Detection of Soil Organic Matter Using IoT-Based Soil Color Sensors with Random Forest Method

Muhammad Afifi Andriansyah, Lusia Rakhmawati, I Gusti Putu Asto Buditjahjanto

Abstract


Background: Soil organic matter (SOM) is an important indicator of soil fertility that plays a role in agricultural productivity and ecosystem sustainability. However, conventional laboratory-based methods still have limitations in terms of time, cost, and do not support real-time monitoring. Therefore, an approach based on sensors and machine learning is needed for quick and efficient estimation. This study proposes an Internet of Things (IoT)-based system that integrates an RGB soil color sensor (TCS3200) and a pH sensor to estimate soil organic matter content using a Random Forest algorithm. Methodology: Laboratory analysis was conducted using the Walkley–Black method. Soil samples were taken from seven locations (T1–T7). The Random Forest model was developed with parameters n_estimators = 100 and max_depth = 10, and validated using a train-test split method (80:20). Findings: The results showed that darker-colored soils have higher organic carbon content. The model's error values indicated an MAE of 0.031 and an RMSE of 0.032. The Random Forest model achieved a classification accuracy of 85.7% and a coefficient of determination R² ≈ 0.97. Contributions: This study contributes by developing an integrated IoT and machine learning system capable of quickly, accurately, and cost-effectively estimating soil organic matter to support precision agriculture

Keywords


Internet of Things; Random Forest; Soil Color; Soil Organic Matter; Precision Agriculture

Full Text:

PDF

References


Adeniyi, O. D., Brenning, A., Bernini, A., Brenna, S., & Maerker, M. (2023). Digital Mapping of Soil Properties Using Ensemble Machine Learning Approaches in an Agricultural Lowland Area of Lombardy, Italy. Land, 12(2), 494. https://doi.org/10.3390/land12020494

Andriansyah, M. A. (2025). Designing soil Color Sensors To Determine Soil Characteristics Based on Internet of Things (IoT). Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering), 14(1), 83–91.

Balı´kJ, S. P. (2025). Changes in Soil Organic Matter Content And Quality After Application Of Different Organic And Mineral Fertilisers in 27 Years Long-Term Field Experiments On Luvisol. Front. Soil Sci, 5:1540137. doi: 10.3389/fsoil.2025.1540137 .

Barros, P. Â., Pedrosa, E. M., Cardoso, M. S., & Mario Monteiro Rolim Ciências Agrárias, L. (2017). Relationship between soil organic matter and nematodes in sugarcane fields. mar./abr. , v. 38, n. 2, p. 551-560.

Brady, N. C., & Weil, R. R. (2021). The Nature And properties of soils. 14Th Edition. Pearson. 1046 page

James, G., Witten, D., Hastie, T., & Tibshirani, R. (2014). An Introduction to Statistical Learning: With Applications in R. Stat. New York: Springer. 426 page.

Guo, L., Gao, Q., Zhang, M., Cheng, P., He, P., Li, L., Ding, D., Liu, C., Muga, F. C., Kamal, M., & Qi, J. (2025). Soil Organic Matter Content Prediction Using Multi-Input Convolutional Neural Network Based on Multi-Source Information Fusion. Agriculture, 15(12), 1313. https://doi.org/10.3390/agriculture15121313

Han J, Wu M, Qi Y, Li X, Chen X, Wang J, Zhu J and Li Q. (2025). A Soil Organic Carbon Mapping Method Based On Transfer Learning Without The Use Of Exogenous Data. Front. Environ. Sci. 13:1580085. doi: 10.3389/fenvs.2025.1580085

Kamilaris, A. &.-B. (2018). Deep Learning in Agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90. https://doi.org/10.1016/j.compag.2018.02.016.

Khalaf, H. S., Mustafa, Y. T., & Fayyadh, M. A. (2023). Digital Mapping of Soil Organic Matter in Northern Iraq: Machine Learning Approach. Applied Sciences, 13(19), 10666. https://doi.org/10.3390/app131910666

Klusowski, J. M. (2018). Complete Analysis of a Random Forest Model. arXiv, 13, 1063–1095.

Kumala, A., Supriatna, S., & Damayanti, A. (2018). Model assessment of soil organic matter content by remote sensing in Bayah, Indonesia. AIP Conf. Proceeding. 2018, Issue 1, 020192. https://doi.org/10.1063/1.5064189

Kumar, A., Moharana, P. C., Jena, R. K., Malyan, S. K., Fagodiya, R. K., Shabnam, A. A., Vinodakumar, S. N., Jigyasu, D. K., Gull, A., Kumari, K. M. V., & Subramaniam, G. D. (2026). Prediction of soil available nitrogen using machine learning and digital mapping techniques in Northeast India. Enviromental Challenges, 22, 101375. https://doi.org/10.1016/j.envc.2025.101375.

Lamsani, M., Pangestika, R. A., Cahyanti, M., & Swedia, E. R. (2023). The Munsell Soil Colour Identification System Using the TCS3200 Colour Sensor and the YL-69 Humidity Sensor. Sebatik, 27(1), 379 389. https://doi.org/10.46984/sebatik.v27i1.2249. [In Indonesian language]

Lavelle, P., Decaëns, T., Aubert, M., Barot, S., Blouin, M., Bureau, F., Margerie, P., Mora, P., & Rossi, J.-P. (2006). Soil Invertebrates and Ecosystem Services. European Journal of Soil Biology, 42(Suppl. 1), S3–S15. https://doi.org/10.1016/j.ejsobi.2006.10.002

Lehmann, J. & Kleber, M. (2021). The Contentious Nature of Soil Organic Matter. Nature, 528(7580), 60–68. https://doi.org/10.1038/nature16069.

Li, Y., Yao, G., Li, S., & Dong, X. (2025). Predicting and Mapping of Soil Organic Matter with Machine Learning in the Black Soil Region of the Southern Northeast Plain of China. Agronomy, 15(3), 533. https://doi.org/10.3390/agronomy15030533

Lohit, V. S., & Mujahid, M. M. (2022). Big Data Analytics In Developing Smart And Sustainable Solutions For The Agricultural Industry. Technoarete Transactions on Advances in Data Science and Analytics, 1(2), 1-7. https://doi.org/10.36647/ttadsa/01.02.a001

Miao, T., Ji, W., Li, B., Zhu, X., Yin, J., Yang, J., Huang, Y., Cao, Y., Yao, D., & Kong, X. (2024). Advanced Soil Organic Matter Prediction with a Regional Soil NIR Spectral Library Using Long Short-Term Memory–Convolutional Neural Networks: A Case Study. Remote Sensing, 16(7), 1256. https://doi.org/10.3390/rs16071256

Minasny, B., Akoeb, E. N., Sabrina, T., Wadoux, A. M. J.-C., & McBratney, A. B. (2020). History and Interpretation Of Early Soil And Organic Matter Investigations in Deli, Sumatra, Indonesia. Catena, 195, 104909. https://doi.org/10.1016/j.catena.2020.104909

Mundada, S., Jain, P., Kumar, N. (2024). Prediction of Soil Organic Carbon using Machine Learning Techniques and Geospatial Data for Sustainable Agriculture. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 49(3), 789-804. https://doi.org/10.1177/18758967251353377

Mansur, N., & Abbod, M. A. (2026). Machine Learning-Based Estimation Of Soil Organic Matter Using RGB Values. Dysona: Applied Science, 73-81.

Nodi, S. S., Paul, M., Robinson, N., Wang, L., & Rehman, S. U. (2023). Determination of Munsell Soil Colour Using Smartphones. Sensors, 23(6), 3181. https://doi.org/10.3390/s23063181

Padarian, J., Minasny, B., & McBratney, A. B. (2018). Using Deep Learning For Digital Soil Mapping. Soil. 1-17 https://doi.org/10.5194/soil-2018-28

Quinton, J. N., & Fiener, P. (2023). Soil Erosion On Arable Land: An Unresolved Global Environmental Threat. Progress in Physical Geography, 48(1), 136–161. https://doi.org/10.1177/03091333231216595

Sinulingga, M. A. P., & Aryanti, E. (2024). Utilization of Rice Husk Biochar and Liquid Organic Fertilizer from Fish Waste for Improving the Physical Properties of Ultisol. Jurnal Agrin, 28(2), 129-135. https://doi.org/10.20884/1.agrin.2024.28.2.837

Shahabi, H., Rahimzad, M., Tavakkoli Piralilou, S., Ghorbanzadeh, O., Homayouni, S., Blaschke, T., Lim, S., & Ghamisi, P. (2021). Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery. Remote Sensing, 13(22), 4698. https://doi.org/10.3390/rs13224698

Ćirić, V., Prekop, N., Šeremešić, S., Vojnov, B., Pejić, B., Radovanović, D., Marinković, D. (2023): The Implication of Cation Exchange Capacity (CEC) Assessment For Soil Quality Management And Improvement. Agriculture and Forestry, 69 (4), 113-133. DOI: 10.17707/AgricultForest.69.4.08

Rodríguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., & Rigol-Sánchez, J. P. (2012). An Assessment of The Effectiveness Of A Random Forest Classifier For Land-Cover Classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93–104. https://doi.org/10.1016/j.isprsjprs.2011.11.002

Wibowo, E. C., & Cahyono, A. D. (2025). Comparative Analysis Of Linier Regresion And Neural Network Algorithms For Stock Price Prediction. Jurnal sistem informasi, 14(4), 1879-1896.

Liaw A., & Wiener, M. (2002). The R Journal: Classification and regression by Random Forest. R Journal, 2(3), 18–22.

Wolfert, S. G. (2017). Big Data In Smart Farming – A Review. Agricultural Systems, 153, 69–80. https://doi.org/10.1016/j.agsy.2017.01.023.

Zhang, W.-C., Wan, H.-S., Zhou, M.-H., Wu, W., & Liu, H.-B. (2022). Soil Total And Organic Carbon Mapping And Uncertainty Analysis Using Machine Learning Techniques. Ecological Indicators, 143, 109420. https://doi.org/10.1016/j.ecolind.2022.109420




DOI: https://doi.org/10.36987/jpbn.v12i1.9077

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Muhammad Afifi Andriansyah, Lusia Rakhmawati, I Gusti Putu Asto Buditjahjanto

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Jurnal Pembelajaran dan Biologi Nukleus (JPBN) by LPPM Universitas Labuhanbatu is under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY - SA 4.0). Official contact: Rivo +6281362238917