Combination of soil color information and machine learning technique for rapid quantification of soil organic matter

Yun-Gu Kang; Jun-Yeong Lee; Jun-Ho Kim; Jiwon Choi; Yong-Jun Kim; Taek-Keun Oh

doi:10.7744/kjoas.530106

All Issue

2026 Vol.53, Issue 1 Preview Page Next Page

Food & Chemistry

Combination of soil color information and machine learning technique for rapid quantification of soil organic matter

1 March 2026. pp. 63-74

PDF XML

Abstract

Soil organic matter (OM) is a crucial indicator of soil productivity and sustainable management; however, traditional OM quantification is time-consuming and labor-intensive. This study aimed to develop land-use-specific OM predictive models using smartphone-based soil color data and machine learning (ML) algorithms. A total of 1,459 soil samples were collected from upland, paddy, and orchard fields in the Chungcheong province, South Korea. Soil images were captured using four different smartphones (e.g., Samsung and Apple) under controlled conditions, and color variables were converted into Commission Internationale de I’Elcairage (CIE)-guided color spaces (e.g., CIE-L^*a^*b^* and CIE-L^*c^*h^*) to minimize device-specific errors. Three ML algorithms, including multiple linear regression (MLR), support vector machine (SVM), and random forest (RF), were evaluated. Pearson correlation analysis identified L^*, b^*, and h^* parameters as key predictors, confirming that soil color darkens as OM content increases. Among the ML algorithms, RF model demonstrated the most stable and superior regression performance, achieving a coefficient of determination (R²) of up to 0.759 for paddy soils, while maintaining consistency across both training and test datasets. These findings suggest that integrating smartphone-based colorimetry with RF algorithms provides a potential alternative to traditional OM analysis, enabling efficient real-time field monitoring for sustainable agricultural land management.

Keywords

agriculture

image analysis

land-use type

smartphone

soil management

References

Baumann K, Schoning I, Schrumpf M, Ellerbrock RH, Leinweber P. 2016. Rapid assessment of soil organic matter: Soil color analysis and Fourier transform infrared spectroscopy. Geoderma 278:49-57.

10.1016/j.geoderma.2016.05.012

Dai L, Wang Z, Zhuo Z, Ma Y, Shi Z, Chen S. 2025. Prediction of soil organic carbon fractions in tropical cropland using a regional visible and near-infrared spectral library and machine learning. Soil and Tillage Research 245:106297.

10.1016/j.still.2024.106297

Dai Z, Liu X, Ding Y. 2024. Iron-removal learning machine for multicolor determination of soil organic carbon. Journal of Soils and Sediments 24:2058-2067.

10.1007/s11368-024-03770-5

Fu Y, Taneja P, Lin S, Ji W, Adamchuk V, Daggupati P, Biswas A. 2020. Predicting soil organic matter from cellular phone images under varying soil moisture. Geoderma 361:114020.

10.1016/j.geoderma.2019.114020

Heil J, Jorges C, Stumpe B. 2022. Fine-scale mapping of soil organic matter in agricultural soils using UAVs and machine learning. Remote Sensing 14:3349.

10.3390/rs14143349

Ho VH, Morita H, Ho TH, Bachofer F, Nguyen TT. 2025. Comparison of geostatistics, machine learning algorithms, and their hybrid approaches for modeling soil organic carbon density in tropical forests. Journal of Soils and Sediments 25:1554-1577.

10.1007/s11368-025-04027-5

Hyun BK, Lee Y, Ryu CH, Cho Y. 2022. Estimation of soil organic matter content using soil organic color chart and soil color meter SPAD 503. Korean Journal of Soil Science and Fertilizer 55:48-57. [in Korean]

10.7745/KJSSF.2022.55.1.048

Kang YG, Choi J, Lee JY, Kim JH, Kim JH, Oh TK. 2025a. Identifying an accurate and efficient approach to soil organic matter removal for quantifying microplastics in agricultural soils. Korean Journal of Agricultural Science 52:417-425. [in Korean]

10.7744/kjoas.520403

Kang YG, Kim YJ, Lee JY, Kim JH, Choi J, Kim JH, Oh TK. 2025b. Short-term effect of biochar application on crop productivity under varying soil pH conditions. Korean Journal of Agricultural Science 52:481-490. [in Korean]

10.7744/kjoas.520407

Kang YG, Lee JY, Kim JH, Oh TK. 2024. Quantifying soil organic matter for sustainable agricultural land management with soil color and machine learning technique. Agronomy Journal 116:982-989.

10.1002/agj2.21525

Kang YG, Sonn YK, Lee JH, Chun JH, Lee CH, Oh TK. 2022. Prediction of soil carbon contents using smartphone images and multiple regression analysis. Korean Journal of Soil Science and Fertilizer 55:228-238. [in Korean]

10.7745/KJSSF.2022.55.3.228

Kim JH, Kang YG, Lee JY, Kim JH, Choi JW, Oh TK. 2024. Influences of silicate fertilizers containing different rates of iron slag on CH₄ emission and rice (Oryza sativa L.) growth. Korean Journal of Agricultural Science 51:227-238. [in Korean]

10.7744/kjoas.510213

Kim JH, Kang YG, Lee JY, Kim JH, Choi JW, Oh TK. 2025. Effect of organic fertilizers mixed with ginkgo leaf biochar on lettuce growth and soil chemical properties. Environmental Research Communications 7:115027.

10.1088/2515-7620/ae219d

Lee JY, Kang YG, Kim JH, Kim JH, Choi J, Oh TK. 2024. Quantification of methane emissions in rice paddies: A machine learning approach with rice cultivar and transplanting date. Korean Journal of Soil Science and Fertilizer 57:331-343. [in Korean]

10.7745/KJSSF.2024.57.4.331

Mundada S, Jain P. 2025. Predicting soil organic carbon with ensemble learning techniques by using satellite images for precision farming. Scientific Reports 15:28760.

10.1038/s41598-025-09804-340769997PMC12328729

Prall J. 2007. Color Cop. Ver. 5.4.5.

Python. 2022. Python. Ver. 3.10.4. Wilmington, DE: Python Software Foundation.

Robertson AR. 1977. The CIE 1976 color-difference formulae. Color Research & Application 2:7-11.

10.1002/j.1520-6378.1977.tb00104.x

Schapire RE. 1990. The strength of weak learnability. Machine Learning 5:197-227.

10.1023/A:1022648800760

Shin JH, Kang YG, Lee JY, Choi J, Kim JH, Kim JH, Oh TK. 2025. Monitoring soil characteristics of the Saemangeum reclaimed agricultural soils for enhancing upland crop productivity. Korean Journal of Agricultural Science 52:223-231. [in Korean]

10.7744/kjoas.520302

Shin JH, Kang YG, Lee JY, Kim JH, Oh TK. 2024. Effect of poultry manure biochar on soil nutrition and carbon improvement in Saemangeum reclaimed soils. Korean Journal of Agricultural Science 51:643-654. [in Korean]

10.7744/kjoas.510418

Sonn YK, Yoo JH, Luyima D, Lee JH, Chun JH, Kang YG, Oh TK, Cho J. 2022. Development of models to estimate total soil carbon across different croplands at a regional scale using RGB photography. International Journal of Environmental Research and Public Health 19:9344.

10.3390/ijerph1915934435954699PMC9368161

Swetha RK, Dasgupta S, Chakraborty S, Li B, Weindorf DC, Mancini M, Silva SHG, Ribeiro BT, Curi N, Ray DP. 2022. Using Nix color sensor and Munsell soil color variables to classify contrasting soil types and predict soil organic carbon in Eastern India. Computers and Electronics in Agriculture 199:107192.

10.1016/j.compag.2022.107192

Tikuye BG, Ray RL. 2025. Soil organic carbon retrieval using a machine learning approach from satellite and environmental covariates in the Lower Brazos River Watershed, Texas, USA. Applied Computing and Geosciences 26:100252.

10.1016/j.acags.2025.100252

Van Bemmelen JM. 1897. Die Absorption. Das Wasser in den Kolloiden, besonders in dem Gel der Kieselsaure. Zeitschrift für anorganische Chemie 13:233-356. [in German]

10.1002/zaac.18970130127

Information

Publisher :Institute of Agricultural Science, Chungnam National University
Publisher(Ko) :충남대학교 농업과학연구소
Journal Title :Korean Journal of Agricultural Science
Journal Title(Ko) :농업과학연구
Volume : 53
No :1
Pages :63-74
Received Date : 2026-01-30
Revised Date : 2026-02-14
Accepted Date : 2026-02-19
DOI :https://doi.org/10.7744/kjoas.530106

Korean Journal of Agricultural Science ISSN:2466-2402(Print) 2466-2410(Online) 농업과학연구

All Issue