Detección de cuerpos de agua en imágenes hiperespectrales usando similitud diferencial espectral y redes neuronales
DOI:
https://doi.org/10.18041/1900-3803/entramado.2.12876Palabras clave:
Cuerpos de agua, Imágenes Hiperespectrales, Similitud Diferencial Espectral, Redes Neuronales, Teledetección, Clasificación Espectral, Eficiencia ComputacionalResumen
Introducción (I): La detección eficiente de materiales en imágenes hiperespectrales es un reto debido a su alta dimensionalidad. Este estudio propone y evalúa dos métodos computacionales —similaridad espectral diferencial (SDS) y redes neuronales secuenciales— para detectar cuerpos de agua en imágenes con 380 bandas de reflectancia. Metodología (M): Se adaptó la metodología CRISP-DM en cuatro fases: comprensión del negocio y los datos, preparación de datos, modelado y evaluación, e implementación. Se utilizaron 200 firmas espectrales para entrenar los modelos, los cuales fueron aplicados a una imagen hiperespectral del barrio Manga, en Cartagena (Colombia). Resultados (R): Ambos métodos identificaron píxeles de cuerpos de agua con porcentajes entre 13,734% y 16,083%, siendo SDS el que cometió menos errores de detección. Además, SDS fue en promedio 16,1 veces más rápido en procesamiento. Conclusión (C): Por su precisión y eficiencia, los métodos evaluados, especialmente SDS, son alternativas viables frente a enfoques más complejos y se consideran adecuados para su integración en sistemas de monitoreo ambiental en tiempo real.
Descargas
Referencias
1. ABDULRAHEEM, Mukhtar Iderawumi; ZHANG, Wey; LI, Shixin; MOSHAYEDI, Ata Jahangir; FAROOQUE, Aitazaz A.; HU, Jiandong. Advancement of remote sensing for soil measurements and applications: A comprehensive review. In: Sustainability. 2023. vol. 15, no. 21. 15444. https://doi.org/10.3390/su152115444
2. ALAM, Mohammed. Introduction to Remote Sensing. Germany: Lap Lambert Academic Publishing, 2019. 120 p. ISBN: 613-9-85088-6.
3. ALI, Mansurat A.; LYU, Xueyan; ERSAN, Mahmut S.; XIAO, Feng. Critical Evaluation of Hyperspectral Imaging Technology for Detection and Quantification of Microplastics in Soil. In: Journal of Hazardous Materials. 2024. vol. 476. 135041. https://doi.org/10.1016/j.jhazmat.2024.135041
4. AWANGE, Joseph; KIEMA, John. Fundamentals of Remote Sensing. In: AWANGE, Joseph; KIEMA, John. Environmental Geoinformatics Extreme Hydro-Climatic and Food Security Challenges: Exploiting the Big Data. 2. ed. Switzerland: Springer Cham, 2019. 115–123 p. https://doi.org/10.1007/978-3-030-03017-9_7
5. CHANCHÍ-GOLONDRINO, Gabriel Elías; OSPINA-ALARCÓN, Manuel Alejandro; SABA, Manuel. Fourier Analysis Approach to Identify Water Bodies Through Hyperspectral Imagery. In: Revista Facultad de Ingeniería. 2023. vol. 33, no. 67. e17232. https://doi.org/10.19053/uptc.01211129.v33.n67.2024.17232
6. CHANG, Yang Lang; TAN, Tan Hsu; LEE, Wei Hong; CHANG, Lena; CHEN, Ying Nong; FAN, Kuo Chin; ALKHALEEFAH, Mohammad. Consolidated Convolutional Neural Network for Hyperspectral Image Classification. In: Remote Sensing. 2022. vol. 14, no. 7. 1571. https://doi.org/10.3390/rs14071571
7. CHEN, Qi; CAI, Dayu; XIA, Jisheng; ZENG, Min; YANG, Haiying; ZHANG, Ruisi; HE, Yang; ZHANG, Xiaoxiao; CHEN, Yi; XU, Xinhui; ZHAO, Zhifang. Remote Sensing Identification of Hydrothermal Alteration Minerals in the Duobuza Porphyry Copper Mining Area in Tibet Using WorldView-3 and GF-5 Data: The Impact of Spatial and Spectral Resolution. In: Ore Geology Reviews. 2025. vol. 180. 106573. https://doi.org/10.1016/j.oregeorev.2025.106573
8. DATTA, Debaleena; MALLICK, Pradeep Kumar; BHOI, Akash Kumar; IJAZ, Muhammad Fazal; SHAFI, Jana; CHOI, Jaeyoung. Hyperspectral Image Classification: Potentials, Challenges, and Future Directions. In: Computational Intelligence and Neuroscience. 2022. vol. 2022. p. 1–36. https://doi.org/10.1155/2022/3854635
9. FAKHRULLIN, Rawil; NIGAMATZYANOVA, Läysän; FAKHRULLINA, Gölnur. Dark-field/hyperspectral Microscopy for Detecting Nanoscale Particles in Environmental Nanotoxicology Research. In: Science of The Total Environment. 2021. vol. 772. 145478. https://doi.org/10.1016/j.scitotenv.2021.145478
10. FEI, Baowei. Hyperspectral Imaging in Medical Applications. In: AMIGO, José Manuel. Hyperspectral Imaging. Amsterdam: Elsevier, 2019. 523–565 p. https://doi.org/10.1016/B978-0-444-63977-6.00021-3
11. FU, Wenxue; MA, Jianwen; CHEN, Pei; CHEN, Fang. Remote Sensing Satellites for Digital Earth. In: GUO, Huadong; GOODCHILD, Michael; ANNONI, Alessandro (eds.). Manual of Digital Earth. Singapore: Springer, 2020. 55–123 p. https://doi.org/10.1007/978-981-32-9915-3_3
12. GHOUS, Usman; SARFRAZ, Muhammad Shahzad; AHMAD, Muhammad; LI, Chenyu; HONG, Danfeng. EXNet: (2+1)D Extreme Xception Net for Hyperspectral Image Classification. In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2024. vol. 17. p. 5159–5172. https://doi.org/10.1109/JSTARS.2024.3362936
13. GREWAL, Reaya; KASANA, Singara Singh; KASANA, Geeta. Hyperspectral Image Segmentation: A Comprehensive Survey. In: Multimedia Tools and Applications. 2023. vol. 82, no. 14. p. 20819–20872. https://doi.org/10.1007/s11042-022-13959-w
14. HU, Qian; WANG, Xinya; JIANG, Junjun; ZHANG, Xiao Ping; MA, Jiayi. Exploring the Spectral Prior for Hyperspectral Image Super-resolution. In: IEEE Transactions on Image Processing. 2024. vol. 33. p. 5260–5272. https://doi.org/10.1109/TIP.2024.3460470
15. HUANG, Hui; SUN, Zehao; LIU, Shuchang; DI, Yanan; XU, Jinzhong; LIU, Caicai; XU, Ren; SONG, Hong; ZHAN, Shuyue; WU, Jiaping. Underwater Hyperspectral Imaging for in Situ Underwater Microplastic Detection. In: Science of The Total Environment. 2021. vol. 776. 145960. https://doi.org/10.1016/j.scitotenv.2021.145960
16. HUANG, He; TAO, Sha. Hyperspectral Image Classification with Token Fusion on GPU. In: Computer Vision and Image Understanding. 2024. vol. 249. 104198. https://doi.org/10.1016/j.cviu.2024.104198
17. HUSSEIN, Sabah Jaber; FAKHRI MERZAH, Zainab. Analysis of Hyperspectral Remote Sensing Images for Extraction Geological Rock Types Maps by Geospatial Techniques. In: IOP Conference Series: Materials Science and Engineering. 2020. vol. 901, no. 1. 012016. https://doi.org/10.1088/1757-899X/901/1/012016
18. KIM, Geonwoo; BAEK, Insuck; STOCKER, Matthew D.; SMITH, Jaclyn E.; VAN-TASSELL, Andrew L.; QIN, Jianwei; CHAN, Diane E.; PACHEPSKY, Yakov; KIM, Moon S. Hyperspectral Imaging from a Multipurpose Floating Platform to Estimate Chlorophyll-a Concentrations in Irrigation Pond Water. In: Remote Sensing. 2020. vol. 12, no. 13. 2070. https://doi.org/10.3390/rs12132070
19. KOLYSHKINA, Inna; SIMOFF, Simeon. Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML approach. In: Frontiers in Big Data. 2021. vol. 4. https://doi.org/10.3389/fdata.2021.660206
20. LECHNER, Alex M.; FOODY, Giles M.; BOYD, Doreen S. Applications in Remote Sensing to Forest Ecology and Management. In: One Earth. 2020. vol. 2, no. 5. p. 405–412. https://doi.org/10.1016/j.oneear.2020.05.001
21. LU, Guolan; FEI, Baowei. Medical Hyperspectral Imaging: A Review. In: Journal of Biomedical Optics. 2014. vol. 19, no. 1. 010901. https://doi.org/10.1117/1.JBO.19.1.010901
22. MAHMOUD, Alaaeldin; EL-SHARKAWY, Yasser H. Instant Plastic Waste Detection on Shores using Laser-induced Fluorescence and Associated Hyperspectral Imaging. In: Optical and Quantum Electronics. 2024. vol. 56, no. 5. 780. https://doi.org/10.1007/s11082-024-06564-8
23. NAVALGUND, Ranganath; JAYARAMAN, Vivek; ROY, Parth Sarathi. Remote Sensing Applications: An Overview. In: Current Science. 2007. vol. 93, no. 12. p. 1447–1766.
24. NIU, Chao; TAN, Kun; WANG, Xue; DU, Peijun; PAN, Chen. A Semi-Analytical Approach for Estimating Inland Water Inherent Optical Properties and Chlorophyll-a Using Airborne Hyperspectral Imagery. In: International Journal of Applied Earth Observation and Geoinformation. 2024. vol. 128. 103774. https://doi.org/10.1016/j.jag.2024.103774
25. PIARULLI, Stefania; MALEGORI, Cristina; GRASSELLI, Ferrante; AIROLDI, Laura; PRATI, Silvia; MAZZEO, Rocco; SCIUTTO, Giorgia; OLIVERI, Paolo. An Effective Strategy for The Monitoring of Microplastics in Complex Aquatic Matrices: Exploiting the Potential of Near Infrared Hyperspectral Imaging (NIR-HSI). In: Chemosphere. 2022. vol. 286, no. 3. 131861. https://doi.org/10.1016/j.chemosphere.2021.131861
26. PLAZA, Antonio; BENEDIKTSSON, Jon Atli; BOARDMAN, Joseph W.; BRAZILE, Jason; BRUZZONE, Lorenzo; CAMPS-VALLS, Gustavo; CHANUSSOT, Jocelyn; FAUVEL, Mathieu; GAMBA, Paolo; GUALTIERI, Anthony; MARCONCINI, Mattia; TILTON, James C.; TRIANNI, Giovanna. Recent Advances in Techniques for Hyperspectral Image Processing. In: Remote Sensing of Environment. 2009. vol. 113. p. S110–S122. https://doi.org/10.1016/j.rse.2007.07.028
27. PROŠEK, Jiří; GDULOVÁ, Kateřina; BARTÁK, Vojtěch; VOJAR, Jiří; SOLSKÝ, Milič; ROCCHINI, Duccio; MOUDRÝ, Vítězslav. Integration of Hyperspectral and LiDAR Data for Mapping Small Water Bodies. In: International Journal of Applied Earth Observation and Geoinformation. 2020. vol. 92. 102181. https://doi.org/10.1016/j.jag.2020.102181
28. SCHRÖER, Christoph; KRUSE, Felix; GÓMEZ, Jorge Marx. A Systematic Literature Review on Applying CRISP-DM Process Model. In: Procedia Computer Science. 2021. vol. 181. p. 526–534. https://doi.org/10.1016/j.procs.2021.01.199
29. SEKHON, Amninder Singh; UNGER, Phoebe; SHARMA, Sonali; SINGH, Bhupinderjeet; CHEN, Xiongzhi; GANJYAL, Girish M.; MICHAEL, Minto. Hyperspectral Imaging of Foodborne Pathogens at Colony and Cellular Levels for Rapid Identification in Dairy Products. In: Food Science & Nutrition. 2024. vol. 12, no. 1. p. 239–254. https://doi.org/10.1002/fsn3.3766
30. SERRANTI, Silvia; PALMIERI, Roberta; BONIFAZI, Giuseppe; CÓZAR, Andrés. Characterization of Microplastic Litter from Oceans by an Innovative Approach Based on Hyperspectral Imaging. In: Waste Management. 2018. vol. 76. p. 117–125. https://doi.org/10.1016/j.wasman.2018.03.003
31. SHAN, Jiajia; ZHAO, Junbo; ZHANG, Yituo; LIU, Lifen; WU, Fengchang; WANG, Xue. Simple and Rapid Detection of Microplastics in Seawater using Hyperspectral Imaging Technology. In: Analytica Chimica Acta. 2019. vol. 1050. p. 161–168. https://doi.org/10.1016/j.aca.2018.11.008
32. SHIMAOKA, André Massahiro; FERREIRA, Renato Cordeiro; GOLDMAN, Alfredo. The Evolution of CRISP-DM for Data Science: Methods, Processes and Frameworks. In: SBC Computing Reviews. 2024. vol. 4, no. 1. p. 28–43. https://doi.org/10.5753/reviews.2024.3757
33. THAKUR, Jay Krishna; TWUMASI, Yaw-A.; MORELLI, Stefano; WESTERN, Luke M.; ROSSER, John-F.; KERVYN, Matthieu. Advances in Remote Sensing Technology. Cham: Scientific Research Publishing, 2017. 325 p.
34. TORRES GIL, Leydy K.; VALDELAMAR MARTÍNEZ, David; SABA, Manuel. The Widespread use of Remote Sensing in Asbestos, Vegetation, Oil and Gas, and Geology Applications. In: Atmosphere. 2023. vol. 14, no. 1. 172. https://doi.org/10.3390/atmos14010172
35. WACZAK, John; AKER, Adam; WIJERATNE, Lakitha O. H.; TALEBI, Shawhin; FERNANDO, Ashen; DEWAGE, Prabuddha M. H.; IQBAL, Mazhar; LARY, Matthew; SCHAEFER, David; BALAGOPAL, Gokul; LARY, David J. Unsupervised Characterization of Water Composition with UAV-Based Hyperspectral Imaging and Generative Topographic Mapping. In: Remote Sensing. 2024. vol. 16, no. 13. 2430. https://doi.org/10.3390/rs16132430
36. WANG, Xinya; HU, Qian; JIANG, Junjun; MA, Jiayi. A Group-Based Embedding Learning and Integration Network for Hyperspectral Image Super-Resolution. In: IEEE Transactions on Geoscience and Remote Sensing. 2022. vol. 60. p. 1–16. https://doi.org/10.1109/TGRS.2022.3217406
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2025 Entramado
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
