A PLSR model to predict soil salinity using Sentinel-2 MSI data

Abstract Salinization is one of the most widespread environmental threats in arid and semi-arid regions that occur either naturally or artificially within the soil. When exceeding the thresholds, salinity becomes a severe danger, damaging agricultural production, water and soil quality, biodiversity, and infrastructures. This study used spectral indices, including salinity and vegetation indices, Sentinel-2 MSI original bands, and DEM, to model soil salinity in the Great Hungarian Plain. Eighty-one soil samples in the upper 30 cm of the soil surface were collected from vegetated and nonvegetated areas by the Research Institute for Soil Sciences and Agricultural Chemistry (RISSAC). The sampling campaign of salinity monitoring was performed in the dry season to enhance salt spectral characteristics during its accumulation in the subsoil. Hence, applying a partial least squares regression (PLSR) between salt content (g/kg) and remotely sensed data manifested a highly moderate correlation with a coefficient of determination R 2 of 0.68, a p-value of 0.000017, and a root mean square error of 0.22. The final model can be deployed to highlight soil salinity levels in the study area and assist in understanding the efficacy of land management strategies.

Download Full-text

A simple approach to estimate coastal soil salinity using digital camera images

Soil Research ◽

10.1071/sr20009 ◽

2020 ◽

Vol 58 (8) ◽

pp. 737

Author(s):

Lu Xu ◽

Raphael A. Viscarra Rossel ◽

Juhwan Lee ◽

Zhichun Wang ◽

Hongyuan Ma

Keyword(s):

Soil Salinity ◽

Precision Agriculture ◽

Mean Squared Error ◽

Rapid Development ◽

Salt Content ◽

Digital Camera ◽

Soil Surface ◽

Coefficient Of Determination ◽

Least Squares Regression ◽

High Concentration

Soil salinisation is a global problem that hinders the sustainable development of ecosystems and agricultural production. Remote and proximal sensing technologies have been used to effectively evaluate soil salinity over large scales, but research on digital camera images is still lacking. In this study, we propose to relate the pixel brightness of soil surface digital images to the soil salinity information. We photographed the surface of 93 soils in the field at different times and weather conditions, and sampled the corresponding soils for laboratory analyses of soil salinity information. Results showed that the pixel digital numbers were related to soil salinity, especially at the intermediate and higher brightness levels. Based on this relationship, we employed random forest (RF) and partial least-squares regression (PLSR) to model soil salt content and ion concentrations, and applied root mean squared error, coefficient of determination and Lin’s concordance correlation coefficient to evaluate the accuracy of models. We found that ions with high concentration were estimated more accurately than ions with low concentrations, and RF models performed overall better than PLSR models. However, the method is only suitable for bare land of coastal soil, and verification is needed for other conditions. In conclusion, a new approach of using digital camera images has good potential to predict and manage soil salinity in the context of precision agriculture with the rapid development of unmanned aerial vehicles.

Download Full-text

The soil-adjusted vegetation index for soil salinity assessment in Uzbekistan

Proceedings of the International conference “InterCarto/InterGIS” ◽

10.35595/2414-9179-2020-3-26-324-333 ◽

2020 ◽

Vol 26 (3) ◽

pp. 324-333

Author(s):

Nozimjon Teshaev ◽

Bunyod Mamadaliyev ◽

Azamjon Ibragimov ◽

Sayidjakhon Khasanov

Keyword(s):

Soil Salinity ◽

Information Technologies ◽

Vegetation Index ◽

Arable Land ◽

Salt Content ◽

Secondary Data ◽

Soil Surface ◽

Soil Salinization ◽

Arid Zones ◽

Agronomic Practices

Soil salinization, as one of the threats of land degradation, is the main environmental issue in Uzbekistan due to its aridic climate. One of the most vulnerable areas to soil salinization is Sirdarya province in Uzbekistan. The main human-induced causes of soil salinization are the insufficient operation of drainage and irrigation systems, irregular observations of the agronomic practices, and non-efficient on-farm water use. All of these causes considerably interact with the level of the groundwater, leading to an increase in the level of soil salinity. The availability of historical data on actual soil salinity in agricultural lands helps in formulating validated generic state-of-the-art approaches to control and monitor soil salinization by remote sensing and geo-information technologies. In this paper, we hypothesized that the Soil-Adjusted Vegetation Index-based results in soil salinity assessment give statistically valid illustrations and salinity patterns. As a study area, the Mirzaabad district was taken to monitor soil salinization processes since it is the most susceptible territory of Sirdarya province to soil salinization and provides considerably less agricultural products. We mainly formulated this paper based on the secondary data, as we downloaded satellite images and conducted an experiment against the in-situ method of soil salinity assessment using the Soil-Adjusted Vegetation Index. As a result, highly saline areas decreased by a factor of two during the studied period (2005–2014), while non-saline areas increased remarkably from a negligible value to over 10 000 ha. Our study showed that arable land suitability for agricultural purposes has been improving year by year, and our research held on this district also proved that there was a gradual decrease in high salt contents on the soil surface and land quality has been improved. The methodology has proven to be statistically valid and significant to be applied to other arid zones for the assessment of soil salinity. We assume that our methodology is surely considered as a possible vegetation index to evaluate salt content in arable land of either Uzbekistan or other aridic zones and our hypothesis is not rejected by this research.

Download Full-text

Study on Soil Salinization Based on GIS and RS

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.333-335.81 ◽

2013 ◽

Vol 333-335 ◽

pp. 81-85 ◽

Cited By ~ 1

Author(s):

Chi Ma

Keyword(s):

Soil Salinity ◽

Research Result ◽

Atmospheric Correction ◽

Salt Content ◽

Soil Salinization ◽

Least Squares Regression ◽

Correction Model ◽

First Order ◽

Gis And Rs ◽

Songliao Plain

This paper obtained the surface reflectance image by using FLAASH atmospheric correction model to conduct atmospheric correction to the HSI image. After the reflectance image was processed with multi mathematical manipulations, the analytical method of geographic information system (GIS) was applied to carry out the partial least squares regression (PLSR) analysis with the measured value of soil salinity, thus quantitatively inverting the soil salinity in Songliao Plain. The research result indicated that the reflectance of HSI hyperspectral imaging can increase the related coefficient R2 of salt content in saline alkali soil significantly after being processed with reciprocal (1/R) and first-order differentiation (R), reaching 0.818 and 0.851 respectively with a root mean square error (RMSE) of 0.77 and 0.694 respectively, quantitatively and quickly gaining the soil salinity in Songliao Plain as well as salinization prevention.

Download Full-text

The Impact of Acquisition Date on the Prediction Performance of Topsoil Organic Carbon from Sentinel-2 for Croplands

Remote Sensing ◽

10.3390/rs11182143 ◽

2019 ◽

Vol 11 (18) ◽

pp. 2143 ◽

Cited By ~ 6

Author(s):

Emmanuelle Vaudour ◽

Cécile Gomez ◽

Thomas Loiseau ◽

Nicolas Baghdadi ◽

Benjamin Loubet ◽

...

Keyword(s):

Time Series ◽

Organic Carbon ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Soil Surface ◽

Prediction Performance ◽

Optical Data ◽

Least Squares Regression ◽

The Impact ◽

Sentinel 2

The spatial assessment of soil organic carbon (SOC) is a major environmental challenge, notably for evaluating soil carbon stocks. Recent works have shown the capability of Sentinel-2 optical data to predict SOC content over temperate agroecosystems characterized by annual crops, using a single acquisition date. Considering a Sentinel-2 time series, this work intends to analyze the impact of acquisition date, and related weather and soil surface conditions on the prediction performance of topsoil SOC content (plough layer). A Sentinel-2 time-series was gathered, comprised of the dates corresponding to both the maximum of bare soil coverage and minimum of cloud coverage. Cross-validated partial least squares regression (PLSR) models were constructed between soil reflectance image spectra, and SOC content analyzed from 329 top soil samples collected over the study area. Cross-validation R2 ranged from 0.005 to 0.58, root mean square error from 5.86 to 3.02 g·kg−1 and residual prediction deviation values from 1.0 to 1.5 (without unit), according to date. The main factors influencing these differences were soil roughness, in conjunction with soil moisture, and the cloud and cloud shadow cover of the entire tile. The best performing dates were spring dates characterized by both lowest soil surface roughness and moisture content. Normalized difference vegetation index (NDVI) values below 0.35 did not influence prediction performance. This consolidates the previous results obtained during single date acquisitions and offers wider perspectives for the further use of Sentinel-2 into multidate mosaics for digital soil mapping.

Download Full-text

Monitoring soil salinity using time-lapse electromagnetic conductivity imaging

10.5194/soil-2019-99 ◽

2020 ◽

Author(s):

Maria Catarina Paz ◽

Mohammad Farzamian ◽

Ana Marta Paz ◽

Nádia Luísa Castanheira ◽

Maria Conceição Gonçalves ◽

...

Keyword(s):

Electrical Conductivity ◽

Soil Salinity ◽

Management Strategies ◽

Time Lapse ◽

Soil Salinization ◽

Spatiotemporal Variability ◽

Coefficient Of Determination ◽

Agricultural System ◽

Soil Electrical Conductivity ◽

Salinity Levels

Abstract. Lezíria Grande of Vila Franca de Xira, located in Portugal, is an important agricultural system where soil faces the risk of salinization, being thus prone to desertification and land abandonment. Soil salinity can be assessed over large areas by the following rationale: (1) use of electromagnetic induction (EMI) to measure the soil apparent electrical conductivity (ECa, dS m−1); (2) inversion of ECa to obtain electromagnetic conductivity images (EMCI) which provide the spatial distribution of the soil electrical conductivity (σ, mS m−1); (3) calibration process consisting of a regression between σ and the electrical conductivity of the saturated soil paste extract (ECe, dS m−1), used as a proxy for soil salinity; and (4) conversion of EMCI into salinity maps using the obtained calibration equation. In this study, EMI surveys and soil sampling were carried out between May 2017 and October 2018 at four locations with different salinity levels across the study area of Lezíria de Vila Franca. A previously developed regional calibration was used for predicting ECe from EMCI. This study aims to evaluate the potential of time-lapse EMCI and the regional calibration to predict the spatiotemporal variability of soil salinity in the study area. The results showed that ECe was satisfactorily predicted, with a root mean square error (RMSE) of 3.22 dS m−1 in a range of 52.35 dS m−1 and a coefficient of determination (R2) of 0.89. Results also showed strong concordance with a Lin’s concordance correlation coefficient (CCC) of 0.93, although, ECe was slightly overestimated with a mean error (ME) of −1.30 dS m−1. Soil salinity maps for each location revealed salinity fluctuations related to the input of salts and water either through irrigation, precipitation or groundwater level and salinity. Time-lapse EMCI has proven to be a valid methodology for evaluating the risk of soil salinization, and can further support the evaluation and adoption of proper agricultural management strategies, especially in irrigated areas, where continuous monitoring of soil salinity dynamics is required.

Download Full-text

Assessment of PRISMA imaging spectrometer data for the estimation of topsoil properties of agronomic interest at the field scale

10.5194/egusphere-egu2020-6728 ◽

2020 ◽

Author(s):

Raffaele Casa ◽

Stefano Pignatti ◽

Simone Pascucci ◽

Victoria Ionca ◽

Nada Mzid ◽

...

Keyword(s):

Spatial Resolution ◽

Precision Agriculture ◽

Central Italy ◽

Bare Soil ◽

Hyperspectral Data ◽

Least Squares Regression ◽

Field Scale ◽

Sampling Campaign ◽

Spectrometer Data ◽

Sentinel 2

On the 22 March 2019 the Italian Space Agency (ASI) launched the PRISMA satellite, having onboard a hyperspectral imager covering the 400-2500 nm range with 234 spectral bands and about 10 nm of bandwidth. The ground spatial resolution is 30 m, plus a panchromatic camera with 5 m spatial resolution. One of the potential application areas of this scientific mission is for precision agriculture applications, among which the mapping of field-scale variability of topsoil properties is of particular interest.PRISMA clear-sky hyperspectral images were acquired in autumn and spring 2019 on the Maccarese farm in Central Italy, in the framework of the PRISCAV project, which is aimed at a first assessment of the PRISMA data. An intensive soil sampling campaign was performed, using a ground sampling scheme adapted to PRISMA and Sentinel-2 spatial resolutions, in the fields where bare soil was exposed at the satellite acquisition dates. Soil texture (clay, silt, sand), carbonates, pH and soil organic carbon (SOC) for the collected soil samples were then determined in the laboratory.The dataset was then used to test calibration and validation of PLSR (Partial Least Squares Regression) and RF (Random Forest) models developed using PRISMA surface reflectance data. To this aim, several pre-treatment tests were performed, including pan-sharpening at 5 m using PRISMA panchromatic data as well as Sentinel-2 multispectral data.The results show that the good results could be obtained in particular for clay estimation. The best-performing algorithm for topsoil properties retrieval using PRISMA hyperspectral data was RF algorithm as compared with PLSR.

Download Full-text

Soil salinity mapping utilizing sentinel-2 and neural networks

Indian Journal of Agricultural Research ◽

10.18805/ijare.a-316 ◽

2018 ◽

Author(s):

R.S. Morgan ◽

M. Abd El-Hady ◽

I.S. Rahim

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Soil Salinity ◽

Vegetation Index ◽

High Spectral Resolution ◽

Coefficient Of Determination ◽

Infrared Band ◽

Artificial Neural ◽

Reflectance Data ◽

Sentinel 2

Soil salinity is the most important soil property that affects the agriculture productivity. Periodical monitoring of its status is considered a crucial factor in the selection of appropriate agricultural practices to attain a sustainable production. The availability of remote sensing data processed by a somewhat novel method such as artificial neural networks (ANN) offer a potential solution that could easily and affordably replace the in-site monitoring methods. The aim of this work is to use high spectral resolution Sentinel-2 (S2) data for soil salinity prediction utilizing neural networks. The study evaluated three approaches in processing the S2 data for inclusion in the artificial neural network for soil salinity prediction. These approaches included S2 spectral reflectance data, spectral indices and principal component analysis (PCA) of the S2 data. The results revealed that a combination of these approaches including the reflectance data of band 11(shortwave infrared band) of S2, the normalized differential vegetation index (NDVI) and the second PCA (dominated by the near infrared band) gave the best performance when used as input when designing the artificial neural networks to predict the soil salinity. The overall accuracy of this approach has a coefficient of determination (R2) of 0.94 between the actual and predicted soil salinity.

Download Full-text

Some Peculiarities of Arable Soil Organic Matter Detection Using Optical Remote Sensing Data

Remote Sensing ◽

10.3390/rs13122313 ◽

2021 ◽

Vol 13 (12) ◽

pp. 2313

Author(s):

Elena Prudnikova ◽

Igor Savin

Keyword(s):

Remote Sensing ◽

Organic Matter ◽

Soil Organic Matter ◽

Spectral Reflectance ◽

Remote Sensing Data ◽

Soil Surface ◽

Optical Remote Sensing ◽

Test Field ◽

Sensing Data ◽

Sentinel 2

Optical remote sensing only provides information about the very thin surface layer of soil. Rainfall splash alters soil surface properties and its spectral reflectance. We analyzed the impact of rainfall on the success of soil organic matter (SOM) content (% by mass) detection and mapping based on optical remote sensing data. The subject of the study was the arable soils of a test field located in the Tula region (Russia), their spectral reflectance, and Sentinel-2 data. Our research demonstrated that rainfall negatively affects the accuracy of SOM predictions based on Sentinel-2 data. Depending on the average precipitation per day, the R2cv of models varied from 0.67 to 0.72, RMSEcv from 0.64 to 1.1% and RPIQ from 1.4 to 2.3. The incorporation of information on the soil surface state in the model resulted in an increase in accuracy of SOM content detection based on Sentinel-2 data: the R2cv of the models increased up to 0.78 to 0.84, the RMSEcv decreased to 0.61 to 0.71%, and the RPIQ increased to 2.1 to 2.4. Further studies are necessary to identify how the SOM content and composition of the soil surface change under the influence of rainfall for other soils, and to determine the relationships between rainfall-induced SOM changes and soil surface spectral reflectance.

Download Full-text

Hyperspectral Data Simulation (Sentinel-2 to AVIRIS-NG) for Improved Wildfire Fuel Mapping, Boreal Alaska

Remote Sensing ◽

10.3390/rs13091693 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1693

Author(s):

Anushree Badola ◽

Santosh K. Panda ◽

Dar A. Roberts ◽

Christine F. Waigl ◽

Uma S. Bhatt ◽

...

Keyword(s):

Land Cover ◽

Spectral Resolution ◽

Hyperspectral Image ◽

Spectral Response ◽

Spectral Characteristics ◽

Hyperspectral Data ◽

Spectral Unmixing ◽

High Spectral Resolution ◽

Fuel Mapping ◽

Sentinel 2

Alaska has witnessed a significant increase in wildfire events in recent decades that have been linked to drier and warmer summers. Forest fuel maps play a vital role in wildfire management and risk assessment. Freely available multispectral datasets are widely used for land use and land cover mapping, but they have limited utility for fuel mapping due to their coarse spectral resolution. Hyperspectral datasets have a high spectral resolution, ideal for detailed fuel mapping, but they are limited and expensive to acquire. This study simulates hyperspectral data from Sentinel-2 multispectral data using the spectral response function of the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) sensor, and normalized ground spectra of gravel, birch, and spruce. We used the Uniform Pattern Decomposition Method (UPDM) for spectral unmixing, which is a sensor-independent method, where each pixel is expressed as the linear sum of standard reference spectra. The simulated hyperspectral data have spectral characteristics of AVIRIS-NG and the reflectance properties of Sentinel-2 data. We validated the simulated spectra by visually and statistically comparing it with real AVIRIS-NG data. We observed a high correlation between the spectra of tree classes collected from AVIRIS-NG and simulated hyperspectral data. Upon performing species level classification, we achieved a classification accuracy of 89% for the simulated hyperspectral data, which is better than the accuracy of Sentinel-2 data (77.8%). We generated a fuel map from the simulated hyperspectral image using the Random Forest classifier. Our study demonstrated that low-cost and high-quality hyperspectral data can be generated from Sentinel-2 data using UPDM for improved land cover and vegetation mapping in the boreal forest.

Download Full-text

Rapid tannin profiling of tree fodders using untargeted mid-infrared spectroscopy and partial least squares regression

Plant Methods ◽

10.1186/s13007-021-00715-8 ◽

2021 ◽

Vol 17 (1) ◽

Author(s):

Jordi Ortuño ◽

Sokratis Stergiadis ◽

Anastasios Koidis ◽

Jo Smith ◽

Chris Humphrey ◽

...

Keyword(s):

Infrared Spectroscopy ◽

Least Squares ◽

Partial Least Squares ◽

Partial Least Squares Regression ◽

Multivariate Calibration ◽

Plant Ecology ◽

Coefficient Of Determination ◽

Least Squares Regression ◽

Mid Infrared ◽

Mid Infrared Spectroscopy

Abstract Background The presence of condensed tannins (CT) in tree fodders entails a series of productive, health and ecological benefits for ruminant nutrition. Current wet analytical methods employed for full CT characterisation are time and resource-consuming, thus limiting its applicability for silvopastoral systems. The development of quick, safe and robust analytical techniques to monitor CT’s full profile is crucial to suitably understand CT variability and biological activity, which would help to develop efficient evidence-based decision-making to maximise CT-derived benefits. The present study investigates the suitability of Fourier-transformed mid-infrared spectroscopy (MIR: 4000–550 cm−1) combined with multivariate analysis to determine CT concentration and structure (mean degree of polymerization—mDP, procyanidins:prodelphidins ratio—PC:PD and cis:trans ratio) in oak, field maple and goat willow foliage, using HCl:Butanol:Acetone:Iron (HBAI) and thiolysis-HPLC as reference methods. Results The MIR spectra obtained were explored firstly using Principal Component Analysis, whereas multivariate calibration models were developed based on partial least-squares regression. MIR showed an excellent prediction capacity for the determination of PC:PD [coefficient of determination for prediction (R2P) = 0.96; ratio of prediction to deviation (RPD) = 5.26, range error ratio (RER) = 14.1] and cis:trans ratio (R2P = 0.95; RPD = 4.24; RER = 13.3); modest for CT quantification (HBAI: R2P = 0.92; RPD = 3.71; RER = 13.1; Thiolysis: R2P = 0.88; RPD = 2.80; RER = 11.5); and weak for mDP (R2P = 0.66; RPD = 1.86; RER = 7.16). Conclusions MIR combined with chemometrics allowed to characterize the full CT profile of tree foliage rapidly, which would help to assess better plant ecology variability and to improve the nutritional management of ruminant livestock.

Download Full-text