Innovative Digital Mapping of Soil Organic Matter Content in Oil Palm Using Image Analysis

Ida Ratna Nila; Rahmawati Rahmawati; Muhammad Ari Fahril; Sabrian Tri Anda; Rachmad Almi Putra; Fajriani Fajriani; Afrahun Naziah

doi:10.18343/jipi.31.2.385

Authors

Ida Ratna Nila Geophysics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia
Rahmawati Rahmawati Physics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia
Muhammad Ari Fahril Geophysics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia
Sabrian Tri Anda Geophysics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia
Rachmad Almi Putra Geophysics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia
Fajriani Fajriani Geophysics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia
Afrahun Naziah Geophysics Study Program, Faculty of Science and Technology, Samudra University, Aceh 24416, Indonesia

DOI:

https://doi.org/10.18343/jipi.31.2.385

Keywords:

soil organic matter, image processing, oil palm, mapping, precision agriculture

Abstract

The goal of this study is to use image processing technology to map the organic matter content of soil in oil palm plantations. The data set comprises photos of oil palms and bare land, as well as field measurements of pH, humidity, temperature, total dissolved solids, and electrical conductivity. Correlation analysis revealed a strong link between picture spectral components (particularly in the blue channel, r = 0.3640) and soil organic matter content. The distribution of organic matter content ranges from 4.5 to 5.5%, with an average of around 5%. The image processing-based predictive model successfully mapped the spatial variation of organic matter content with high accuracy. The mapping results demonstrate spatial variability, which can be exploited to support precision agriculture in oil palm areas.

Keywords: soil organic matter, image processing, oil palm, mapping, precision agriculture

Downloads

Download data is not yet available.

References

Ajeng AA. 2020. The effects of biofertilizers growth, soil fertility, and oil palm productivity. Processes, 8(12): 1681. https://doi.org/10.3390/pr8121681

Akhtar MN, Nazir U, Majeed H, Ahmad S, Ahmad M, Imran M. 2023. Leveraging advanced remote sensing and artificial intelligence technologies for sustainable management of palm oil plantations. A review. Agriculture. 13(2): 504. https://doi.org/10.3390/agriculture13020504

Chai T, Draxler RR. 2014. Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geoscientific Model Development. 7: 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014

Golicz K.2024. A comprehensive survey of soil organic carbon under oil palm: Temporal trends, drivers, and implications for sustainability. Environmental Monitoring and Assessment. 197(1): 86. https://doi.org/10.1007/s10661-024-13540-y

Haralick RM, Shanmugam K, Dinstein I. 1973. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics. SMC–3: 610–621. https://doi.org/10.1109/TSMC.1973.4309314

Heil J. 2022. Fine-scale mapping of soil organic matter in agricultural fields using image-based methods. Remote Sensing. 14(14): 3349. https://doi.org/10.3390/rs14143349

Kačergius A. 2025. Influences of organic carbon and microbiota on soil functions. International Journal of Soil Science. 14(5): 500. https://doi.org/10.3390/biology14050500

Luo Cl. 2022. Regional mapping of soil organic matter content using multitemporal synthetic Landsat 8 images in Google Earth Engine. CATENA. 209: 105842.

Nowkandeh SM. 2018. Estimating soil organic matter content from Hyperion reflectance images using PLSR, PCR, MinR and SWR models in semi-arid regions of Iran. Environmental Development. 25: 23–32.

Pearson K. 1901. On lines and planes of closest fit to systems of points in space. Philosophical Magazine. 2(11): 559–572. https://doi.org/10.1080/14786440109462720

Rahman N. 2021. The effects of management practices on soil organic carbon (SOC) stocks of oil palm plantations in Indonesia. Journal of Environmental Management. 278(Pt 2): 111446.

Reyes RAG. 2023. Relationship of soil organic matter content with spectral indices (NDVI, SAVI): A case study. Journal of Soil Spectroscopy.

Reyes RAG. 2023. Blue and green spectral channels as predictors of soil organic matter content in plantation environments. Journal of Soil Spectroscopy.

Romano E. 2023. Using image texture analysis to evaluate soil–compost mixing uniformity. Agriculture. 13(6): 1113. https://doi.org/10.3390/agriculture13061113

Rouse JW Jr, Haas RH, Schell JA, Deering DW. 1973. Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation. Texas A&M University (US): Remote Sensing Center.

Segura C. 2024. Comparison of direct and indirect soil organic carbon estimation methods. Journal of Environmental Management. 365: 121573. https://doi.org/10.1016/j.jenvman.2024.121573

Taneja P.. 2022. Predicting soil organic matter and soil moisture content from digital images and machine learning. Canadian Journal of Soil Science. 102(3): 1–15. https://doi.org/10.1139/cjss-2021-0133

Yu, W.2024. Significant improvement in soil organic carbon estimation using hybrid ML models and combined predictors. Remote Sensing, 16(4): 688. https://doi.org/10.3390/rs16040688

Zhang Y. 2019. Prediction of soil organic carbon based on Landsat 8 imagery: Relationships between NDVI and SOC. Remote Sensing. 11(14): 1683. https://doi.org/10.3390/rs11141683