DETECCIÓN AUTOMÁTICA DE CUERPOS DE AGUA DEL BAJÍO UTILIZANDO PARÁMETROS MORFOMÉTRICOS OBTENIDOS DE IMÁGENES SATELITALES Y PROCESADOS CON REDES NEURONALES (AUTOMATIC DETECTION OF WATER BODIES OF EL BAJÍO USING MORPHOMETRIC PARAMETERS OBTAINED FROM SATELLITE IMAGES AND PROCESSED WITH NEURONAL NETWORKS)

José Daniel Fernández Peña, Claudia A. Gallegos Sánchez, José Alfredo Padilla Medina, Alejandro Israel Barranco Gutiérrez, José Antonio Vázquez López, Pedro J. Correa Caicedo

Resumen


Resumen
La conservación de las masas de agua superficiales es un tema crucial para el desarrollo socioeconómico de los asentamientos humanos. Por tanto, el seguimiento constante de la distribución territorial del agua es cada vez más una prioridad. Las imágenes procesadas fueron obtenidas de la misión satelital SENTINEL 2 que provee su información en base a 13 bandas multiespectrales, de las cuales se usaron las bandas B3 (verde) y B8 (infrarrojo cercano) en el cálculo del parámetro de identificación de agua NDWI. En este trabajo se propone un sistema de identificación de masas de agua mediante redes neuronales a partir de una base de datos de clasificadores que permite a la red discriminar píxel a píxel si existe o no presencia de agua. La red se implementa en dos ambientes diferentes: Matlab y Google Colaboratory, dos plataformas que logran obtener buenos resultados en el diseño de modelos de redes neuronales. En las pruebas realizadas queda demostrada la capacidad predictiva del sistema implementado, logrando un rendimiento por encima del 90% de precisión, cumpliendo con los objetivos de identificación.
Palabras Clave: cuerpos de agua, visión artificial, Google Colaboratory, Matlab, red neuronal.

Abstract
The conservation of surface water bodies is a crucial issue for the socioeconomic development of human settlements. Therefore, the constant monitoring of territorial water distribution is increasingly a priority. The processed images were obtained from the SENTINEL 2 satellite mission that provides its information based on 13 multispectral bands, of which bands B3 (green) and B8 (near infrared) were used in the calculation of the water identification parameter NDWI. In this work, a system for identifying bodies of water using neural networks is proposed from a database of classifiers that allows the network to discriminate pixel by pixel whether it is in the presence of water or not. The network is implemented in two different environments: Matlab and Google Colaboratory, two platforms that achieve good results in the design of neural network models. In the tests carried out, the predictive capacity of the implemented system is demonstrated, achieving a performance above 90% accuracy, meeting the identification objectives.
Keywords: water bodies, artificial vision, Google Colaboratory, Matlab, neural network.

Texto completo:

90-104 PDF

Referencias


Kafy, Abdulla - Al. (2018). Importance of Surface Water Bodies for Sustainable Cities: A Case Study of Rajshahi City Corporation.

Zhang, Fangfang & Li, Junsheng & Shen, Qian & Ye, Huping & Wang, Shenglei & lu, Zoe. (2018). A simple automated dynamic threshold extraction method for the classification of large water bodies from landsat-8 OLI water index images. International Journal of Remote Sensing. 39. 3429-3451. https://doi.org/10.1080/01431161.2018.1444292.

Ko, Byoungchul & Kim, Hyeong & Nam, Jae. (2015). Classification of Potential Water Bodies Using Landsat 8 OLI and a Combination of Two Boosted Random Forest Classifiers. Sensors. 15. 13763-13777. https://doi.org/10.3390/s150613763.

Litjens, G. & Kooi, T. & Bejnordi, B.E. & Setio, A. & Ciompi, F. & Ghafoorian, M. & Laak, J.V. & Ginneken, B. & Sánchez, C. (2017). A survey on deep learning in medical image analysis. Medical image analysis, 42, 60-88.

Xie, Qiaoyun & Dash, Jadu & Huete, Alfredo & Jiang, Aihui & Yin, Gaofei & Ding, Yanling & Peng, Dailiang & Hall, Christopher & Brown, Luke & Shi, Yue & Ye, Huichun & Dong, Yingying & Huang, Wenjiang. (2019). Retrieval of crop biophysical parameters from Sentinel-2 remote sensing imagery. International Journal of Applied Earth Observation and Geoinformation. 80. 187-195. https://doi.org/10.1016/j.jag.2019.04.019.

Utton, Albert. (2019). Water in a Developing World: The Management of a Critical Resource. Routledge.

Chawla, Ila & Karthikeyan, L. & Mishra, Ashok. (2020). A Review of Remote Sensing Applications for Water Security: Quantity, Quality, and Extremes. Journal of Hydrology. 585. 124826. https://doi.org/10.1016/j.jhydrol.2020.124826.

Yuan, Qiangqiang & Shen, Huanfeng & Li, Tongwen & Li, Zhiwei & Li, Shuwen & Jiang, Yun & Xu, Hongzhang & Weiwei, Tan & Yang, Qianqian & Wang, Jiwen & Gao, Jianhao & Zhang, Liangpei. (2020). Deep learning in environmental remote sensing: Achievements and challenges. Remote Sensing of Environment. 241. 111716. https://doi.org/10.1016/j.rse.2020.111716.

Cheng, Gong & Xie, Xingxing & Han, Junwei & Li, Kaiming & Xia, Gui-Song. (2020). Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 13. 3735-3756. https://doi.org/10.1109/JSTARS.2020.3005403.

Hong, Danfeng & Gao, Lianru & Yokoya, Naoto & Yao, Jing & Chanussot, Jocelyn & Du, Qian & Zhang, Bing. (2020). More Diverse Means Better: Multimodal Deep Learning Meets Remote-Sensing Imagery Classification. IEEE Transactions on Geoscience and Remote Sensing. PP. 1-15. https://doi.org/10.1109/TGRS.2020.3016820.

Nima Pahlevan & Sandeep K. Chittimalli & Sundarabalan V. Balasubramanian & Vincenzo Vellucci. (2019). Sentinel-2/Landsat-8 product consistency and implications for monitoring aquatic systems. Remote Sensing of Environment. 20. 19-29. https://doi.org/10.1016/j.rse.2018.10.027.

Randles, Bernadette & Pasquetto, Irene & Golshan, Milena & Borgman, Christine. (2017). Using the Jupyter Notebook as a Tool for Open Science: An Empirical Study. 1-2. https://doi.org/10.1109/JCDL.2017.7991618.

Bisong E. (2019) Google Colaboratory. In: Building Machine Learning and Deep Learning Models on Google Cloud Platform. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-4470-8_7

Pessoa, Tiago & Medeiros, Raul & Nepomuceno, Thiago & Bian, Gui-Bin & Albuquerque, V.H.C. & Filho, Pedro Pedrosa. (2018). Performance Analysis of Google Colaboratory as a Tool for Accelerating Deep Learning Applications. IEEE Access. PP. 1-1. https://doi.org/10.1109/ACCESS.2018.2874767.

MATLAB. (2019). version 9.6.0.1062519 (R2019a). The MathWorks Inc. Natick, Massachusetts

Manaswi, Navin Kumar & John, Suresh. (2018). Deep learning with applications using python. Springer.

Maragoudakis, Manolis & Kontos, Konstantinos. (2018). Machine learning for water bodies identification from satellite images. International Journal of Data Mining, Modelling and Management. 10. 209. 10.1504/IJDMMM.2018.10015048.

Isikdogan, Furkan & Bovik, Alan & Passalacqua, Paola. (2017). Surface Water Mapping by Deep Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. PP. 1-10. 10.1109/JSTARS.2017.2735443.

Chen, Yang & Fan, Rongshuang & Yang, Xiucheng & Wang, Jingxue & Latif, Aamir. (2018). Extraction of Urban Water Bodies from High-Resolution Remote-Sensing Imagery Using Deep Learning. Water. 10. 585. 10.3390/w10050585.






URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es

Barra de separación

Licencia Creative Commons    Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada.    

TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA

Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México

Tel. 461 61 17575 Ext 5450 y 5146

pistaseducativas@itcelaya.edu.mx

http://pistaseducativas.celaya.tecnm.mx/index.php/pistas