Soil organic carbon variability assessment using satellite imagery and artificial neural network

SHYAMAL  MUNDADA; POOJA  JAIN

doi:10.56093/ijas.v95i8.161380

Authors

SHYAMAL MUNDADA Indian Institute of Information Technology, Nagpur, Maharashtra 441 108, India
POOJA JAIN Indian Institute of Information Technology, Nagpur, Maharashtra 441 108, India

https://doi.org/10.56093/ijas.v95i8.161380

Keywords:

Environmental covariates, Neural network soil organic carbon, Spatial modelling

Abstract

The present study was carried out during 2022–2024 at Indian Institute of Information Technology, Nagpur, Maharashtra to evaluate SOC stocks in the Dhamtari district of Chhattisgarh, India. Two machine learning models and their variants-Boosted Regression Tree, Boosted Regression Tree with Early Stopping, Multilayer Perceptron, and Multilayer Perceptron with Early Stopping were used for predicting Soil Organic Carbon (SOC). The findings of the research indicated that Multilayer Perceptron produced better results in both scenarios that is, without and with Early Stopping technique applied. Multilayer Perceptron with Early Stopping model recorded nearly the same RMSE for both calibration and validation datasets as 0.1618 and 0.1601, respectively. Produced soil maps will assist farmers in adopting accurate information for decisions which will boost farm output and offer security for food through the balanced use of nutrients.

Downloads

Download data is not yet available.

References

Bationo Andre, Job Kihara, Bernard Vanlauwe, Boaz Waswa and Joseph Kimetu. 2007. Soil organic carbon dynamics, functions and management in West African agro-ecosystems. Agricultural Systems 94: 13–25.

Batjes N H. 1996. Total carbon and nitrogen in the soils of the world. European Journal of Soil Science 47: 151–63.

Brady, Nyle C and Ray R Weil. 2008. The Nature and Properties of Soils, Vol. 13. Prentice Hall Upper Saddle River, New Jersey. Cambule A H, Rossiter D G, Stoorvogel J J and Smaling E M A. 2014. Soil organic carbon stocks in the Limpopo National Park, Mozambique: Amount spatial distribution and uncertainty. Geoderma 213: 46–56.

Danaher S and E O'Mongain. 1992. Singular value decomposition in multispectral radiometry. International Journal of Remote Sensing 13: 1771–77.

Doetterl Sebastian, Antoine Stevens, Kristof van Oost, Timothy A Quine and Bas van Wesemael. 2013. Spatially-explicit regional-scale prediction of soil organic carbon stocks in cropland using environmental variables and mixed model approaches. Geoderma 204–05: 31–42.

Drake, John M, Randin, Christophe, Guisan and Antoine. 2006. Modelling ecological niches with support vector machines. Journal of Applied Ecology 43: 424–32.

El-Ramady, Hassan R, T A Alshaal, M Amer, E Domokos- Szabolcsy, N Elhawat, J Prokisch, and M Fári. 2014. Soil quality and plant nutrition. Sustainable Agriculture Reviews Agroecology and Global Change, pp. 345–447. Springer.

Friedman Jerome H. 2002. Stochastic gradient boosting. Computational Statistics and Data Analysis 38: 367–78.

Friedman, Jerome, Trevor Hastie and Robert Tibshirani. 2000. Additive logistic regression: A statistical view of boosting (With discussion and a rejoinder by the authors). The Annals of Statistics (Institute of Mathematical Statistics) 28: 337–407.

Gardner M W and Dorling S R. 1998. Artificial neural networks (the multilayer perceptron)–A review of applications in the atmospheric sciences. Atmospheric Environment 32: 2627–36.

Golub G H and C Reinsch. 1970. Singular value decomposition and least squares solutions. Numerische Mathematik 14: 403–20.

Grimm R, T Behrens, M Märker and H Elsenbeer. 2008. Soil organic carbon concentrations and stocks on Barro Colorado Island-Digital soil mapping using Random Forests analysis. Geoderma 146: 102–13.

Hastie Trevor, Robert Tibshirani and Jerome Friedman. 2009. Basis Expansions and Regularization in the Elements of Statistical Learning: Data Mining, Inference, and Prediction, pp. 139–89. Springer New York.

Hengl Tomislav, Gerard B M, Heuvelink G B and Alfred Stein. 2004. A generic framework for spatial prediction of soil variables based on regression-kriging. Geoderma 120: 75–93.

Hengl, Heuvelink G B and David G Rossiter. 2007. About regression-kriging: From equations to case studies. Computers and Geosciences 33: 1301–15.

Huete, Alfredo, Kamel Didan, Tomoaki Miura, E Patricia Rodriguez, Xiang Gao and Laerte G Ferreira. 2002. Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sensing of Environment 83: 195–213.

Jaber Salahuddin M and Mohammed I Al-Qinna. 2011. Soil organic carbon modeling and mapping in a semi-arid environment using thematic mapper data. Photogrammetric Engineering and Remote Sensing 77: 709–19.

Karnieli Arnon. 1997. Development and implementation of spectral crust index over dune sands. International Journal of Remote Sensing 18: 1207–20.

Karunaratne S B, T F A Bishop, J A Baldock and I O A Odeh. 2014. Catchment scale mapping of measureable soil organic carbon fractions. Geoderma 219: 14–23.

Kaufman J and Didier Tanre. 1992. Atmospherically resistant vegetation index (ARVI) for EOS-MODIS. IEEE Transactions on Geoscience and Remote Sensing 30: 261–70.

Kumar A, Moharana P C, Jena R K, Malyan S K, Sharma G K, Fagodiya R K, Shabnam A A, Jigyasu D K, Kumari K M V and Doss S G. 2023. Digital mapping of soil organic carbon using machine learning algorithms in the upper Brahmaputra valley of north-eastern India. Land 12.

Kumar Sandeep, Lal Rattan and Desheng Liu. 2012. A geographically weighted regression kriging approach for mapping soil organic carbon stock. Geoderma 189: 627–34.

Kumaraperumal R, Pazhanivelan S, Geethalakshmi V, Nivas Raj M, Muthumanickam D, Kaliaperumal R, Shankar V, Nair A M, Yadav M K and Tarun Kshatriya T V. 2022. Comparison of machine learning-based prediction of qualitative and quantitative digital soil-mapping approaches for eastern districts of Tamil Nadu, India. Land 11(12): 2279.

Lefevre C, Rekik F, Alcantara V and Wiese L. 2017. Soil Organic Carbon: The Hidden Potential. Food and Agriculture Organization, United Nations.

Li Qi-quan, Tian-xiang Yue, Chang-quan Wang, Wen-jiang Zhang, Yong Yu, Bing Li, Juan Yang and Gen-chuan Bai. 2013. Spatially distributed modeling of soil organic matter across China: An application of artificial neural network approach. Catena 104: 210–18.

Malone B P, A B McBratney, B Minasny and G M Laslett. 2009. Mapping continuous depth functions of soil carbon storage and available water capacity. Geoderma 154: 138–52.

Martin M P, M Wattenbach, P Smith, J Meersmans, C Jolivet, L Boulonne and D Arrouays. 2011. Spatial distribution of soil organic carbon stocks in France. Biogeosciences 8: 1053–65.

Meersmans J, F De Ridder, F Canters, S De Baets and M Van Molle. 2008. A multiple regression approach to assess the spatial distribution of Soil Organic Carbon (SOC) at the regional scale (Flanders, Belgium). Geoderma 143: 1–13.

Meliho M, Boulmane M, Khattabi A, Dansou C E, Orlando C A, Mhammdi N and Noumonvi K D. 2023. Spatial prediction of soil organic carbon stock in the Moroccan high atlas using machine learning. Remote Sensing 15.

Raya S S, J P Singhb, Gargi Dasa and Sushma Panigrahyb. 2004. Use of high resolution remote sensing data for generating site- specific soil management plan. Red 550: 727.

Rossel R A Viscarra and T Behrens. 2010. Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma 158: 46–54.

Roy, David P, Michael A Wulder, Thomas R Loveland, Curtis E Woodcock, Richard G Allen, Martha C Anderson and Dennis Helder. 2014. Landsat-8: Science and product vision for terrestrial global change research. Remote Sensing of Environment 145: 154–72.

Sahoo Uttam Kumar, Soibam Lanabir Singh, Anudip Gogoi, Alice Kenye and Snehasudha S Sahoo. 2019. Active and passive soil organic carbon pools as affected by different land use types in Mizoram north-east India. PLOS one 14: 1–16.

Sarkar S, De B, Das P, Saha D, Awasthi D P, Paul N and Sen D. 2025. Nutrient management approach to improve productivity and profitability of pigeonpea (Cajanus cajan) in north-east hill zones of India. The Indian Journal of Agricultural Sciences 95(4): 400–05.

Schapire Robert E. 2003. The Boosting Approach to Machine Learning: An Overview. In Nonlinear Estimation and Classification, pp. 149–71. David D Denison, Mark H Hansen, Christopher C Holmes, Bani Mallick and Bin Yu (Eds). Springer, New York.

Shekar B H and Guesh Dagnew. 2019. Grid search-based hyperparameter tuning and classification of microarray cancer data. Second International Conference on Advanced Computational and Communication Paradigms, pp. 1–8.

Stankewitz Bernhard. 2024. Early stopping for L²- boosting in high-dimensional linear models. The Annals of Statistics 52(2): 491–518.

Vagen Tor-Gunnar and Leigh A Winowiecki. 2013. Mapping of soil organic carbon stocks for spatially explicit assessments of climate change mitigation potential. Environmental Research Letters (IOP Publishing) 8: 015–011.

Wiesmeier Martin, Frauke Barthold, Benjamin Blank and Ingrid Kogel-Knabner. 2011. Digital mapping of soil organic matter stocks using Random Forest modeling in a semi-arid steppe ecosystem. Plant and Soil 340: 7–24.

Willmott Cort J and Kenji Matsuura. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research 30: 79–82.

Wright Sewall. 1921. Correlation and causation. Journal of Agricultural Research 20(7): 557.

Yang Yuanhe, Jingyun Fang, Yanhong Tang, Chengjun Ji, Chengyang Zheng, Jinsheng He and Biao Zhu. 2008. Storage, patterns and controls of soil organic carbon in the Tibetan grasslands. Global Change Biology 14(7): 1592–99.

Zhenxing Bian, Shuai Wang, Qianlai Zhuang Xinxin Jin Qiubing Wang and Shuhai Jia. 2020. Applying statistical methods to map soil organic carbon of agricultural lands in northeastern coastal areas of China. Archives of Agronomy and Soil Science 66: 532–44.