Journal Paper Digests 2021 #21
- Soil organic carbon estimation using VNIR-SWIR spectroscopy: The effect of multiple sensors and scanning conditions
- Using ground-penetrating radar to investigate the thickness of mollic epipedons developed from loessial parent material
- Evaluating validation strategies on the performance of soil property prediction from regional to continental spectral data
- Digital soil maps can perform as well as large-scale conventional soil maps for the prediction of catchment baseflows
- Estimation of root zone soil moisture from ground and remotely sensed soil information with multisensor data fusion and automated machine learning
Soil organic carbon estimation using VNIR-SWIR spectroscopy: The effect of multiple sensors and scanning conditions
Visible-near infrared-shortwave infrared (VNIR-SWIR) spectroscopy is being increasingly used for soil organic carbon (SOC) assessment. Common practice consists of scanning soil samples using a single spectrometer. Considerations have rarely been documented of the effects of using multiple instruments and scanning conditions on SOC model calibration that occur when merging soil spectral libraries (SSLs), particularly in soils with low SOC concentration and using both field spectroradiometers and laboratory fixed spectrometers. To address this gap, we scanned 143 low-SOC-content soil samples using three spectrometers (ASD FieldSpec 3, ASD FieldSpec 4, and FOSS XDS) and four setup features - FOSS, contact probe (CP), dark-box (DB), and open laboratory (LAB) - at three laboratories. The application of an internal soil standard (ISS) to align one laboratory spectrum with another for spectral correction and spectral merging of various SSLs was examined. SOC models were developed using i) data from each single spectrometer - single laboratory separately and ii) merged data from multiple spectrometers - different laboratories, applying the 1st derivatives of spectra and random forest (RF) regression. The results indicate that the spectral shape and wavelength position of key features obtained from all spectrometers and setups did not show any noticeable differences, though spectra based on FOSS setup, particularly on low-SOC samples, demonstrated greater range in absolute derivative values regardless of ISS application. The derivative ISS-corrected spectra showed less variation among different spectrometers compared to their uncorrected raw reflectance spectra. All single spectrometer models predicted SOC reasonably well. However, the spectra acquired by the FOSS setup predicted SOC more accurately (R2 = 0.77, RPIQ = 3.30, RMSE = 0.22 %, and SD = 0.04) than the spectra acquired by the other setups. The models derived from merged uncorrected raw reflectance spectra yielded poor results (R2 = 0.48, RPIQ = 2.33, RMSE = 0.33 %, and SD = 0.10); nevertheless, assessment of SOC using the 1st derivative ISS-corrected merged SSLs considerably improved the prediction accuracy (R2 = 0.70, RPIQ = 3.10, RMSE = 0.25 %, and SD = 0.06). Hence, the derivative spectra coupled with the ISS correction improved the accuracy of SOC prediction models obtained from the merged soil spectra collected in different environments using different instruments. We therefore recommend application of the ISS spectral alignment method linked to the 1st derivative approach to enhance the compilation of SSLs at the regional and global scales for SOC assessment.
Using ground-penetrating radar to investigate the thickness of mollic epipedons developed from loessial parent material
The information of mollic epipedon (ME) thickness was essential for evaluation and protection of Mollisol resource. However, the traditional methods including the soil profile method, soil probes, and the drilling method, are low efficient and accurate for large area survey of soil thickness. In this study, the ground penetrating radar (GPR) was employed to detect the thickness of ME with underlying loessial parent material (LPM) along three slopes in straight, convex, and concave shapes in northeast China. The accuracy of GPR for measuring the ME thickness was verified by using excavation profile and pre-buried iron pipes. The effects of soil moisture and bulk density on soil permittivity were also investigated based on indoor experiments. The results indicated that the soil permittivity increased and decreased with the increase of bulk density and soil moisture, respectively. The relationships among soil moisture, bulk density and permittivity of both Mollisol and LPM could be described by two fitted equations, and the errors of the prediction equations was in the range of 0.32 %-5.10 %. The errors of GPR to measure the ME thickness was in the range of 3.72 %-10.64 %. The spatial distribution of the ME thickness along the three slopes varied, and the concave slope had a thicker ME than the convex and straight slope. Meanwhile, similar trends were shown that the sedimentation at the slope foot led to the thickest ME, while soil erosion at the slope shoulder and back resulted in the thinnest ME. This study could provide an efficient and accurate method to investigate soil thickness for further evaluation and protection of soil resources.
Evaluating validation strategies on the performance of soil property prediction from regional to continental spectral data
Visible-near infrared (vis-NIR) spectroscopy has been widely used to characterize soil information from field to global scales. Before applying a calibrated spectral predictive model to acquire soil information, either independent validation or k-fold cross validation is used to evaluate model performance. However, there is no consensus on which validation strategy is more suitable and robust when evaluating model performance for the studies in different scales. The objective of this study is to evaluate and compare the model performance of two validation strategies coupling different calibration sizes (a ratio of calibration to validation of 2:1, 4:1 and 9:1) and calibration sampling strategies (random sampling (RS), rank, Kennard-Stone (KS), rank-Kennard-Stone (RKS) and conditioned Latin hypercube sampling (cLHS)) across scales. A total of 17,272 vis-NIR spectra of mineral soils from LUCAS data (continental scale) and their soil organic carbon (SOC) and clay contents were used in this study, and the dataset was further split into national (2761 samples in France) and five regional datasets (110 to 248 samples from five French administrative regions). To eliminate the effect of changing validation set on the model performance, a consistent test set (20% of total samples at each scale) was split to evaluate all the combinations involved in two validation strategies. The Lin’s concordance correlation coefficient (CCC) of the cubist model were stable for both SOC and clay for different calibration sizes, calibration sampling and validation strategies for a large calibration size (>1400) at the national and continental scales. A larger calibration size can potentially improve model performance for a small dataset (<300) at the regional scale, and a wider calibration range would result in better model performance. No silver bullet was found among the different calibration sampling strategies at the regional scale. For five French regions (small data set), we found a high variation (95th percentile minus the 5th percentile) in the CCC among the models built from 50 repeated RS (0.10-0.44 for SOC, 0.16-0.52 for clay) and cLHS (0.08-0.40 for SOC, 0.12-0.36 for clay). This finding indicates that a one-time RS or cLHS for selecting the calibration set has high uncertainty in model evaluation for a small dataset and therefore should be used with caution. Therefore, we suggest the following: (1) for a large data set (thousands), either one-time random sampling for independent validation or k-fold cross validation would be appropriate; (2) for a small data set (dozens to hundreds), k-fold cross validation and/or repeated random sampling for independent validation would be more robust for spectral predictive model evaluation.
Digital soil maps can perform as well as large-scale conventional soil maps for the prediction of catchment baseflows
The rapid advance of digital soil mapping (DSM) has resulted in the generation of fine resolution soils spatial datasets with associated uncertainty that can be as accurate but more cost-effective and faster to produce than conventional soil maps. There is documented and increasing interest by policy makers and end-users in moving from conventional soil mapping to DSM; however, the wider operational use of DSM depends on demonstrating the effectiveness of DSM in fulfilling user needs and requirements along with providing DSM products that can be easily used by non-specialists. In this study we used the Hydrology of Soil Types (HOST) classification scheme, which was devised to predict flows in ungauged catchments and is used by both the research and policy maker communities in the UK, as the exemplar for comparing the efficiency of HOST class maps produced using both DSM and conventional soil map approaches for predicting catchment hydrological response. The performance for hydrological predictions of a detailed (1:25,000 scale) polygon HOST class map and a HOST-DSM class map produced via spatial disaggregation was assessed by comparing Base Flow Index (BFI) calculated using HOST class proportions from both maps with BFI calculated using flow data from gauges in 39 selected catchments. Results showed that the disaggregated HOST-DSM class map gave similar or even better BFI predictions than the conventional polygon-based HOST class map, while also providing a better insight on spatial soil variability within map units and its effect on hydrological predictions. This study demonstrates the potential of DSM to produce soil hydrological maps that provide comparable or better baseflow predictions than maps produced using detailed and intensive soil surveying. The study results also suggest that translating DSM of classes to more easily interpretable mapping datasets and incorporating prediction uncertainty in the final DSM product, as in the case of BFI maps based on HOST-DSM classes, could help with facilitating the transition towards a wider operational use of DSM.
Estimation of root zone soil moisture from ground and remotely sensed soil information with multisensor data fusion and automated machine learning
Root zone soil moisture (RZSM) estimation and monitoring based on high spatial resolution remote sensing information such as obtained with an Unmanned Aerial System (UAS) is of significant interest for field-scale precision irrigation management, particularly in water-limited regions of the world. To date, there is no accurate and widely accepted model that relies on UAS optical surface reflectance observations for RZSM estimation at high spatial resolution. This study is aimed at the development of a new approach for RZSM estimation based on the fusion of high spatial resolution optical reflectance UAS observations with physical and hydraulic soil information integrated into Automated Machine Learning (AutoML). The H2O AutoML platform includes a number of advanced machine learning algorithms that efficiently perform feature selection and automatically identify complex relationships between inputs and outputs. Twelve models combining UAS optical observations with various soil properties were developed in a hierarchical manner and fed into AutoML to estimate surface, near-surface, and root zone soil moisture. The addition of independently measured surface and near-surface soil moisture information to the hierarchical models to improve RZSM estimation was investigated. The accuracy of soil moisture estimates was evaluated based on a comparison with Time Domain Reflectometry (TDR) sensors that were deployed to monitor surface, near-surface and root zone soil moisture dynamics. The obtained results indicate that the consideration of physical and hydraulic soil properties together with UAS optical observations improves soil moisture estimation, especially for the root zone with a RMSE of about 0.04 cm3 cm-3. Accurate RZSM estimates were obtained when measured surface and near-surface soil moisture data was added to the hierarchical models, yielding RMSE values below 0.02 cm3 cm-3 and R and NSE values above 0.90. The generated high spatial resolution RZSM maps clearly capture the spatial variability of soil moisture at the field scale. The presented framework can aid farm scale precision irrigation management via improving the crop water use efficiency and reducing the risk of groundwater contamination.