NIPES Journal of Science and Technology Research 4(4) 2022 pp.40- 56 

Oil Palm Plantation Detection in Satellite Image Using Deep Learning

Fidelis Odinma Chete  and  Vincent Akinwande

Abstract

The traditional approach, such as manual surveys, used by farmers and governments to detect where oil palms are planted has proven to be ineffective, tedious and time consuming. This problem can be addressed if images obtained from satellites can be used to scan through the forest to detect oil palm plantations.  In this paper, we developed a web based deep learning system that is capable of processing a satellite image of land to detect the presence of oil palm plantations in Nigeria using high-resolution satellite imagery. This research designed a detection system which uses a convolutional neural network to extricate important features, and a classifier trained using satellite images. Results showed exceptional effectiveness with a training loss of 0.11 and an accuracy of 99.0%. Utilizing different images for validation taken from diverse elevations, the model reached a training loss of 0.245 and an accuracy of 82.9999% on validation data, while on test data we got 1.59 in loss and an accuracy of 87.5%. Thus, the proposed approach is seemingly effective within the field of precision agriculture.

Keywords: Computerized Mapping, Convolutional Neural Network, Deep Learning, Oil Palm, Satellite Imagery

Cite this article as: Fidelis Odinma Chete, & Vincent Akinwande. (2022). Oil Palm Plantation Detection in Satellite Image Using Deep Learning. NIPES Journal of Science and Technology Research, 4(4), 40–56. https://doi.org/10.5281/zenodo.7393401

  1. Bonet, F. Caraffini, A. Pena, A. Puert, and  M. Gongora (2020).  “Oil palm detection via deep transfer learning.” IEEE Congress on Evolutionary Computation (CEC),    pp. 1-8
  2. Cheng, L. Yu,  Y. Xu, H. Lu,  A.P. Cracknell,  K. Kanniah  and  P. Gong (2018). ”Mapping oil palm extent in Malaysia using ALOS-2 PALSAR-2 data”. Int. J. Remote Sens.  39, 432–452.
  3. K. Lian and  D. S. Wilcove (2007).” Cashing in palm oil for conservation”. Nature 448, 993–4.
  4. U. Ojo, R. A. Offiong, S. Odion-Akhaine, A. Baiyewu-Teru, and   F. Allen (2017)    .” Oil palm plantations in forest landscapes: impacts, aspirations and ways forward in Nigeria”. Wageningen, the Netherlands: Tropenbos International. 2017.
  5. Li, H. Fu, L.Yu and A. Cracknell (2016). “A deep learning based oil palm tree detection and counting for high resolution remote sensing images”. Remote Sens.  9, 22.
  6. Li, R. Dong, H. Fu and L.Yu (2019). “Large-scale oil palm tree detection from high-resolution satellite images using two-stage convolutional neural networks”. Remote Sensing, 2019, 11(1): 11.
  7. Xinni, H. G. Kamarul, H. Fengrong and I. M. Izzeldin (2021).   “Automatic Detection of Oil Palm Tree from UAV Images Based on the Deep Learning Method”. Applied Artificial Intelligence, 35(1), 13-24.
  8. A. Mubin, E. Nadarajoo, H. Z. M Shafri and  A. Hamedianfar (2019). “Young and mature oil palm tree detection and counting using convolutional neural network deep learning method”.  International journal of remote sensing,  40(19),7500-7515
  9. Blaschke(2010) “Object based image analysis for remote sensing”. ISPRS journal of photogrammetry and remote sensing,  65(1), 2-16.
  10. Chen, E. Dobriban and J. H. Lee (2020). “A group-theoretic framework for data augmentation”. Journal of Machine Learning Research, 21(245), 1-71
  11. Yang, Z. Zeng, S. G. Teo     L. Wang,   V. Chandrasekhar  and  S. Hoi (2018). “Deep learning for practical image recognition: Case study on kaggle competitions”. Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining,   pp 923-931
  12. He, X. Zhang, S. Ren and  J. Sun (2016). ” Deep Residual Learning for Image Recognition”. In Proceedings of the  2016  IEEE conference on computer vision and pattern recognition,  pp 770-778,  doi:10.1109/CVPR.2016.90
  13. Hamilton, S. Raghunathan, A. Annavajhala,    D. Kirsanov,    E. De Leon,   E. Barzilay,    I. Matiach, J. Davison,  M. Busch,   M. Oprescu,   R. Sur,  R. Astala, T. Wen  and   C. Park (2017). “Flexible and Scalable Deep Learning with MMLSpark” . Journal of Machine Learning Research, 1-48. Retrieved September 12, 2022 from: https://www.researchgate.net/figure/Schematic-overview-of-basic-transfer-learning-algorithm-We-use-ResNet50-and-truncate-the_fig3_324472161
  14. Feng (2017). “An Overview of ResNet and its Variants. Towards Data Science”. Retrieved September 12, 2022 from https://towardsdatascience.com/an-overview-of-resnet-and-its-variants-5281e2f56035