EUVIMEDEUVIMED entdecken
Crossref

Machine Learning for Soil Classification: Challenges and Opportunities

Siti Nur Fatin Liyana Mohd Azmin, Hamijah Mohd Rahman, Nur Nadhirah Mohd Harith Lim, Nureize Arbaiy

Journal of Applied Science, Technology and Computing · 2024

DOI: 10.30880/jastec.2024.01.01.004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Science, Technology and Computing, 2024. Verfasst von Siti Nur Fatin Liyana Mohd Azmin und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In agriculture and environmental science, soil classificationis essential for making well-informed decisions about crop selection, land management, and environmental protection. However conventional methods of classifying soil require a lot of work and time, and they mostly rely on human expertise. This work investigates the possibilities of machine learning (ML) models to automate soil classification utilizinglarge datasets of soil samples toovercome the shortcomings of existing techniques. In this paper, many machineslearning techniques, including support vector machines (SVM), decision trees (DT), random forests (RF), and neural networks (NN), are examinedfor the classification of soil. There are certain models that work better than others, though, and this is based on the qualitiesof the soil samples. In addition to that, experiments using Random Forest, Naïve Bayes, and k-Nearest Neighbor(k-NN) were also undertaken. Classification strategies are being chosento create a classified model using data mining. The algorithm with the highest accuracy is Random Forest (97.23%), followed by Naïve Bayes (96.82%), and k-Nearest Neighbor(k-NN), which has the lowest accuracy (92.92%). The paper highlights the challenges of applying machine learning to soil classification, such as consistency and human specialist availability, toeffectively categorizesoil samples. The results indicate that, despitethese challenges, ML models present a potential substitute for labor-intensive conventional methods in the classification of soil.

Zitieren

APA

Azmin, S. N. F. L. M., Rahman, H. M., Lim, N. N. M. H., & Arbaiy, N. (2024). Machine Learning for Soil Classification: Challenges and Opportunities. Journal of Applied Science, Technology and Computing. https://doi.org/10.30880/jastec.2024.01.01.004

Vancouver

Azmin SNFLM, Rahman HM, Lim NNMH, Arbaiy N. Machine Learning for Soil Classification: Challenges and Opportunities. Journal of Applied Science, Technology and Computing. 2024. doi:10.30880/jastec.2024.01.01.004

BibTeX
@article{Azmin2024,
  author = {Azmin, Siti Nur Fatin Liyana Mohd and Rahman, Hamijah Mohd and Lim, Nur Nadhirah Mohd Harith and Arbaiy, Nureize},
  title = {Machine Learning for Soil Classification: Challenges and Opportunities},
  journal = {Journal of Applied Science, Technology and Computing},
  year = {2024},
  doi = {10.30880/jastec.2024.01.01.004}
}
Kostenlos starten →