scholarly journals Soil Organic Carbon Mapping from Remote Sensing: The Effect of Crop Residues

2020 ◽  
Vol 12 (12) ◽  
pp. 1913 ◽  
Author(s):  
Klara Dvorakova ◽  
Pu Shi ◽  
Quentin Limbourg ◽  
Bas van Wesemael
Keyword(s):  
Remote Sensing ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Cross Validation ◽  
Crop Residues ◽  
Prediction Models ◽  
Partial Least Square ◽  
Least Square ◽  
Local Soil ◽  
Sentinel 2

Since the onset of agriculture, soils have lost their organic carbon to such an extent that the soil functions of many croplands are threatened. Hence, there is a strong demand for mapping and monitoring critical soil properties and in particular soil organic carbon (SOC). Pilot studies have demonstrated the potential for remote sensing techniques for SOC mapping in croplands. It has, however, been shown that the assessment of SOC may be hampered by the condition of the soil surface. While growing vegetation can be readily detected by means of the well-known Normalized Difference Vegetation Index (NDVI), the distinction between bare soil and crop residues is expressed in the shortwave infrared region (SWIR), which is only covered by two broad bands in Landsat or Sentinel-2 imagery. Here we tested the effect of thresholds for the Cellulose Absorption Index (CAI), on the performance of SOC prediction models for cropland soils. Airborne Prism Experiment (APEX) hyperspectral images covering an area of 240 km2 in the Belgian Loam Belt were used together with a local soil dataset. We used the partial least square regression (PLSR) model to estimate the SOC content based on 104 georeferenced calibration samples (NDVI < 0.26), firstly without setting a CAI threshold, and obtained a satisfactory result (coefficient of determination (R2) = 0.49, Ratio of Performance to Deviation (RPD) = 1.4 and Root Mean Square Error (RMSE) = 2.13 g kgC−1 for cross-validation). However, a cross comparison of the estimated SOC values to grid-based measurements of SOC content within three fields revealed a systematic overestimation for fields with high residue cover. We then tested different CAI thresholds in order to mask pixels with high residue cover. The best model was obtained for a CAI threshold of 0.75 (R2 = 0.59, RPD = 1.5 and RMSE = 1.75 g kgC−1 for cross-validation). These results reveal that the purity of the pixels needs to be assessed aforehand in order to produce reliable SOC maps. The Normalized Burn Ratio (NBR2) index based on the SWIR bands of the MSI Sentinel 2 sensor extracted from images collected nine days before the APEX flight campaign correlates well with the CAI index of the APEX imagery. However, the NBR2 index calculated from Sentinel 2 images under moist conditions is poorly correlated with residue cover. This can be explained by the sensitivity of the NBR2 index to both soil moisture and residues.

Soil organic carbon mapping from remote sensing: The effect of crop residues

2020 ◽  
Author(s):  
Klara Dvorakova ◽  
Pu Shi ◽  
Limbourg Quentin ◽  
Bas van Wesemael
Keyword(s):  
Remote Sensing ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Cross Validation ◽  
Crop Residues ◽  
Partial Least Square ◽  
Spatial Coverage ◽  
Local Soil ◽  
Calibration Samples ◽  
Plsr Model

&lt;p&gt;Since the onset of agriculture, soils have lost their organic carbon to such an extent that the soil functions of many croplands are threatened and there is therefore a strong demand for mapping and monitoring critical soil properties and in particular soil organic carbon (SOC). Pilot studies have demonstrated the potential for remote sensing techniques for SOC mapping in croplands, given their large spatial coverage and high temporal resolution. It has however been shown that the assessment of SOC may be hampered by crop residues. In this study we tested the effect of the threshold for the cellulose absorption index (CAI), on the performance of SOC prediction models for bare cropland soils. Airborne Prism Experiment (APEX) hyperspectral images covering an area of 230 km&lt;sup&gt;2&lt;/sup&gt; in the Belgian Loam Belt were used together with a local soil dataset. We used the partial least square regression (PLSR) model to estimate the SOC content based on 104 georeferenced calibration samples, firstly without setting a CAI threshold, and obtained a satisfactory result (R&amp;#178;=0.49, RPD=1.4 and RMSE=2.14 g kgC&lt;sup&gt;-1&lt;/sup&gt; for cross-validation). However, a cross comparison of the estimated SOC values to grid-based measurements of SOC content within three fields revealed a systematic overestimation for fields with high residue cover. We then tested different thresholds of CAI in order to mask pixels with high residue cover, by eliminating calibration samples used in the PLSR model based on this threshold. The best model was obtained for CAI threshold of 0.8 (R&amp;#178;=0.59, RPD=1.5 and RMSE=1.76 g kgC&lt;sup&gt;-1&lt;/sup&gt; for cross-validation). These results reveal that the purity of the pixels needs to be assessed aforehand in order to produce reliable SOC maps. Preliminary results indicate that an index based on the SWIR bands of the MSI Sentinel 2 sensor is also capable of detecting crop residues. However, the application under moist conditions and for different types of residues needs to be confirmed.&lt;/p&gt;

Sentinel-2 exposed soil composite for soil organic carbon prediction: the ‘greening-up’ method for detecting suitable images

2021 ◽  
Author(s):  
Klara Dvorakova ◽  
Bas van Wesemael
Keyword(s):  
Remote Sensing ◽  
Surface Roughness ◽  
Soil Moisture ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Satisfactory Result ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Sentinel 2

&lt;p&gt;Pilot studies have demonstrated the potential for remote sensing techniques for soil organic carbon&amp;#160; (SOC) mapping in exposed croplands. However, the use of remote sensing for SOC prediction is often hindered by disturbing factors at the soil surface such as photosynthetic active and nonphotosynthetic active vegetation, variation in soil moisture or surface roughness. With the increasing amount of freely available satellite data, many studies have focused on stabilizing the soil reflectance by building image composites that are generated using a set of criteria. These composites tend to minimize and cancel out the disturbing effects. Here we aim to develop a robust method that allows selecting Sentinel-2 (S-2) pixels that are not affected by the following disturbing factors: crop residues, surface roughness and soil moisture. We selected all S-2 cloud-free images covering the Loam Belt of Belgium from January 2019 to December 2020 (in total 38 images). We then built four exposed soil composites based on four sets of criteria: (1) NDVI &lt; 0.25, (2) NDVI &lt; 0.25 &amp; Normalized Burn Ratio (NBR2) &lt; 0.07, (3) the &amp;#8216;greening-up&amp;#8217; period of a crop and (4) the &amp;#8216;greening-up&amp;#8217; period of a crop &amp; NBR2 &lt; 0.07. The &amp;#8216;greening-up&amp;#8217; period was selected based on the NDVI timeline, where &amp;#8216;greening-up&amp;#8217; is considered as the last date of acquisition where the soil is bare (NDVI &lt; 0.25) before the crop develops (NDVI &gt; 0.6).,We then built a partial least square regression (PLSR) model with 10-fold cross-validation to estimate the SOC content based on 137 georeferenced calibration samples on the four above described composites. We obtained a non-satisfactory result for composites (1) to (3): R&amp;#178; = 0.22, RMSE = 3.46 g&amp;#160;C kg&lt;sup&gt;-1&lt;/sup&gt; and RPD 1.12 for (1), R&amp;#178; = 0.19, RMSE = 3.43 g C&amp;#160;kg&lt;sup&gt;-1&lt;/sup&gt; and RPD 1.10 for (2) and R&amp;#178; = 0.15, RMSE = 2.74 g&amp;#160;C kg&lt;sup&gt;-1&lt;/sup&gt; and RPD 1.06 for (3). We, however, obtained a satisfactory result for composite (4): R&amp;#178; = 0.54, RMSE = 2.09 g C kg&lt;sup&gt;-1&lt;/sup&gt; and RPD 1.68. Hence, the &amp;#8216;greening-up&amp;#8217; method combined with a strict NBR2 threshold allows selecting the purest exposed soil pixels suitable for SOC prediction. The limit of this method might be the surface coverage, which for a two-year period reached 47% of croplands, compared to 89% exposure if only the NDVI threshold is applied.&lt;/p&gt;

scholarly journals Soil Organic Carbon Mapping Using LUCAS Topsoil Database and Sentinel-2 Data: An Approach to Reduce Soil Moisture and Crop Residue Effects

2019 ◽  
Vol 11 (18) ◽  
pp. 2121 ◽  
Author(s):  
Fabio Castaldi ◽  
Sabine Chabrillat ◽  
Axel Don ◽  
Bas van Wesemael
Keyword(s):  
Soil Moisture ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Ad Hoc ◽  
Crop Residues ◽  
Prediction Models ◽  
Bare Soil ◽  
Large Area ◽  
Red Edge ◽  
Sentinel 2

Soil organic carbon (SOC) loss is one of the main causes of soil degradation in croplands. Thus, spatial and temporal monitoring of SOC is extremely important, both from the environmental and economic perspective. In this regard, the high temporal, spatial, and spectral resolution of the Sentinel-2 data can be exploited for monitoring SOC contents in the topsoil of croplands. In this study, we aim to test the effect of the threshold for a spectral index linked to soil moisture and crop residues on the performance of SOC prediction models using the Multi-Spectral Instrument (MSI) Sentinel-2 and the European Land Use/cover Area frame Statistical survey (LUCAS) topsoil database. The LUCAS spectral data resampled according to MSI/Sentinel-2 bands, which were used to build SOC prediction models combining pairs of the bands. The SOC models were applied to a Sentinel-2 image acquired in North-Eastern Germany after removing the pixels characterized by clouds and green vegetation. Then, we tested different thresholds of the Normalized Burn Ratio 2 (NBR2) index in order to mask moist soil pixels and those with dry vegetation and crop residues. The model accuracy was tested on an independent validation database and the best ratio of performance to deviation (RPD) was obtained using the average between bands B6 and B5 (Red-Edge Carbon Index: RE-CI) (RPD: 4.4) and between B4 and B5 (Red-Red-Edge Carbon Index: RRE-CI) (RPD: 2.9) for a very low NBR2 threshold (0.05). Employing a higher NBR2 tolerance (higher NBR2 values), the mapped area increases to the detriment of the validation accuracy. The proposed approach allowed us to accurately map SOC over a large area exploiting the LUCAS spectral library and, thus, avoid a new ad hoc field campaign. Moreover, the threshold for selecting the bare soil pixels can be tuned, according to the goal of the survey. The quality of the SOC map for each tolerance level can be judged based on the figures of merit of the model.

scholarly journals Exploring the Suitability of UAS-Based Multispectral Images for Estimating Soil Organic Carbon: Comparison with Proximal Soil Sensing and Spaceborne Imagery

2021 ◽  
Vol 13 (2) ◽  
pp. 308
Author(s):  
James Kobina Mensah Biney ◽  
Mohammadmehdi Saberioon ◽  
Luboš Borůvka ◽  
Jakub Houška ◽  
Radim Vašát ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Prediction Models ◽  
Unmanned Aircraft ◽  
Support Vector ◽  
Spectral Indices ◽  
Entire Study ◽  
Proximal Soil Sensing ◽  
Sentinel 2

Soil organic carbon (SOC) is a variable of vital environmental significance in terms of soil quality and function, global food security, and climate change mitigation. Estimation of its content and prediction accuracy on a broader scale remain crucial. Although, spectroscopy under proximal sensing remains one of the best approaches to accurately predict SOC, however, spectroscopy limitation to estimate SOC on a larger spatial scale remains a concern. Therefore, for an efficient quantification of SOC content, faster and less costly techniques are needed, recent studies have suggested the use of remote sensing approaches. The primary aim of this research was to evaluate and compare the capabilities of small Unmanned Aircraft Systems (UAS) for monitoring and estimation of SOC with those obtained from spaceborne (Sentinel-2) and proximal soil sensing (field spectroscopy measurements) on an agricultural field low in SOC content. Nine calculated spectral indices were added to the remote sensing approaches (UAS and Sentinel-2) to enhance their predictive accuracy. Modeling was carried out using various bands/wavelength (UAS (6), Sentinel-2 (9)) and the calculated spectral indices were used as independent variables to generate soil prediction models using five-fold cross-validation built using random forest (RF) and support vector machine regression (SVMR). The correlation regarding SOC and the selected indices and bands/wavelengths was determined prior to the prediction. Our results revealed that the selected spectral indices slightly influenced the output of UAS compared to Sentinel-2 dataset as the latter had only one index correlated with SOC. For prediction, the models built on UAS data had a better accuracy with RF than the two other data used. However, using SVMR, the field spectral prediction models achieved a better overall result for the entire study (log(1/R), RPD = 1.40; R2CV = 0.48; RPIQ = 1.65; RMSEPCV = 0.24), followed by UAS and then Sentinel-2, respectively. This study has shown that UAS imagery can be exploited efficiently using spectral indices.

Soil organic carbon prediction using phenological parameters and remote sensing variables generated from Sentinel-2 images

CATENA ◽  
2021 ◽  
Vol 205 ◽  
pp. 105442
Author(s):  
Xianglin He ◽  
Lin Yang ◽  
Anqi Li ◽  
Lei Zhang ◽  
Feixue Shen ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Sentinel 2

scholarly journals Estimating Soil Organic Carbon in Agricultural Gypsiferous Soils by Diffuse Reflectance Spectroscopy

Water ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 261 ◽  
Author(s):  
Maria Marques ◽  
Ana Álvarez ◽  
Pilar Carral ◽  
Iris Esparza ◽  
Blanca Sastre ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Prediction Ability ◽  
Greenhouse Gas Inventories ◽  
Starting Point

Contents of soil organic carbon (SOC), gypsum, CaCO3, and quartz, among others, were analyzed and related to reflectance features in visible and near-infrared (VIS/NIR) range, using partial least square regression (PLSR) in ParLes software. Soil samples come from a sloping olive grove managed by frequent tillage in a gypsiferous area of Central Spain. Samples were collected in three different layers, at 0–10, 10–20 and 20–30 cm depth (IPCC guidelines for Greenhouse Gas Inventories Programme in 2006). Analyses were performed by C Loss-On-Ignition, X-ray diffraction and water content by the Richards plates method. Significant differences for SOC, gypsum, and CaCO3 were found between layers; similarly, soil reflectance for 30 cm depth layers was higher. The resulting PLSR models (60 samples for calibration and 30 independent samples for validation) yielded good predictions for SOC (R2 = 0.74), moderate prediction ability for gypsum and were not accurate for the rest of rest of soil components. Importantly, SOC content was related to water available capacity. Soils with high reflectance features held c.a. 40% less water than soils with less reflectance. Therefore, higher reflectance can be related to degradation in gypsiferous soil. The starting point of soil degradation and further evolution could be established and mapped through remote sensing techniques for policy decision making.

scholarly journals Prediction of Soil Organic Carbon for Ethiopian Highlands Using Soil Spectroscopy

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Tadele Amare ◽  
Christian Hergarten ◽  
Hans Hurni ◽  
Bettina Wolfgramm ◽  
Birru Yitaferu ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Diffuse Reflectance ◽  
Principal Component ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Coefficient Of Determination ◽  
Calibration Models ◽  
The Stability

Soil spectroscopy was applied for predicting soil organic carbon (SOC) in the highlands of Ethiopia. Soil samples were acquired from Ethiopia’s National Soil Testing Centre and direct field sampling. The reflectance of samples was measured using a FieldSpec 3 diffuse reflectance spectrometer. Outliers and sample relation were evaluated using principal component analysis (PCA) and models were developed through partial least square regression (PLSR). For nine watersheds sampled, 20% of the samples were set aside to test prediction and 80% were used to develop calibration models. Depending on the number of samples per watershed, cross validation or independent validation were used. The stability of models was evaluated using coefficient of determination (R2), root mean square error (RMSE), and the ratio performance deviation (RPD). The R2 (%), RMSE (%), and RPD, respectively, for validation were Anjeni (88, 0.44, 3.05), Bale (86, 0.52, 2.7), Basketo (89, 0.57, 3.0), Benishangul (91, 0.30, 3.4), Kersa (82, 0.44, 2.4), Kola tembien (75, 0.44, 1.9), Maybar (84. 0.57, 2.5), Megech (85, 0.15, 2.6), and Wondo Genet (86, 0.52, 2.7) indicating that the models were stable. Models performed better for areas with high SOC values than areas with lower SOC values. Overall, soil spectroscopy performance ranged from very good to good.

scholarly journals Predicting Soil Organic Carbon Content Using Hyperspectral Remote Sensing in a Degraded Mountain Landscape in Lesotho

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Freddy Bangelesa ◽  
Elhadi Adam ◽  
Jasper Knight ◽  
Inos Dhau ◽  
Marubini Ramudzuli ◽  
...  
Keyword(s):  
Random Forest ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Organic Carbon Content ◽  
Random Forest Regression ◽  
Least Square Regression ◽  
Field Spectroscopy

Soil organic carbon constitutes an important indicator of soil fertility. The purpose of this study was to predict soil organic carbon content in the mountainous terrain of eastern Lesotho, southern Africa, which is an area of high endemic biodiversity as well as an area extensively used for small-scale agriculture. An integrated field and laboratory approach was undertaken, through measurements of reflectance spectra of soil using an Analytical Spectral Device (ASD) FieldSpec® 4 optical sensor. Soil spectra were collected on the land surface under field conditions and then on soil in the laboratory, in order to assess the accuracy of field spectroscopy-based models. The predictive performance of two different statistical models (random forest and partial least square regression) was compared. Results show that random forest regression can most accurately predict the soil organic carbon contents on an independent dataset using the field spectroscopy data. In contrast, the partial least square regression model overfits the calibration dataset. Important wavelengths to predict soil organic contents were localised around the visible range (400–700 nm). This study shows that soil organic carbon can be most accurately estimated using derivative field spectroscopy measurements and random forest regression.

scholarly journals Error propagation in spectrometric functions of soil organic carbon

SOIL ◽  
2019 ◽  
Vol 5 (2) ◽  
pp. 275-288
Author(s):  
Monja Ellinger ◽  
Ines Merbach ◽  
Ulrike Werban ◽  
Mareike Ließ
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Error Propagation ◽  
Field Experiments ◽  
Model Building ◽  
Model Performance ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Measurement Protocol

Abstract. Soil organic carbon (SOC) plays a major role concerning chemical, physical, and biological soil properties and functions. To get a better understanding of how soil management affects the SOC content, the precise monitoring of SOC on long-term field experiments (LTFEs) is needed. Visible and near-infrared (Vis–NIR) reflectance spectrometry provides an inexpensive and fast opportunity to complement conventional SOC analysis and has often been used to predict SOC. For this study, 100 soil samples were collected at an LTFE in central Germany by two different sampling designs. SOC values ranged between 1.5 % and 2.9 %. Regression models were built using partial least square regression (PLSR). In order to build robust models, a nested repeated 5-fold group cross-validation (CV) approach was used, which comprised model tuning and evaluation. Various aspects that influence the obtained error measure were analysed and discussed. Four pre-processing methods were compared in order to extract information regarding SOC from the spectra. Finally, the best model performance which did not consider error propagation corresponded to a mean RMSEMV of 0.12 % SOC (R2=0.86). This model performance was impaired by ΔRMSEMV=0.04 % SOC while considering input data uncertainties (ΔR2=0.09), and by ΔRMSEMV=0.12 % SOC (ΔR2=0.17) considering an inappropriate pre-processing. The effect of the sampling design amounted to a ΔRMSEMV of 0.02 % SOC (ΔR2=0.05). Overall, we emphasize the necessity of transparent and precise documentation of the measurement protocol, the model building, and validation procedure in order to assess model performance in a comprehensive way and allow for a comparison between publications. The consideration of uncertainty propagation is essential when applying Vis–NIR spectrometry for soil monitoring.

The interplay among analytical method, preprocessing, and modeling on soil organic carbon Vis-NIR-SWIR predictions

2021 ◽  
Author(s):  
Taciara Zborowski Horst-Heinen ◽  
Ricardo Simão Diniz Dalmolin ◽  
Alessandro Samuel-Rosa ◽  
Sabine Grunwald
Keyword(s):  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Predictive Models ◽  
Analytical Method ◽  
Analytical Methods ◽  
Near Infrared ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Spectral Models

&lt;p&gt;The relationship between visible-near-infrared (Vis-NIR-SWIR) spectra and soil organic carbon (SOC) and the effects of preprocessing techniques on SOC predictive models have been shown in several studies. However, little attention has been given to the effect of analytical methods used to produce the SOC data used to calibrate those models. The predictive performance of Vis-NIR spectral models depends not only on the preprocessing technique and machine learning method but also on the analytical method employed to produce the SOC data. Our hypothesis is that some combinations of preprocessing and models may be more sensitive to laboratory (measurement) error than others. To test this hypothesis, we evaluated the leave-one-out cross-validation performance of three predictive models (Random Forest (RF), Cubist, and Partial Least Square Regression (PLSR)) calibrated using SOC data produced via three analytical methods (dry combustion (DC) and wet combustion with quantification by titration (WCt) and colorimetry (WCc)) and three Vis-NIR spectra preprocessing techniques (smoothing (SMO), continuum removal (CRR), and Savitzky-Golay first derivative (SGD)). The prediction performance varied among the models. DC and WCt provided a higher correlation between SOC and spectra than WCc, and thus, resulted in higher accuracy. The Cubist+CRR was ranked the best performing model, with an average of R2 = 0.81 and RMSE = 0.81% among analytical methods. Cubist+CRR also minimized the accuracy differences resulting from SOC analytical methods employed. The RF model had low accuracy and was unable to explain more than 46% of the variance. Overall, the analytical method significantly affects SOC predictions, and its impact may be larger than the preprocessing.&amp;#160;&lt;/p&gt;

Sign in / Sign up

Export Citation Format

Share Document