Publication:
Estimating reference evapotranspiration and soil moisture for crop irrigation needs using machine learning and remote sensing

Thumbnail Image
Files

Files

Rodríguez, Diego-2025.pdf (3.94 MB)
 Autorización.pdf (136.94 KB)
View Statistics
Reference Managers
Mendeley
Indexers
Google Scholar CORE
QR Code
QR Code
Authors

Authors

Rodríguez Torres, Diego Fernando
Abstract (Spanish)
Este estudio presenta un módulo de predicción de la humedad del suelo y la evapotranspiración de referencia utilizando datos satelitales, orientado a optimizar los requerimientos hídricos de los cultivos. Se implementaron y evaluaron dos modelos de aprendizaje automático—LightGBM y Random Forest—en tres escenarios distintos, utilizando productos satelitales como SMAP y ERA5-Land y empleando un análisis de series de tiempo. El desempeño se evaluó mediante el error absoluto medio (MAE) y la raíz del error cuadrático medio (RMSE), destacando LightGBM por su mejor precisión. El módulo desarrollado fue integrado en la plataforma ThingsBoard como parte de un sistema de gestión agrícola, demostrando la viabilidad de los datos satelitales como alternativa para regiones con infraestructura IoT limitada.
Abstract (English)
This study presents a prediction module for soil moisture and reference evapotranspiration based on satellite remote sensing data, aimed at optimizing agricultural water requirements. Two machine learning models—LightGBM and Random Forest—were implemented and evaluated across three different scenarios, using satellite products such as SMAP and ERA5-Land, through a time-series analysis. Performance was assessed using mean absolute error (MAE) and root mean square error (RMSE), with LightGBM demonstrating the highest accuracy. The developed module was integrated into the ThingsBoard platform as part of an agricultural management system, demonstrating the feasibility of using satellite remote sensing in regions with limited or no IoT infrastructure.
Director

Advisors/Directors

Garzon Alfonso, Wilmer Edicson
Cadavid Rengifo, Héctor Fabio
Extent
65 páginas
URI: https://repositorio.escuelaing.edu.co/handle/001/3604
Collections

Collections

FD - Trabajos de Grado Maestría en Informática
References

J. Bruinsma, “The resource outlook to 2050: by how much do land, water and crop yields need to increase by 2050? expert meeting on how to feed the world in 2050,” http://www. fao. org/wsfs/forum2050/wsfsbackground-documents/wsfs-expert-papers/en/, 2009.

A. Glória, J. Cardoso, and P. Sebastião, “Sustainable irrigation system for farming supported by machine learning and real-time sensor data,” Sensors, vol. 21, no. 9, p. 3079, 2021.

ThingsBoard, “Thingsboard- open-source iot platform.” https://thingsboard.io, 2024. Accessed: 2024.

C. Brouwer, A. Goffeau, and M. Heibloem, “Irrigation water management: Training manual no. 1- introduction to irrigation.”

N. EarthData, “What is remote sensing? | earthdata.

J. Leites, V. Cerqueira, and C. Soares, “Lag selection for univariate time series forecasting using deep learning: An empirical study,” arXiv preprint arXiv:2405.11237, 2024

R. K. Sidhu, R. Kumar, and P. S. Rana, “Machine learning based crop water demand forecasting using minimum climatological data,” Multimedia Tools and Applications, vol. 79, pp. 13109–13124, 2020.

A. Mokhtar, N. Al-Ansari, W. El-Ssawy, R. Graf, P. Aghelpour, H. He, S. M. Hafez, and M. Abuarab, “Prediction of irrigation water requirements for green beans-based machine learning algorithm models in arid region,” Water resources management, vol. 37, no. 4, pp. 1557–1580, 2023.

S. Sadri, J. S. Famiglietti, M. Pan, H. E. Beck, A. Berg, and E. F. Wood, “Farmcan: a physical, statistical, and machine learning model to forecast crop water deficit for farms,” Hydrology and Earth System Sciences, vol. 26, no. 20, pp. 5373–5390, 2022.

A. Elbeltagi, A. Srivastava, A. H. Al-Saeedi, A. Raza, I. Abd-Elaty, and M. El-Rawy, “Forecasting long-series daily reference evapotranspiration based on best subset regression and machine learning in egypt,” Water, vol. 15, no. 6, p. 1149, 2023.

Y. Cai, W. Zheng, X. Zhang, L. Zhangzhong, and X. Xue, “Research on soil moisture prediction model based on deep learning,” PloS one, vol. 14, no. 4, p. e0214508, 2019.

F.-R. Jiménez-López, I.-A. Ruge-Ruge, and A.-F. Jiménez-López, “Deep learning techniques applied to predict the irrigation prescription for potato crops in boyacá,” in 2021 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), pp. 1–8, IEEE, 2021.

G. A. Alzate Acuña, “Diseño de un sistema de riego para granja inteligente basado en internet de las cosas,” 2020.

Google and C. C. D. Store, “Era5-land daily aggregated- ecmwf climate reanalysis.” https://developers.google.com/earth-engine/datasets/ catalog/ECMWF_ERA5_LAND_DAILY_AGGR.

J. Amat Rodrigo and J. Escobar Ortiz, “skforecast.” https://skforecast.org/, 5 2024.

e. a. Saha, S., “Ncep climate forecast system version 2 (cfsv2) 6-hourly products. research data archive at the national center for atmospheric research, computational and information systems laboratory.,” 2011.

“Cropwat. land and water. food and agriculture organization of the united nations.”s

“Tolima- al día con el clima.”