A Framework for Retrieving Soil Organic Matter by Coupling Multi-Temporal Remote Sensing Images and Variable Selection in the Sanjiang Plain, China

Soil organic matter (SOM) is an important soil property for agricultural production. Rising grain demand has increased the intensity of cultivated land development in the Sanjiang Plain of China, and there is a strong demand for SOM monitoring in this region. Therefore, Baoqing County of the Sanjiang Plain, an important grain production area, was considered the study area. In the study, we proposed a framework for high-accuracy SOM retrieval by coupling multi-temporal remote sensing (RS) images and variable selection algorithms. A total of 73 surface soil samples (0–20 cm) were collected in 2010, and Landsat 5 images acquired during the bare soil period (April, May, and June) were selected from 2008 to 2011. Three variable selection algorithms, namely, Genetic Algorithm, Random Frog and Competitive Adaptive Reweighted Sampling (CARS), were combined with Partial Least Squares Regression (PLSR) to build SOM retrieval models on the spectral bands and indices of the images. The results using a single-date image showed that the combination of variable selection algorithms and PLSR outperformed using PLSR alone, and CARS showed the best performance (R2 = 0.34, RMSE = 15.66 g/kg) among all the algorithms. Therefore, only CARS was applied to SOM retrieval in the different year interval groups. To investigate the effect of the image acquisition time, all images were divided into various year interval groups, and the resulting images were then stacked. The results using multi-temporal images showed that the SOM retrieval accuracy improved as the year interval lengthened. The optimal result (R2 = 0.59, RMSE = 11.81 g/kg) was obtained from the 2008–2011 group, wherein the difference indices derived from the images of 2009, 2010, and 2011 dominated the selected spectral variables. Moreover, the spatial prediction of SOM based on the optimal model was consistent with the distribution of SOM. Our study suggested that the proposed framework that couples stacked multi-temporal RS images with variable selection algorithms has potential for SOM retrieval.

[1]  Huanjun Liu,et al.  Remote Sensing Prediction Model of Cultivated Land Soil Organic Matter Considering the Best Time Window , 2022, Sustainability.

[2]  J. Six,et al.  Towards spatially continuous mapping of soil organic carbon in croplands using multitemporal Sentinel-2 remote sensing , 2022, ISPRS Journal of Photogrammetry and Remote Sensing.

[3]  Dongming Li,et al.  Inversion of Soil Organic Matter Content Based on Improved Convolutional Neural Network , 2022, Sensors.

[4]  K. Van Oost,et al.  High-Resolution Soil Organic Carbon Mapping at the Field Scale in Southern Belgium (Wallonia) , 2022, SSRN Electronic Journal.

[5]  Siqin Tong,et al.  Change of Rice Paddy and Its Impact on Human Well-Being from the Perspective of Land Surface Temperature in the Northeastern Sanjiang Plain of China , 2022, International journal of environmental research and public health.

[6]  Jannis Heil,et al.  Fine-Scale Mapping of Soil Organic Matter in Agricultural Soils Using UAVs and Machine Learning , 2022, Remote. Sens..

[7]  Xia Zhang,et al.  Estimation of soil organic matter content using selected spectral subset of hyperspectral data , 2022, Geoderma.

[8]  C. Gomez,et al.  Satellite Multi-Sensor Data Fusion for Soil Clay Mapping Based on the Spectral Index and Spectral Bands Approaches , 2022, Remote. Sens..

[9]  Huanjun Liu,et al.  Regional mapping of soil organic matter content using multitemporal synthetic Landsat 8 images in Google Earth Engine , 2022, CATENA.

[10]  Yu Han,et al.  Mapping Soil Organic Matter and Analyzing the Prediction Accuracy of Typical Cropland Soil Types on the Northern Songnen Plain , 2021, Remote. Sens..

[11]  Taha Gorji,et al.  Assessing the performance of machine learning algorithms for soil salinity mapping in Google Earth Engine Platform using Sentinel-2A and Landsat-8 OLI data , 2021, Advances in Space Research.

[12]  Ke Wu,et al.  A Novel Change Detection Approach Based on Spectral Unmixing from Stacked Multitemporal Remote Sensing Images with a Variability of Endmembers , 2021, Remote. Sens..

[13]  Biswabara Sahu,et al.  Deterministic and geostatistical models for predicting soil organic carbon in a 60 ha farm on Inceptisol in Varanasi, India , 2021 .

[14]  Philippe Lagacherie,et al.  Temporal mosaicking approaches of Sentinel-2 images for extending topsoil organic carbon content mapping in croplands , 2021, Int. J. Appl. Earth Obs. Geoinformation.

[15]  Z. Venter,et al.  Mapping soil organic carbon stocks and trends with satellite-driven high resolution maps over South Africa. , 2021, The Science of the total environment.

[16]  Wu Xiao,et al.  Multi-Temporal Mapping of Soil Total Nitrogen Using Google Earth Engine across the Shandong Province of China , 2020, Sustainability.

[17]  T. Kuyper,et al.  Eco-functionality of organic matter in soils , 2020, Plant and Soil.

[18]  A. Mouazen,et al.  Comparing laboratory and airborne hyperspectral data for the estimation and mapping of topsoil organic carbon: Feature selection coupled with random forest , 2020 .

[19]  M. Feng,et al.  An efficient variable selection method based on random frog for the multivariate calibration of NIR spectra , 2020, RSC advances.

[20]  R. Meng,et al.  Mapping field-scale soil organic carbon with unmanned aircraft system-acquired time series multispectral images , 2020 .

[21]  Hong Ji,et al.  CARS Algorithm-Based Detection of Wheat Moisture Content before Harvest , 2020, Symmetry.

[22]  Huanjun Liu,et al.  Prediction of soil organic matter using multi-temporal satellite images in the Songnen Plain, China , 2019 .

[23]  Hidetoshi Asai,et al.  Laboratory Visible and Near-Infrared Spectroscopy with Genetic Algorithm-Based Partial Least Squares Regression for Assessing the Soil Phosphorus Content of Upland and Lowland Rice Fields in Madagascar , 2019, Remote. Sens..

[24]  E. Vaudour,et al.  Sentinel-2 image capacities to predict common topsoil properties of temperate and Mediterranean agroecosystems , 2019, Remote Sensing of Environment.

[25]  Yi Li,et al.  Soil Moisture Retrieval Model for Remote Sensing Using Reflected Hyperspectral Information , 2019, Remote. Sens..

[26]  Lin Li,et al.  Agricultural Development and Implication for Wetlands Sustainability: A Case from Baoqing County, Northeast China , 2019, Chinese Geographical Science.

[27]  Qing-Song Xu,et al.  libPLS: An integrated library for partial least squares regression and linear discriminant analysis , 2018 .

[28]  Xuezheng Shi,et al.  Economics- and policy-driven organic carbon input enhancement dominates soil organic carbon accumulation in Chinese croplands , 2018, Proceedings of the National Academy of Sciences.

[29]  Michael E. Schaepman,et al.  Barest Pixel Composite for Agricultural Areas Using Landsat Time Series , 2017, Remote. Sens..

[30]  Susana Fernández,et al.  Prediction of Topsoil Organic Carbon Using Airborne and Satellite Hyperspectral Imagery , 2017, Remote. Sens..

[31]  Jinchi Zhang,et al.  Vegetation change impacts on soil organic carbon chemical composition in subtropical forests , 2016, Scientific Reports.

[32]  R. Casa,et al.  Evaluation of the potential of the current and forthcoming multispectral and hyperspectral imagers to estimate soil texture and organic carbon , 2016 .

[33]  J. Huising,et al.  Effects of land cover on ecosystem services in Tanzania: A spatial assessment of soil organic carbon , 2016 .

[34]  Huajun Tang,et al.  Cropland soil organic matter content change inNortheast China, 1985-2005 , 2015 .

[35]  M. Bernoux,et al.  From forest to cropland and pasture systems: a critical review of soil organic carbon stocks changes in Amazonia , 2015, Global change biology.

[36]  T. G. Orton,et al.  Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale , 2014, 1502.02513.

[37]  Zhou Shi,et al.  Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations , 2014, Science China Earth Sciences.

[38]  Qing-Song Xu,et al.  Random frog: an efficient reversible jump Markov Chain Monte Carlo-like approach for variable selection with applications to gene selection and disease classification. , 2012, Analytica chimica acta.

[39]  Bo Du,et al.  Targeted change detection for stacked multi-temporal hyperspectral image , 2012, 2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS).

[40]  A. Marchetti,et al.  Spatial Distribution of Soil Organic Matter Using Geostatistics: A Key Indicator to Assess Soil Degradation Status in Central Italy , 2012 .

[41]  Huazhou Chen,et al.  Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods , 2011 .

[42]  R. V. Rossel,et al.  Using data mining to model and interpret soil diffuse reflectance spectra. , 2010 .

[43]  Zou Xiaobo,et al.  Variables selection methods in near-infrared spectroscopy. , 2010, Analytica chimica acta.

[44]  Xuezheng Shi,et al.  Cross-reference for relating Genetic Soil Classification of China with WRB at different scales , 2010 .

[45]  Hongdong Li,et al.  Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. , 2009, Analytica chimica acta.

[46]  L. Marks,et al.  A genetic algorithm for variable selection in logistic regression analysis of radiotherapy treatment outcomes. , 2008, Medical physics.

[47]  R. V. Rossel,et al.  Soil organic carbon prediction by hyperspectral remote sensing and field vis-NIR spectroscopy: An Australian case study , 2008 .

[48]  W. Cai,et al.  Outlier detection in near-infrared spectroscopic analysis by using Monte Carlo cross-validation , 2008 .

[49]  M. Schaepman,et al.  Spectral reflectance based indices for soil organic carbon quantification , 2008 .

[50]  Cheryl A. Palm,et al.  Soils: A Contemporary Perspective , 2007 .

[51]  Bas van Wesemael,et al.  Regional assessment of soil organic carbon changes under agriculture in Southern Belgium (1955-2005) , 2007 .

[52]  E-T Vesely,et al.  What is soil organic matter worth? , 2006, Journal of environmental quality.

[53]  Vincent Baeten,et al.  Multivariate Calibration and Chemometrics for near Infrared Spectroscopy: Which Method? , 2000 .

[54]  Riccardo Leardi,et al.  Application of genetic algorithm–PLS for feature selection in spectral data sets , 2000 .

[55]  R. Leardi,et al.  Genetic algorithms applied to feature selection in PLS regression: how and when to use them , 1998 .

[56]  H. Tiessen,et al.  The role of soil organic matter in sustaining soil fertility , 1994, Nature.

[57]  L. Wilding,et al.  Spatial variability: its documentation, accommodation and implication to soil surveys , 1985 .

[58]  Zongming Wang,et al.  Remote estimates of soil organic carbon using multi-temporal synthetic images and the probability hybrid model , 2022, Geoderma.

[59]  Huanjun Liu,et al.  Hyper-temporal remote sensing data in bare soil period and terrain attributes for digital soil mapping in the Black soil regions of China , 2020 .

[60]  Ning Ma,et al.  A Novel Nonlinear Partial Least Square Integrated With Error-Based Extreme Learning Machine , 2019, IEEE Access.

[61]  Minzan Li,et al.  Prediction of Total Nitrogen in Soil Based on Random Frog Leaping Wavelet Neural Network , 2018 .

[62]  Annamaria Castrignanò,et al.  Laboratory-based Vis–NIR spectroscopy and partial least square regression with spatially correlated errors for predicting spatial variation of soil organic matter content , 2015 .

[63]  Deutsche Ausgabe.  World Reference Base for Soil Resources 2006 , 2007 .