Application GIS and remote sensing for soil organic carbon mapping in a farm-scale in the hilly area of central Vietnam

Abstract

Soil Organic Carbon (SOC) influences many soil properties including nutrient and water holding capacity, nutrient cycling and stability, improved water infiltration and aeration. It also is an essential parameter in the assessment of soil quality, especially for agricultural production. However, SOC mapping is a complicated process that is costly and time-consuming due to the physical challenges of the natural conditions that is being surveyed. The best model for SOC mapping is still in debate among many researchers. Recently, the development of machine learning and Geographical Information Systems (GIS) has provided the potential for more accurate spatial prediction of SOC content. This research was conducted in a relatively small-scale capacity in the Central Vietnam region. The aim of this study is to compare the accuracy of Inverse Distance Weighting (IDW), Ordinary Kriging (OK), and Random Forest (RF) methods for SOC interpolation, with a dataset of 47 soil samples for an area of 145 hectares. Three environmental variables including elevation, slope, and the Normalized Difference Vegetation Index (NDVI) were used for the RF model. In the RF model, the values of the number of variables randomly sampled as candidates at each split, (mtry), and the number of bootstrap replicates, (ntree), were determined in terms of 1 and 1,000 respectively The results at our research site showed that using IDW is the most accurate method for SOC mapping, followed by the methods of RF and OK respectively. Concerning SOC mapping based-on auxiliary variables, in areas where there is human activity, the selection of auxiliary variables should be carefully considered because the variation in the SOC may not only be due to environmental variables but also by farming technologies.

Towards Improving Sustainable Water Management in Geothermal Fields: SVM and RF Land Use Monitoring

“…These parameter adjustments are crucial for optimizing land use classification accuracy and ensuring the models' predictive performance accurately reflects changing environmental conditions. Understanding and fine-tuning these characteristics allows practitioners to effectively employ SVM and RF models in various analytical scenarios, facilitating accurate land use monitoring and sustainable water management methods in geothermal areas [60][61][62].…”

“…A low training error indicates that the model has learned well from the training data [61]. RF uses parameters such as 'mtry,' which determines the number of features considered when searching for the best split at each tree node and the number of trees, which increases the accuracy of the model to a certain extent [62]. The 'Number of Variables Attempted at Each Split' parameter guides the algorithm to consider many variables in the decision process, while the Out-of-Bag (OOB) error rate estimate provides an unbiased picture of the model's accuracy [51].…”

“…Such thorough parameter adjustment is critical for applications that need high model accuracy, such as ecological modeling or disease prediction. Understanding the implications of these settings can guide practitioners in refining RF models to achieve higher precision in diverse analytical contexts [51,62].…”

Characterizing, Predicting, and Mapping Soil Available Phosphor, pH, and Electrical Conductivity in Rubber Plantation Based on Three Different Methods of Ordinary Kriging in GIS Environment

“…Interpolation was conducted to display the spatial variability. Interpolation as the method for estimating the values of un-sampled locations from sampled locations [11]- [16] has been prominently used in previous studies [17], [8]. However, it is evidence that the studies are rarely found in elaborating interpolation methods for soil properties in a rubber plantation.…”

Effects of spatial data resolution on the modelling and mapping of soil organic carbon content in hill country grassland landscapes

“…The ability to quantify the spatially explicit pattern of SOC in a complex farmed landscape provides a picture of SOC content across space, and this information can be utilized to prioritize target areas for soil carbon management towards maintaining and enhancing soil health. Some studies have applied straightforward interpolation techniques or down‐scaling approaches to produce farm level SOC map information (Dewage et al, 2020; Malone et al, 2017; Van Huynh et al, 2022). However, these methods are not very effective in describing the pattern of SOC in areas with heterogenous landscapes.…”