Fusion of Sentinel 1 and Alos Palsar Data to Separate Palm Oil Plantations from Forest Cover Mapping using Pauli Decomposition Approach

Authors

Keywords:

SAR, PolSAR, NDFI, Decomposition, Forest Mapping, Landsat.

Abstract

In this work, a multi-sensor approach to extract misclassified oil palm plantations from forest cover map using a modified Pauli Decomposition technique is presented. The proposed method includes the generation of a primary forest cover map built using a Landsat-based Normalized Difference Fraction Index, and then the palm oil plantation is filtered out using scattering mechanisms through the Modified Pauli Decomposition technique based on the fusion of Sentinel 1 and Alos Palsar data. Accuracy assessment of the final product, produces accuracy values of 0.946 for forest class, while the classification accuracy for non-forest class is 0.92.

Downloads

Download data is not yet available.

Author Biographies

Erith Alexander Muñoz, The Food and Agriculture Organization of United Nations

have a degree in Physics (2007) and a Master degree in Electrical Engineering (2012) of the University of Carabobo, Carabobo-Venezuela. Master in Space Applications of Alert and Early Warning to Natural Emergencies (2014) by the National University of Cordoba, Cordoba-Argentina. In 2012 worked as visitant researcher at the Italian National Research Council (CNR-Italy), receiving training in atmospheric remote sensing and numerical weather models development. In 2014 he worked as a researcher in the Ecuadorian Army Geographical Institute in areas of Remote Sensing, Atmospheric Physics, and Numerical Model Development. He currently works as a Regional Expert in Remote Sensing for Latin America and The Caribbean for the Food and Agriculture Organization of United Nations. Between his research interest there are computational electromagnetism, Digital signal Processing of SAR data, High Performance Computing, Parallel Programming, Remote Sensing and Computer Vision.

Alfonso Zozaya, Universidad Tecnológica Metropolitana (UTEM), Santiago de Chile-Chile

received the B.Sc. degree in Electronic Engineering, with a major in Telecommunication, from the Polytechnic Institute of the National Armed Forces of Venezuela (I.U.P.F.A.N.), Maracay, Venezuela, in 1991, and his PhD degree from the Polytechnic University of Catalonia (UPC), Barcelona, Spain, in the area of Signal Theory and Communications in 2002. He worked as a Professor at the University of Carabobo, Valencia, Venezuela from 1994 to 2014. He worked as a senior researcher at the Ecuadorian Space Institute, Quito, Ecuador, in the area of synthetic aperture radars in the periods from September 2014 to September 2015 and from August 2016 to August 2017. Currently, he is with the Universidad Tecnol\'{o}gica Metropolitana, Santiago de Chile, where he works as a Full Professor at the Department of Electricity. His research areas of interest are applied electromagnetic, computational electromagnetic, digital signal processing, RF circuits design, antenna engineering, synthetic aperture radars, and UWB radars.

Erik Lindquist, The Food and Agriculture Organization of United Nations

is currently a Forestry Officer with the United Nations Food and Agriculture Organization based in Quito, Ecuador. He has 23 years of experience in remote sensing and GIS. He started his career working for the US Forest Service as a plant ecologist in the Wind River Mountains of Wyoming. He then moved to central Africa and worked with the Wildlife Conservation Society leading botanical and wildlife surveys in the Democratic Republic of Congo. His current focus with FAO is creating platforms that facilitate the use of geospatial data for autonomous land surface monitoring at national scales, especially in developing countries. In collaboration with the international Global Forest Observations Initiative, national research institutions, and Ministries of Environment the FAO has launched a cloud-based computing platform called SEPAL (System for Earth Observation Data Acquisition, Processing and Analysis for Land Monitoring). SEPAL is a big-data processing platform that combines super-computing power, open-source geospatial data processing software and modern geospatial data infrastructures like Google’s Earth Engine to enable researchers and technicians anywhere in the world to create data and produce locally relevant results that can affect decision making. Erik has a Bachelor’s degree in Botany from Miami University (Ohio) and a PhD in Geospatial Science and Engineering from South Dakota State University.

References

K. Calders, I. Jonckheere, J. Nightingale, and M. Vastaranta, “Remote sensing technology applications in forestry and redd+,” 2020.

A. Miranda, A. Lara, A. Altamirano, C. Zamorano-Elgueta, H. J. Hernández, M. E. González, A. Pauchard, and Á. Promis, “Monitoreo de la superficie de los bosques nativos de chile: un desafı́o pendiente,” Bosque (Valdivia), vol. 39, no. 2, pp. 265–275, 2018

E. Honorio Coronado and T. R. Baker, “Manual para el monitoreo del ciclo del carbono en bosques amazónicos,” 2010

F. Team et al., “From reference levels to results reporting: Redd+ under the united nations framework convention on climate change.” 2020.

S.-M. Joo and J.-S. Um, “Evaluating mrv potentials based on satellite

image in un-redd opportunity cost estimation: A case study for mt.

geum-gang of north korea,” Spatial Information Research, vol. 22, no. 3,

pp. 47–58, 2014.

D. Müller, S. Suess, A. A. Hoffmann, and G. Buchholz, “The value of satellite-based active fire data for monitoring, reporting and verification of redd+ in the lao pdr,” Human ecology, vol. 41, no. 1, pp. 7–20, 2013.

R. Meng, J. Wu, F. Zhao, B. D. Cook, R. P. Hanavan, and S. P. Serbin, “Measuring short-term post-fire forest recovery across a burn severity gradient in a mixed pine-oak forest using multi-sensor remote sensing techniques,” Remote Sensing of Environment, vol. 210, pp. 282–296, 2018.

P. Hyde, R. Dubayah, W. Walker, J. B. Blair, M. Hofton, and C. Hunsaker, “Mapping forest structure for wildlife habitat analysis using multi-sensor (lidar, sar/insar, etm+, quickbird) synergy,” Remote

Sensing of Environment, vol. 102, no. 1-2, pp. 63–73, 2006.

M. Vohland, J. Stoffels, C. Hau, and G. Schuler, “Remote sensing techniques for forest parameter assessment: multispectral classification and linear spectral mixture analysis,” Silva Fennica, vol. 41, no. 3, p.441, 2007.

A. Banskota, N. Kayastha, M. J. Falkowski, M. A. Wulder, R. E. Froese, and J. C. White, “Forest monitoring using landsat time series data: A review,” Canadian Journal of Remote Sensing, vol. 40, no. 5, pp. 362–

, 2014.

E. Muñoz, A. Zozaya, and E. Lindquist, “Satellite remote sensing of forest degradation using ndfi and the bfast algorithm,” IEEE Latin America Transactions, vol. 18, no. 07, pp. 1288–1295, 2020.

G. P. Asner, M. Keller, R. Pereira Jr, and J. C. Zweede, “Remote sensing of selective logging in amazonia: Assessing limitations based on detailed field observations, landsat etm+, and textural analysis,” Remote Sensing of Environment, vol. 80, no. 3, pp. 483–496, 2002.

C. Dickinson, P. Siqueira, D. Clewley, and R. Lucas, “Classification of forest composition using polarimetric decomposition in multiple landscapes,” Remote sensing of environment, vol. 131, pp. 206–214, 2013.

J. C. Vogeler and W. B. Cohen, “A review of the role of active remote sensing and data fusion for characterizing forest in wildlife habitat models,” Revista de Teledetección.(45): 1-14., no. 45, pp. 1–14, 2016.

“CMNUCConvensión marco de las naciones unidas para el cambio climático,” https://redd.unfccc.int/submissions.html, accessed: 2021-02-18.

A. Zozaya, “Electromagnetic interaction models for the characterization of targets in sar scenes: preliminary literature review,” Revista Ingenierı́a UC, vol. 22, no. 1, pp. 26–63, 2015.

X. Mei, W. Nie, J. Liu, and K. Huang, “Polsar image crop classification based on deep residual learning network,” in 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics).

IEEE, 2018, pp. 1–6.

M. Erith, Z. Alfonso, and L. Erik, “A multi-sensor approach to separate palm oil plantations from forest cover using ndfi and a modified pauli decomposition technique,” in IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020, pp. 4481–4484.

D. Roberts, M. Smith, and J. Adams, “Green vegetation, nonphotosynthetic vegetation, and soils in aviris data,” Remote Sensing of Environment, vol. 44, no. 2-3, pp. 255–269, 1993.

C. Souza Jr, L. Firestone, L. M. Silva, and D. Roberts, “Mapping forest degradation in the eastern amazon from spot 4 through spectral mixture models,” Remote sensing of environment, vol. 87, no. 4, pp. 494–506, 2003.

N. Keshava, “A survey of spectral unmixing algorithms,” Lincoln laboratory journal, vol. 14, no. 1, pp. 55–78, 2003.

C. M. Souza Jr, D. A. Roberts, and M. A. Cochrane, “Combining spectral and spatial information to map canopy damage from selective logging and forest fires,” Remote Sensing of Environment, vol. 98, no. 2-3, pp. 329–343, 2005.

B. R. Parida and S. P. Mandal, “Polarimetric decomposition methods for lulc mapping using alos l-band polsar data in western parts of mizoram, northeast india,” SN Applied Sciences, vol. 2, pp. 1–15, 2020.

M. Musthafa, U. Khati, and G. Singh, “Sensitivity of polsar decomposition to forest disturbance and regrowth dynamics in a managed forest,” Advances in Space Research, vol. 66, no. 8, pp. 1863–

, 2020.

D. Hernández and D. Pinilla, “Realización de mapas de cobertura de la tierra a partir de imágenes polarimétricas,” Revista de teledetección: Revista de la Asociación Española de Teledetección, no. 39, pp. 119–124, 2013.

L. Zhang, J. Zhang, B. Zou, and Y. Zhang, “Comparison of methods for target detection and applications using polarimetric sar image,” Piers online, vol. 4, no. 1, pp. 140–145, 2008.

X. Huang, N. Torbick, and B. Ziniti, “Study of a simple volume scattering model on burned forest using polarimetric palsar-2 data,” IEEE Geoscience and Remote Sensing Letters, vol. 15, no. 12, pp. 1872–1876,

R. Natsuaki, T. Shimada, and A. Hirose, “Effect of temporal baseline in pixel-by-pixel scattering mechanism vector optimization for polinsar,” in EUSAR 2018; 12th European Conference on Synthetic Aperture Radar. VDE, 2018, pp. 1–3.

FAO, “Sepal,” 2020.

N. Gorelick, M. Hancher, M. Dixon, S. Ilyushchenko, D. Thau, and R. Moore, “Google earth engine: Planetary-scale geospatial analysis for everyone,” Remote Sensing of Environment, 2017. [Online]. Available: https://doi.org/10.1016/j.rse.2017.06.031

K. Xu, J. Qian, Z. Hu, Z. Duan, C. Chen, J. Liu, J. Sun, S. Wei, and X. Xing, “A new machine learning approach in detecting the oil palm plantations using remote sensing data,” Remote Sensing, vol. 13, no. 2, p. 236, 2021.

K. L. Chong, K. D. Kanniah, C. Pohl, and K. P. Tan, “A review of remote sensing applications for oil palm studies,” Geo-spatial Information Science, vol. 20, no. 2, pp. 184–200, 2017.

Published

2022-02-23

How to Cite

Muñoz, E. A., Zozaya, A., & Lindquist, E. (2022). Fusion of Sentinel 1 and Alos Palsar Data to Separate Palm Oil Plantations from Forest Cover Mapping using Pauli Decomposition Approach. IEEE Latin America Transactions, 20(6), 921–930. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/5664