2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 16 , Issue 2 , PP: 22-31, 2024 | Cite this article as | XML | Html | PDF
Bryan Barragán-Pazmiño 1 , Angel Ordóñez Echeverría 2 , Magdy Echeverría Guadalupe 3 , Theofilos Toulkeridis 4
Doi: https://doi.org/10.54216/FPA.160202
Machine learning approaches are utilized to identify patterns in behavior and generate predictions across various applications. The objective of this work is to create a highly efficient model for accurately measuring and analyzing the levels of soil organic carbon (SOC) in the Chambo river sub-basin, which is situated in the province of Chimborazo. The model evaluation entails the application of diverse machine learning algorithms and approaches to determine the most efficient regression model. Regression models are improved using techniques such as Artificial Neural Networks, Support Vector Machines, and Decision Trees. The Resilient Backpropagation method yields the most precise model, as it accounts for a greater proportion of the variability in SOC content for the test data. This aligns with the findings from the training data, demonstrating a relatively low mean absolute error and a processing time that is approximately 400 times faster than that of the Multilayer Perceptron algorithm. The evaluation of estimating models is an objective procedure that considers not only the findings and precise metrics derived from the model's design, but also other relevant elements. The effectiveness of the Random Forest approach, specifically the quantile regression forests technique, has been established for estimating SOC contents in the Chambo river sub-basin data.
Organic carbon , soil , machine learning , chemical and physical properties.
[1] Martinez, M. A. Q., Rugel, D. T. L., Alcivar, C. J. E., & Vazquez, M. Y. L. (2021). A framework for selecting classification models in the intruder detection system using TOPSIS. In Human Interaction, Emerging Technologies and Future Applications III: Proceedings of the 3rd International Conference on Human Interaction and Emerging Technologies: Future Applications (IHIET 2020), August 27-29, 2020, Paris, France (pp. 173-179). Springer International Publishing..
[2] Wadoux, A. M. C., Minasny, B., & McBratney, A. B. (2020). Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Science Reviews, 210, 103359..
[3] Huera-Lucero, T., Labrador-Moreno, J., Blanco-Salas, J., & Ruiz-Téllez, T. (2020). A framework to incorporate biological soil quality indicators into assessing the sustainability of territories in the Ecuadorian Amazon. Sustainability, 12(7), 3007.
[4] Correa, A., Ochoa‐Tocachi, B. F., Birkel, C., Ochoa‐Sánchez, A., Zogheib, C., Tovar, C., & Buytaert, W. (2020). A concerted research effort to advance the hydrological understanding of tropical páramos. Hydrological Processes, 34(24), 4609-4627.
[5] Eze S, Magilton M, Magnone D, Varga S, Gould I, Mercer TG, Goddard MR. Meta-analysis of global soil data identifies robust indicators for short-term changes in soil organic carbon stock following land use change. Sci Total Environ. 2023;860:160484.
[6] Zhang X, Wang J, Feng X, Yang H, Li Y, Yakov K, Li FM. Effects of tillage on soil organic carbon and crop yield under straw return. Agric Ecosyst Environ. 2023;354:108543.
[7] Somenahally AC, McLawrence J, Chaganti VN, Ganjegunte GK, Obayomi O, Brady JA. Response of soil microbial communities, inorganic and organic soil carbon pools in arid saline soils to alternative land use practices. Ecol Indic. 2023;150:110227.
[8] Babu S, Singh R, Avasthe R, Kumar S, Rathore SS, Singh VK, Petrosillo I. Soil carbon dynamics under organic farming: Impact of tillage and cropping diversity. Ecol Indic. 2023;147:109940.
[9] Zheng F, Liu X, Ding W, Song X, Li S, Wu X. Positive effects of crop rotation on soil aggregation and associated organic carbon are mainly controlled by climate and initial soil carbon content: a meta-analysis. Agric Ecosyst Environ. 2023;355:108600.
[10] Yang R, Yang S, Chen LL, Yang Z, Xu L, Zhang X, Zamanian K. Effect of vegetation restoration on soil erosion control and soil carbon and nitrogen dynamics: a meta-analysis. Soil Tillage Res. 2023;230:105705.
[11] Echeverría-Puertas, J., Echeverría, M., Cargua, F., & Toulkeridis, T. (2023). Spatial dynamics of the shore coverage within the zone of influence of the Chambo river, Central Ecuador. Land, 12(1), 180.
[12] Nakamura T, Touch N. Changes in Soil Physical Properties Owing to Soil Reduction Treated with Electrokinetic Treatment. Environmental and Rural Development. 2023;132.
[13] Carrión-Mero, P., Duenas-Tovar, J., Jaya-Montalvo, M., Berrezueta, E., & Jiménez-Orellana, N. (2022). Geodiversity assessment to regional scale: Ecuador as a case study. Environmental Science & Policy, 136, 167-186..
[14] Wang S, Li R, Wu Y, Wang W. Estimation of surface soil moisture by combining a structural equation model and an artificial neural network (SEM-ANN). Science of The Total Environment. 2023;876:162558.
[15] Kumar A, Sinha S, Saurav S, Chauhan VB. Prediction of unconfined compressive strength of cement–fly ash stabilized soil using support vector machines. Asian Journal of Civil Engineering. 2024;25(2):1149-1161.
[16] Kebonye NM, Agyeman PC, Biney JK. Optimized modelling of countrywide soil organic carbon levels via an interpretable decision tree. Smart Agricultural Technology. 2023;3:100106.
[17] Bento NL, Ferraz GAE, Barata RAP, Soares DV, Teodoro SA, Estima PHDO. Classifiers based on artificial intelligence in the prediction of recently planted coffee cultivars using a Remotely Piloted Aircraft System. Anais da Academia Brasileira de Ciências. 2023;95(3):e20210534.
[18] Pacini L, Yunta F, Jones A, Montanarella L, Barrè P, Saia S, Schillaci C. Fine earth soil bulk density at 0.2 m depth from Land Use and Coverage Area Frame Survey (LUCAS) soil 2018. European Journal of Soil Science. 2023;74(4):e13391.
[19] de Baar JH, Garcia-Marti I, van der Schrier G. Spatial regression of multi-fidelity meteorological observations using a proxy-based measurement error model. Advances in Science and Research. 2023;20:49-53.
[20] Salati S, Matinfar M, Jafari H. A numerical approach for solving Bagely-Torvik and fractional oscillation equations. Adv Model Appl. 2023;8:241-252.
[21] Cornelio, O. M., Ching, I. S., & Gonzales, J. G. (2019). Algorithm to Determine and Eliminate Neutral Nodes in Neutrosophic Cognitive Map. Neutrosophic Computing and Machine Learning, 8, 1-8.
