental covariates to predict the SOC content. Four ensemble models—random forest (RF), Cubist, stochastic gradient boosting (SGB), and Bayesian regularized neural networks (BRNNs)—were used to fit the trend of SOC content, and the simple kriging (SK) method was used to interpolate the residuals of the ensemble models, and then the SOC and residual were superimposed to obtain the RK prediction result. Moreover, the 115 samples were divided into calibration and validation sets at a ratio of 80%, and the tenfold cross-validation method was used to fit the optimal parameters of the model. From the results of four ensemble models: RF performed best in the calibration set (R²_c = 0.834) but poorly in the validation set (R²_v = 0.362); Cubist had good accuracy and stability in both the calibration and validation sets (R²_c = 0.693 and R²_v = 0.445); SGB performed poorly (R²_c = 0.430 and R²_v = 0.336); and BRNN had the lowest accuracy (R²_c = 0.323 and R²_v = 0.282). The results showed that the R² of the four RK models in the validation set were 0.718, 0.674, 0.724, and 0.625, respectively. Compared with the ensemble models without superimposed residuals, the prediction accuracy was improved by 0.356, 0.229, 0.388, and 0.343, respectively. In conclusion, Cubist has high prediction accuracy and generalization ability in areas with complex topography, and the RK model can make full use of trends and spatial structural factors that are not easy to mine by ML models, which can effectively improve the prediction accuracy. This provides a reference for soil survey and digital mapping in complex terrain areas.

In digital soil mapping, machine learning models have been widely applied. However, the accuracy of machine learning models can be limited by the use of a single model and a small number of soil samples. This study introduces a novel method, semi-supervised classification combined with stacking learning (SSC-SL), to enhance soil classification mapping in hilly and low-mountain areas of Northern Jurong City, Jiangsu Province, China. This study incorporated Gaofen-2 (GF-2) remote sensing imagery along with its associated remote sensing indices, the ALOS Digital Elevation Model (DEM) and their derived topographic factors, and soil parent material data in its modelling process. We first used three base learners, Ranger, Rpart, and XGBoost, to construct the SL model. In addition, we employed the fuzzy c-means clustering algorithm (FCM) to construct a clustering map. To fully leverage the information from a multitude of environmental variables, understand the distribution of data, and enhance the effectiveness of the classification, we selected unlabelled samples near the boundaries of the patches on the clustering map. The SSC-SL model demonstrated superior stability and performance, with optimal accuracy at a 0.9 confidence level, achieving an overall accuracy of 0.77 and a kappa coefficient of 0.73. These metrics exceeded those of the highest performing base learner (Ranger model) by 10.4% and 12.3%, respectively, and they outperformed the least effective base learner (Rpart model) by 27.3% and 32.9%. It notably improves the spatial distribution accuracy of soil types. Key environmental variables influencing soil type distribution include soil parent material (SPM), land use (LU), the multi-resolution valley bottom flatness index (MRVBF), and Elevation (Ele). In conclusion, the SSC-SL model offers a novel and effective approach for enhancing the predictive accuracy of soil classification mapping.

Soil texture is one of the most important physical properties of soil and plays a crucial role in determining its suitability for crop cultivation. Currently, supervised classification machine learning methods are most commonly used in digital soil mapping. However, these methods may not yield optimal predictive performance due to the limited number of soil samples. Therefore, we propose using Constrained K-Means Clustering to combine a small number of labeled samples with a large amount of unlabeled data, thereby achieving improved prediction in soil texture mapping. In this study, we focused on a typical hilly region in northern Jurong City, Jiangsu Province, China, and used Constrained K-Means Clustering as our mapping model. GF-2 remote sensing imagery and the ALOS digital elevation model (DEM), along with their derived variables, were employed as environmental variables. In Constrained K-Means Clustering, the choice of distance method is a key parameter. Here, we used four different distance methods (euclidean, maximum, manhattan, and canberra) and compared the results with those of the random forest (RF) and multilayer perceptron (MLP) models. Notably, the euclidean distance method within Constrained K-Means Clustering achieved the highest overall accuracy ($OA$), $Kappa$ coefficient, and $MacroF1Score$, with values of 0.77, 0.68, and 0.75, respectively. These methods were higher than those obtained by the RF and MLP models by 0.12, 0.18, and 0.12, and 0.18, 0.26, and 0.18, respectively. This indicates that Constrained K-Means Clustering demonstrates strong predictive performance in soil texture mapping. Moreover, land use (LU), multi-resolution of ridge top flatness index (MRRTF), topographic position index (TPI), and plan curvature (PlC) emerged as the key environmental variables for predicting soil texture. Overall, Constrained K-Means Clustering proves to be an effective digital soil mapping approach, offering a novel perspective for soil texture mapping with limited samples.

Soil surveying and mapping provide important support for environmental science research on soil and other resources. Due to the rapid change in land use and the long update cycle of soil maps, historical conventional soil maps (CSMs) may be outdated and have low accuracy. Therefore, there is an urgent need for accurate and up-to-date soil maps. Soil has a high correlation with its corresponding environmental factors in space, and typical samples contain an appropriate soil–environment relationship of soil types. Understanding how to extract typical samples according to environmental factors and determine the implied soil–environment relationship is the key to updating soil maps. In this study, a hierarchical typical sample extraction method based on land use type and environmental factors was designed. According to the corresponding relationship between the soil type and the land use type (ST-LU), the outdate soil map patches caused by changes in land use were excluded, follow by typical samples being extracted according to the peak intervals of the soil–environmental factor histograms. Additionally, feature selection was performed through variance analysis and mutual information, and four machine learning models were used to predict soil types. In addition, the influence of environmental factors on soil prediction was discussed, in terms of variable importance analysis. Using an overall common validation set, the results show that the prediction accuracy using typical samples for learning in the modeling set is above 0.8, while the prediction accuracy when using random samples is only about 0.4. Compared with the original soil map, the accuracy and resolution of the predicted soil maps based on typical samples are greatly improved. In general, typical samples can effectively explore the actual soil–environment knowledge implied in the soil type map. By extracting typical samples from historical soil type map and combining them with high-resolution remote sensing data, we can generate new soil type maps with high accuracy and short update cycle. This can provide some references for typical sampling design and soil type prediction.

Topography is one of the dominant factors in regional soil formation and development. Soil distribution has a certain pattern from high to low in space, and this pattern has a high degree of consistency with slope position. Most of the current research on soil mapping uses landscape types generated by existing methods directly as environmental covariates, and there are few landscape classification methods specifically oriented toward soil surveys. There is rarely any research on landform classification using relative slope position (RSP) and elevation. Therefore, we designed a landform classification method based on RSP and elevation, Terrainforms (TF), and combined the landform type with land use type to construct soil–landscape units for soil type and attribute spatial prediction. In this study, two commonly used landform classification methods, Geomorphons and Landforms, were also used to compare with this design method. It was found that the constructed soil–landscape units had a high consistency with the soil spatial distribution. The landform types based on RSP and elevation obtained the second-highest prediction accuracy in both soil type and soil organic carbon (SOC), and the constructed soil–landscape types obtained the highest prediction accuracy. The results show that the landform classification method based on RSP and elevation is not easily limited by the analysis scale, and is an efficient and accurate landform classification method. The TF landform type and its constructed soil–landscape types can be used as an important environmental variable in soil prediction and sampling, which can provide some guidance and reference for landform classification and digital soil mapping.

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.