EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Sugarcane Height Estimation Model Based on Multi-Source Satellite Data Fusion Using Machine Learning

Thabed Tholib Baladraf, Marimin Marimin, Irman Hermadi, Andes Ismayana

Engineering, Technology & Applied Science Research · 04.04.2026 · 16 (2) · 34630-34636

DOI: 10.48084/etasr.16345 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 04.04.2026. Verfasst von Thabed Tholib Baladraf und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The combination of satellite and Machine Learning (ML) approaches is emerging as a new paradigm in crop height estimation, facilitating informed decision-making. This study aims to identify key factors influencing sugarcane height prediction and compare the performance of single satellite data with data fusion. The proposed height estimation model was designed with the help of satellite data from Sentinel-2 and Landsat 9. A data fusion technique was used to extract vegetation, morphological, and meteorological indicators from three land plots in 2023 and 2024. The collected data were preprocessed using the Interquartile Range (IQR). Forward chaining was utilized to split data into training and testing subsets (40:20, 50:20, 60:20, 70:20, and 80:20). Feature importance analysis was performed to identify features contributing to sugarcane height prediction. The selected features were used as inputs for three ML models: Random Forest (RF), Extreme Gradient Boosting (XGB), and Support Vector Regression (SVR). The results of sugarcane height estimation indicate that the use of multi-source data fusion (vegetation indicators, morphology, and meteorology) with XGB achieved the best and most robust performance, with a coefficient of determination (R2) of 0.997, a Root Mean Square Error (RMSE) of 6.254 cm, and a Mean Absolute Percentage Error (MAPE) of 3.097%. The findings demonstrate a strong potential of real-time remote sensing-based height estimation for sugarcane, supporting precise monitoring and data-driven decision-making.

Zitieren

APA

Baladraf, T. T., Marimin, M., Hermadi, I., & Ismayana, A. (2026). A Sugarcane Height Estimation Model Based on Multi-Source Satellite Data Fusion Using Machine Learning. Engineering, Technology & Applied Science Research, 16(2), 34630-34636. https://doi.org/10.48084/etasr.16345

Vancouver

Baladraf TT, Marimin M, Hermadi I, Ismayana A. A Sugarcane Height Estimation Model Based on Multi-Source Satellite Data Fusion Using Machine Learning. Engineering, Technology & Applied Science Research. 2026;16(2):34630-34636. doi:10.48084/etasr.16345

BibTeX
@article{Baladraf2026,
  author = {Baladraf, Thabed Tholib and Marimin, Marimin and Hermadi, Irman and Ismayana, Andes},
  title = {A Sugarcane Height Estimation Model Based on Multi-Source Satellite Data Fusion Using Machine Learning},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {34630--34636},
  doi = {10.48084/etasr.16345}
}
Kostenlos starten →