Machine-Learning Classification of Soil Bulk Density in Salt Marsh Environments

Long-Term Benefits of Cenchrus fungigraminus Residual Roots Improved the Quality and Microbial Diversity of Rhizosphere Sandy Soil through Cellulose Degradation in the Ulan Buh Desert, Northwest China

Long-term plant residue retention can effectively replenish soil quality and fertility. In this study, we collected rhizosphere soil from the residual roots of annual Cenchrus fungigraminus in the Ulan Buh Desert over the past 10 years. The area, depth, and length of these roots decreased over time. The cellulose content of the residual roots was significantly higher in the later 5 years (2018-2022) than the former 5 years (2013-2017), reaching its highest value in 2021. The lignin content of the residual roots did not differ across samples except in 2015 and reached its highest level in 2021. The total sugar of the residual roots in 2022 was 227.88 ± 30.69 mg·g-1, which was significantly higher than that in other years. Compared to the original sandy soil, the soil organic matter and soil microbial biomass carbon (SMBC) contents were 2.17-2.41 times and 31.52-35.58% higher in the later 3 years (2020-2022) and reached the highest values in 2020. The residual roots also significantly enhanced the soil carbon stocks from 2018-2022. Soil dehydrogenase, nitrogenase, and N-acetyl-β-D-glucosidase (S-NAG) were significantly affected from 2019-2022. The rhizosphere soil community richness and diversity of the bacterial and fungal communities significantly decreased with the duration of the residual roots in the sandy soil, and there was a significant difference for 10 years. Streptomyces, Bacillus, and Sphigomonas were the representative bacteria in the residual root rhizosphere soil, while Agaricales and Panaeolus were the enriched fungal genera. The distance-based redundancy analysis and partial least square path model results showed that the duration of residual roots in the sandy soil, S-NAG, and SMBC were the primary environmental characteristics that shaped the microbial community. These insights provide new ideas on how to foster the exploration of the use of annual herbaceous plants for sandy soil improvement in the future.

Pedotransfer Functions for Estimating Soil Bulk Density Using Image Analysis of Soil Structure

Soil bulk density is one of the most important soil properties. When bulk density cannot be measured by direct laboratory methods, prediction methods are used, e.g., pedotransfer functions (PTFs). However, existing PTFs have not yet incorporated information on soil structure although it determines soil bulk density. We aimed therefore at development of new PTFs for predicting soil bulk density using data on soil macrostructure obtained from image analysis. In the laboratory soil bulk density (BD), texture and total organic carbon were measured. On the basis of image analysis, soil macroporosity was evaluated to calculate bulk density by image analysis (BDim) and number of macropore cross-sections of diameter ≥5 mm was determined and classified (MP5). Then, we created PTFs that involve soil structure parameters, in the form BD~BDim + MP5 or BD~BDim. We also compared the proposed PTFs with selected existing ones. The proposed PTFs had mean prediction error from 0 to -0.02 Mg m^-3, modelling efficiency of 0.17-0.39 and prediction coefficient of determination of 0.35-0.41. The proposed PTFs including MP5 better predicted boundary BDs, although the intermediate BD values were more scattered than for the existing PTFs. The observed relationships indicated the usefulness of image analysis data for assessing soil bulk density which enabled to develop new PTFs. The proposed models allow to obtain the bulk density when only images of the soil structure are available, without any other data.

Using machine learning algorithms to predict groundwater levels in Indonesian tropical peatlands

Tropical peatlands play a vital role in the global carbon cycle as large carbon reservoirs and substantial carbon sinks. Indonesia possesses the largest share (65 %) of tropical peat carbon, equal to 57.4 Gt C. Human perturbations such as extensive logging, deforestation and canalization exacerbate water losses, especially during dry seasons, when low precipitation and high evapotranspiration rates combine with the increased drainage to lower groundwater levels. Drying and increasing temperatures of the surface peat exacerbate ignition and wildfire risks within the peat soils. As such, it is critically important to know how groundwater levels in peatlands are changing over space and time. In this study, a multilinear regression model as well as two machine learning algorithms, random forest and extreme gradient boosting, were used to model groundwater level over the study period (2010-12) within a peat dome impacted by drainage canals and multiple wildfires in Central Kalimantan, Indonesia. Although all three models performed well, based on overall fit, spatial modeling of groundwater level results revealed that extreme gradient boosting (R² = 0.998, RMSE = 0.048 m) outperformed random forest (R² = 0.997, RMSE = 0.054 m) and multilinear regression (R² = 0.970, RMSE = 0.221 m) near drainage canals, which are key fire ignition risk locations in the peatlands. Our study also shows that, on average, elevation and precipitation are the most important parameters influencing groundwater level spatiotemporally.

Remote Sensing of Surface and Subsurface Soil Organic Carbon in Tidal Wetlands: A Review and Ideas for Future Research

Tidal wetlands, widely considered the most extensive reservoir of soil organic carbon (SOC), can benefit from remote sensing studies enabling spatiotemporal estimation and mapping of SOC stock. We found that a majority of the remote-sensing-based SOC mapping efforts have been focused on upland ecosystems, not on tidal wetlands. We present a comprehensive review detailing the types of remote sensing models and methods used, standard input variables, results, and limitations for the handful of studies on tidal wetland SOC. Based on that synthesis, we pose several unexplored research questions and methods that are critical for moving tidal wetland SOC science forward. Among these, the applicability of machine learning and deep learning models for predicting surface SOC and the modeling requirements for SOC in subsurface soils (soils without a remote sensing signal, i.e., a soil depth greater than 5 cm) are the most important. We did not find any remote sensing study aimed at modeling subsurface SOC in tidal wetlands. Since tidal wetlands store a significant amount of SOC at greater depths, we hypothesized that surface SOC could be an important covariable along with other biophysical and climate variables for predicting subsurface SOC. Preliminary results using field data from tidal wetlands in the southeastern United States and machine learning model output from mangrove ecosystems in India revealed a strong nonlinear but significant relationship (r2 = 0.68 and 0.20, respectively, p < 2.2 × 10−16 for both) between surface and subsurface SOC at different depths. We investigated the applicability of the Soil Survey Geographic Database (SSURGO) for tidal wetlands by comparing the data with SOC data from the Smithsonian’s Coastal Blue Carbon Network collected during the same decade and found that the SSURGO data consistently over-reported SOC stock in tidal wetlands. We concluded that a novel machine learning framework that utilizes remote sensing data and derived products, the standard covariables reported in the limited literature, and more importantly, other new and potentially informative covariables specific to tidal wetlands such as tidal inundation frequency and height, vegetation species, and soil algal biomass could improve remote-sensing-based tidal wetland SOC studies.

Object-Based Multigrained Cascade Forest Method for Wetland Classification Using Sentinel-2 and Radarsat-2 Imagery

The development of advanced and efficient methods for mapping and monitoring wetland regions is essential for wetland resources conservation, management, and sustainable development. Although remote sensing technology has been widely used for detecting wetlands information, it remains a challenge for wetlands classification due to the extremely complex spatial patterns and fuzzy boundaries. This study aims to implement a comprehensive and effective classification scheme for wetland land covers. To achieve this goal, a novel object-based multigrained cascade forest (OGCF) method with multisensor data (including Sentinel-2 and Radarsat-2 remote sensing imagery) was proposed to classify the wetlands and their adjacent land cover classes in the wetland National Natural Reserve. Moreover, a hybrid selection method (ReliefF-RF) was proposed to optimize the feature set in which the spectral and polarimetric decomposition features are contained. We obtained six spectral features from visible and shortwave infrared bands and 10 polarimetric decomposition features from the H/A/Alpha, Pauli, and Krogager decomposition methods. The experimental results showed that the OGCF method with multisource features for land cover classification in wetland regions achieved the overall accuracy and kappa coefficient of 88.20% and 0.86, respectively, which outperformed the support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and deep neural network (DNN). The accuracy of the wetland classes ranged from 75.00% to 97.53%. The proposed OGCF method exhibits a good application potential for wetland land cover classification. The classification scheme in this study will make a positive contribution to wetland inventory and monitoring and be able to provide technical support for protecting and developing natural resources.