基于多年月尺度合成影像的耕地土壤有机质空间预测

doi:10.1016/j.jia.2023.09.017

摘要/Abstract

摘要：

快速、准确地获取耕地土壤有机质(SOM)空间分布对农业可持续发展和碳平衡管理较为重要。本文提出了基于多年月尺度合成影像预测SOM的方法。利用谷歌地球引擎(GEE)平台获取2016-2021年覆盖整个研究区的哨兵2号遥感影像数据并逐月合成，提取合成影像的光谱波段和植被指数作为环境协变量，并构建随机森林(RF)、支持向量机(SVM)和梯度提升回归树(GBRT)模型比较不同变量组合下SOM预测精度的差异。结果表明：(1) 1、3、4、10和 11 月合成的光谱波段均与SOM显著相关(P < 0.05)；(2)基于单月变量的模型预测精度整体较低，其中，1月份变量的RF模型预测精度最高，决定系数R²为0.36。但将不同月份变量按四个季度进行组合，第一季度(Q1)和第四季度(Q4)模型预测性能较好，且三个季度变量任意组合的模型预测精度差异较小。当所有月份的变量均被纳入模型时，模型预测性能最佳；(3)三种机器学习算法中，RF模型的预测精度始终高于 SVM 和 GBRT 模型，其决定系数R²为0.56。除 12 月份的Band12波段外，其余变量的重要性无显著差异。该研究为高精度及空间分辨率的SOM数字制图提供了理论参考

Abstract:

Rapid and accurate acquisition of soil organic matter (SOM) information in cultivated land is important for sustainable agricultural development and carbon balance management. This study proposed a novel approach to predict SOM with high accuracy using multiyear synthetic remote sensing variables on a monthly scale. We obtained 12 monthly synthetic Sentinel-2 images covering the study area from 2016 to 2021 through the Google Earth Engine (GEE) platform, and reflectance bands and vegetation indices were extracted from these composite images. Then the random forest (RF), support vector machine (SVM) and gradient boosting regression tree (GBRT) models were tested to investigate the difference in SOM prediction accuracy under different combinations of monthly synthetic variables. Results showed that firstly, all monthly synthetic spectral bands of Sentinel-2 showed a significant correlation with SOM (P<0.05) for the months of January, March, April, October, and November. Secondly, in terms of single-monthly composite variables, the prediction accuracy was relatively poor, with the highest R² value of 0.36 being observed in January. When monthly synthetic environmental variables were grouped in accordance with the four quarters of the year, the first quarter and the fourth quarter showed good performance, and any combination of three quarters was similar in estimation accuracy. The overall best performance was observed when all monthly synthetic variables were incorporated into the models. Thirdly, among the three models compared, the RF model was consistently more accurate than the SVM and GBRT models, achieving an R² value of 0.56. Except for band 12 in December, the importance of the remaining bands did not exhibit significant differences. This research offers a new attempt to map SOM with high accuracy and fine spatial resolution based on monthly synthetic Sentinel-2 images.

Key words: soil organic matter , Sentinel-2 , monthly synthetic images , machine learning model , spatial prediction

. 基于多年月尺度合成影像的耕地土壤有机质空间预测[J]. Journal of Integrative Agriculture, 2024, 23(4): 1393-1408.

Jie Song, Dongsheng Yu, Siwei Wang, Yanhe Zhao, Xin Wang, Lixia Ma, Jiangang Li. Mapping soil organic matter in cultivated land based on multi-year composite images on monthly time scales[J]. Journal of Integrative Agriculture, 2024, 23(4): 1393-1408.

参考文献

Akpa S I C, Odeh I O A, Bishop T F A, Hartemink A E, Amapu I Y. 2016. Total soil organic carbon and carbon sequestration potential in Nigeria. Geoderma, 271, 202–215.

Baumgardner M F, Silva L F, Biehl L L, Stoner E R. 1986. Reflectance properties of soils. Advances in Agronomy, 38, 1–44.

Ben-Dor E, Inbar Y, Chen Y. 1997. The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400–2500 nm) during a controlled decomposition process. Remote Sensing of Environment, 61, 1–15.

Bolton D K, Friedl M A. 2013. Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics. Agricultural and Forest Meteorology, 173, 74–84.

Breiman L. 2001. Random forests. Machine Learning, 45, 5–32.

Castaldi F, Chabrillat S, Don A, Van Wesemael B. 2019. Soil organic carbon mapping using LUCAS topsoil database and Sentinel-2 data: An approach to reduce soil moisture and crop residue effects. Remote Sensing, 11, 2121.

Chabrillat S, Ben-Dor E, Cierniewski J, Gomez C, Schmid T, van Wesemael B. 2019. Imaging spectroscopy for soil mapping and monitoring. Surveys in Geophysics, 40, 361–399.

Chai L, Wang Y H, Wang X, Ma L, Cheng Z X, Su L M. 2021. Pollution characteristics, spatial distributions, and source apportionment of heavy metals in cultivated soil in Lanzhou, China. Ecological Indicators,125, 107507.

Chang C W, Laird D A, Mausbach M J, Hurburgh C R. 2001. Near-infrared reflectance spectroscopy–principal components regression analyses of soil properties. Soil Science Society of America Journal, 65, 480–490.

Chen D, Chang N J, Xiao J F, Zhou Q B, Wu W B. 2019. Mapping dynamics of soil organic matter in croplands with MODIS data and machine learning algorithms. Science of the Total Environment, 669, 844–855.

Chen G S, Lu H L, Zou W T, Li L H, Emam M, Chen X B, Jing W P, Wang J, Li C. 2023. Spatiotemporal fusion for spectral remote sensing: A statistical analysis and review. Journal of King Saud University (Computer and Information Sciences), 35, 259–273.

Chen Y, Ma L X, Yu D S, Zhang H D, Feng K Y, Wang X, Song J. 2022. Comparison of feature selection methods for mapping soil organic matter in subtropical restored forests. Ecological Indicators, 135, 108545.

Cortes C, Vapnik V. 1995. Support-vector networks. Machine Learning, 20, 273–297.

Dian R W, Li S T, Sun B, Guo A J. 2021. Recent advances and new guidelines on hyperspectral and multispectral image fusion. Information Fusion, 69, 40–51.

Dou X, Wang X, Liu H J, Zhang X L, Meng L H, Pan Y, Yu Z Y, Cui Y. 2019. Prediction of soil organic matter using multi-temporal satellite images in the Songnen Plain, China. Geoderma, 356, 113896.

Dutta D, Kumar P. 2019. A framework for global characterization of soil properties using repeat hyperspectral satellite data. IEEE Transactions on Geoscience and Remote Sensing, 57, 3308–3323.

Emadi M, Taghizadeh-Mehrjardi R, Cherati A, Danesh M, Mosavi A, Scholten T. 2020. Predicting and mapping of soil organic carbon using machine learning algorithms in northern Iran. Remote Sensing, 12, 2234.

Fathizad H, Taghizadeh-Mehrjardi R, Hakimzadeh Ardakani M A, Zeraatpisheh M, Heung B, Scholten T. 2022. Spatiotemporal assessment of soil organic carbon change using machine-learning in arid regions. Agronomy, 12, 628.

Fathololoumi S, Vaezi A R, Alavipanah S K, Ghorbani A, Saurette D, Biswas A. 2020. Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: A case study in Iran. Science of the Total Environment, 721, 137703.

Fisher A, Rudin C, Dominici F, 2019. All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. Journal of Machine Learning Research, 20, 1–81.

Forkuor G, Hounkpatin O K L, Welp G, Thiel M. 2017. High resolution mapping of soil properties using remote sensing variables in South-Western Burkina Faso: A comparison of machine learning and multiple linear regression models. PLoS ONE, 12, e0170478.

Friedman J H. 2001. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29, 1189–1232.

Gatti A, Bertolini A. 2015. Sentinel-2 products specification document. [2022-2-23]. https://earth.esa.int/documents/247904/685211/Sentinel-2-Products-Specification-Document

Ge X Y, Ding J L, Teng D X, Wang J Z, Huo T C, Jin X Y, Wang J J, He B Z, Han L J. 2022. Updated soil salinity with fine spatial resolution and high accuracy: The synergy of Sentinel-2 MSI, environmental covariates and hybrid machine learning approaches. Catena, 212, 106054.

Gelsleichter Y A, Costa E M, Anjos L H C D, Marcondes R A T. 2023. Enhancing soil mapping with hyperspectral subsurface images generated from soil lab Vis-SWIR spectra tested in southern Brazil. Geoderma Regional, 33, e00641.

Gong Z T, Chen Z C, Zhao W J, Shi H. 2000. Classification of ferrallitic soils in Chinese soil taxonomy. Pedosphere, 10, 125–133.

Gorelick N, Hancher M, Dixon M, Ilyushchenko S, Thau D, Moore R. 2017. Google Earth Engine: planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, 18–27.

Guo L, Fu P, Shi T Z, Chen Y Y, Zeng C, Zhang H T, Wang S Q. 2021. Exploring influence factors in mapping soil organic carbon on low-relief agricultural lands using time series of remote sensing data. Soil and Tillage Research, 210, 104982.

Hamzehpour N, Shafizadeh-Moghadam H, Valavi R. 2019. Exploring the driving forces and digital mapping of soil organic carbon using remote sensing and soil texture. Catena, 182,104141.

He X L, Yang L, Li A Q, Zhang L, Shen F X, Cai Y Y, Zhou C H. 2021. Soil organic carbon prediction using phenological parameters and remote sensing variables generated from Sentinel-2 images. Catena, 205, 105442.

Huete A, Didan K, Miura T, Rodriguez E P, Gao X, Ferreira L G. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment, 83, 195–213.

John K, Abraham Isong I, Michael Kebonye N, Okon Ayito E, Chapman Agyeman P, Marcus Afu S. 2020. Using machine learning algorithms to estimate soil organic carbon variability with environmental variables and soil nutrient indicators in an alluvial soil. Land, 9, 487.

Kaya F, Başayiğit L, Keshavarzi A, Francaviglia R. 2022. Digital mapping for soil texture class prediction in northwestern Türkiye by different machine learning algorithms. Geoderma Regional, 31, e00584.

Keskin H, Grunwald S, Harris W G. 2019. Digital mapping of soil carbon fractions with machine learning. Geoderma, 339, 40–58.

Khanal S, Fulton J, Klopfenstein A, Douridas N, Shearer S. 2018. Integration of high resolution remotely sensed data and machine learning techniques for spatial prediction of soil properties and corn yield. Computers and Electronics in Agriculture, 153, 213–225.

Lai Y Q, Wang H L, Sun X L. 2021. A comparison of importance of modelling method and sample size for mapping soil organic matter in Guangdong, China. Ecological Indicators, 126, 107618.

Lausch A, Bannehr L, Beckmann M, Boehm C, Feilhauer H, Hacker J M, Heurich M, Jung A, Klenke R, Neumann C, Pause M, Rocchini D, Schaepman M E, Schmidtlein S, Schulz K, Selsam P, Settele J, Skidmore A K, Cord A F. 2016. Linking earth observation and taxonomic, structural and functional biodiversity: Local to ecosystem perspectives. Ecological Indicators, 70, 317–339.

Luo C, Zhang X L, Meng X T, Zhu H W, Ni C P, Chen M H, Liu H J. 2022. Regional mapping of soil organic matter content using multitemporal synthetic Landsat 8 images in Google Earth Engine. Catena, 209 (Part 1), 105842.

Mahmoudzadeh H, Matinfar H R, Taghizadeh-Mehrjardi R, Kerry R. 2020. Spatial prediction of soil organic carbon using machine learning techniques in western Iran. Geoderma Regional, 21, e00260.

Meng X Y, Gao X, Li S, Li S Y, Lei J Q. 2021. Monitoring desertification in mongolia based on landsat images and google earth engine from 1990 to 2020. Ecological Indicators, 129, 107908.

Minhoni R T D A, Scudiero E, Zaccaria D, Saad J C C. 2021. Multitemporal satellite imagery analysis for soil organic carbon assessment in an agricultural farm in southeastern Brazil. Science of the Total Environment, 784, 147216.

Molnar C. 2018. Interpretable Machine Learning: A Guide For Making Black Box Models Explainable. 2nd ed. e-book, Leanpub. https://christophm.github.io/interpretable-ml-book/.

Munnaf M A, Mouazen A M. 2022. Removal of external influences from on-line vis-NIR spectra for predicting soil organic carbon using machine learning. Catena, 211, 106015.

Ndepete C P, Sert S, Beycioğlu A, Katanalp B Y, Eren E, Bağrıaçık B, Topolinski S. 2022. Exploring the effect of basalt fibers on maximum deviator stress and failure deformation of silty soils using ANN, SVM and FL supported by experimental data. Advances in Engineering Software, 172, 103211.

Nelson D W, Sommers L E. 1996. Total carbon, organic carbon, and organic matter. In: Methods of Soil Analysis: Part 3. Chemical Methods. Soil Science Society of America, Madison. pp. 961–1010.

Padarian J, Minasny B, McBratney A B. 2020. Machine learning and soil sciences: A review aided by machine learning tools. Soil, 6, 35–52.

Peng D L, Wu C Y, Li C J, Zhang X Y, Liu Z J, Ye H C, Luo S Z, Liu X J, Hu Y, Fang B. 2017. Spring green-up phenology products derived from MODIS NDVI and EVI: intercomparison, interpretation and validation using national phenology network and AmeriFlux observations. Ecological Indicators, 77, 323–336.

Qi J, Kerr Y, Chehbouni A. 1994. External factor consideration in vegetation index development. In: Proceeding of International Symposium on Physical Measurements and Signatures in Remote Sensing. Val D’Isere, France.

R Development Core Team. 2021. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. [2021-10-20]. https://www.R-project.org/

Rogge D, Bauer A, Zeidler J, Mueller A, Esch T, Heiden U. 2018. Building an exposed soil composite processor (SCMaP) for mapping spatial and temporal characteristics of soils with Landsat imagery (1984–2014). Remote Sensing of Environment, 205, 1–17.

Seely B, Welham C, Blanco J A. 2010. Towards the application of soil organic matter as an indicator of forest ecosystem productivity: Deriving thresholds, developing monitoring systems, and evaluating practices. Ecological Indicators, 10, 999–1008.

Shonk J, Gaultney L D, Schulze D G, Van Scoyoc G E. 1991. Spectroscopic sensing of soil organic matter content. Transactions of the ASAE, 34, 1978–1984.

Silvero N E Q, Demattê J A M, Amorim M T A, dos Santos N V, Rizzo R, Safanelli J L, Poppiel R R, Mendes W D S, Bonfatti B R. 2021. Soil variability and quantification based on Sentinel-2 and Landsat-8 bare soil images: A comparison. Remote Sensing of Environment, 252, 112117.

Swain S R, Chakraborty P, Panigrahi N, Vasava H B, Reddy N N, Roy S, Majeed I, Das B S. 2021. Estimation of soil texture using Sentinel-2 multispectral imaging data: An ensemble modeling approach. Soil and Tillage Research, 213, 105134.

Tucker C J. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8, 127–150.

Vaudour E, Gomez C, Fouad Y, Lagacherie P. 2019. Sentinel-2 image capacities to predict common topsoil properties of temperate and Mediterranean agroecosystems. Remote Sensing of Environment, 223, 21–33.

Viscarra Rossel R A, Chappell A, de Caritat P, McKenzie N J. 2011. On the soil information content of visible-near infrared reflectance spectra. European Journal of Soil Science, 62, 442–453.

Wang S, Guan K Y, Zhang C H, Zhou Q, Wang S B, Wu X C, Jiang C Y, Peng B, Mei W Y, Li K Y, Li Z Y, Yang Y, Zhou W, Huang Y Z, Ma Z W. 2023. Cross-scale sensing of field-level crop residue cover: Integrating field photos, airborne hyperspectral imaging, and satellite data. Remote Sensing of Environment, 285, 113366.

Wang X, Wang L P, Li S J, Wang Z M, Zheng M, Song K S. 2022. Remote estimates of soil organic carbon using multi-temporal synthetic images and the probability hybrid model. Geoderma, 425, 116066.

Wang X, Zhang Y H, Atkinson P M, Yao H Y. 2020. Predicting soil organic carbon content in Spain by combining Landsat TM and ALOS PALSAR images. International Journal of Applied Earth Observation and Geoinformation, 92, 102182.

Wang X P, Zhang F, Kung H T, Johnson V C. 2018. New methods for improving the remote sensing estimation of soil organic matter content (SOMC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR) in northwest China. Remote Sensing of Environment, 218, 104–118.

Webster R, Oliver M A. 2010. Sample adequately to estimate variograms of soil properties. Journal of Soil Science, 43, 177–192.

Yang J T, Li X S, Wu B, Wu J J, Sun B, Yan C Z, Gao Z H. 2021. High spatial resolution topsoil organic matter content mapping across desertified land in northern China. Frontiers in Environmental Science, 9, 668912.

Yu G R, Chen Z, Piao S L, Peng C H, Ciais P, Wang Q F, Li X R, Zhu X J. 2014. High carbon dioxide uptake by subtropical forest ecosystems in the East Asian monsoon region. Proceedings of the National Academy of Sciences of the United States of America, 111, 4910–4915.

Zeraatpisheh M, Garosi Y, Owliaie H R, Ayoubi S, Taghizadeh-Mehrjardi R, Scholten T, Xu M. 2022. Improving the spatial prediction of soil organic carbon using environmental covariates selection: A comparison of a group of environmental covariates. Catena, 208, 105723.

Zhang Y C S, Guo L, Chen Y Y, Shi T Z, Luo M, Ju Q L, Zhang H T, Wang S Q. 2019. Prediction of soil organic carbon based on Landsat 8 monthly NDVI data for the Jianghan Plain in Hubei Province, China. Remote Sensing, 11, 1683.

Zhou T, Geng Y J, Ji C, Xu X R, Wang H, Pan J J, Jan B, Dagmar H, Angela L. 2021. Prediction of soil organic carbon and the C:N ratio on a national scale using machine learning and satellite data: A comparison between Sentinel-2, Sentinel-3 and Landsat-8 images. Science of the Total Environment, 755, 142661.