Intelligent mapping of irrigated areas from Landsat 8 images using transfer learning

Abstract

The lack of reliable and up-to-date data in developing countries is a major obstacle to sustainable development. In Morocco, where groundwater withdrawals by farmers are very intensive and informal, maps describing and monitoring the extension of irrigated areas are scarce and labor-intensive to obtain. In this paper a novel transfer learning algorithm is proposed to map irrigated areas at different stages of an agricultural cycle from Landsat 8 images. The results obtained displays satisfactory performance over traditional machine learning algorithms. On a small dataset, we initially tested three well known deep learning architectures (SegNet, DenseNet and Unet). The results obtained were not satisfactory. So, to get high performance, we rely on a transfer learning architecture combining UNet with ResNet50 backbone (trained on 2012 ILSVRC ImageNet dataset) as a baseline after a phase where different configurations were tested. In the first part of this study, we compared the use of three optimization methods: Adam and two variants of Stochastic Gradient Descent (SGD) associated with two techniques (Cyclical Learning Rate and Warm Restart) to find the optimal learning rate and then test the impact of data augmentation on the overall accuracies. Data augmentation had improved the overall accuracy for the three methods. Adam based method from 94% to 97% with mean IoU of 0,79 (for all land cover classes) and 0,86 for irrigated areas class. For SGD based methods, the overall accuracy had increased from 91% to 94% with mean IoU of 0,75 (for all land cover classes) and 0,82 for irrigated areas class. As we are interested in having irrigated areas maps at different key periods of the agricultural cycle, we also explored, in the second part of this study, the temporal generalization of the best model. 

Keywords

• Irrigated areas mapping
• Landsat 8
• Deep learning
• UNet
• ResNet50

References

1. Acquarelli J, Marchiori E, Buydens L M C, Tran T & van Laarhoven T (2018). Spectral-spatial classification of hyperspectral images: Three tricks and a new learning setting. Remote Sensing, 10(7), 1156. DOI: 10.3390/rs10071156
2. Audebert N, Le Saux, B & Lefèvre S (2017). Fusion of heterogeneous data in convolutional networks for urban semantic labeling. 2017 Joint Urban Remote Sensing Event (JURSE), 1-4.
3. Audebert, N, Le Saux B & Lefèvre S (2016). Semantic segmentation of earth observation data using multimodal and multi-scale deep networks. Asian Conference on Computer Vision. Springer, Cham, 180-196.
4. Badrinarayanan V, Kendall A & Cipolla R (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 39(12), 2481-2495.
5. Ball J E, Anderson D T & Wei P (2018). State-of-the-art and gaps for deep learning on limited training data in remote sensing. IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, 4119-4122.
6. Benbahria Z, Sebari I, Hajji H & Smiej M F (2018). Automatic mapping of irrigated areas in Mediterranean context using Landsat 8 time series images and random forest algorithm. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 7986-7989. Valencia, Spain, DOI: 10.1109/IGARSS.2018.8517810
7. Bergstra J & Bengio Y (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13, 281–305.
8. Bilinski P & Prisacariu V (2018). Dense decoder shortcut connections for single-pass semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6596-6605.

9. Bloice M D (2017). https://github.com/mdbloice/Augmentor Accessed date: January, 27th 2020
10. Diederik P K & Jimmy L B (2014). Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations, San Diego
11. Feng W, Sui H, Huang W, Xu C & An K (2019). Water body extraction from very high-resolution remote sensing imagery using deep U-Net and a superpixel-based conditional random field model. IEEE Geoscience and Remote Sensing Letters, 16(4), 618-622.
12. Ghazi M M, Yanikoglu B & Aptoula E (2017). Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing, 235, 228-235.
13. He K, Zhang X, Ren S & Sun J (2016). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778.
14. Iglovikov V, Mushinskiy S & Osin V (2017). Satellite imagery feature detection using deep convolutional neural network: A kaggle competition. Computer Vision and Pattern Recognition.
15. Jégou S, Drozdzal M, Vazquez D, Romero A & Bengio Y (2017). The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 11-19.
16. Jiang R X (2017). https://towardsdatascience.com/dstl-satellite-imagery-contest-on-kaggle-2f3ef7b8ac40 Accessed date: 1May, 2020)
17. Johnson B A, Tateishi R & Hoan N T (2012). Satellite image pansharpening using a hybrid approach for object-based image analysis. ISPRS International Journal of Geo-Information, 1(3), 228-241.
18. Kenstler, B. (2018). https://github.com/bckenstler/CLR Accessed date: January, 27th 2020
19. Khryashchev V, Ivanovsky L, Pavlov V, Ostrovskaya A & Rubtsov A (2018). Comparison of Different Convolutional Neural Network Architectures for Satellite Image Segmentation. 23rd Conference of Open Innovations Association (FRUCT), 172-179
20. Lagrange A, Le Saux B, Beaupere A, Boulch A, Chan-Hon-Tong A, Herbin S, Randrianarivo H & Ferecatu M (2015). Benchmarking classification of earth-observation data: From learning explicit features to convolutional networks. International Geoscience and Remote Sensing Symposium (IGARSS), 4173-4176.
21. LeCun Y, Bottou L, Bengio Y & Haffner P (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
22. Lin Z, Chen Y, Zhao X &Wang G (2013). Spectral-spatial classification of hyperspectral image using autoencoders. In: 2013 9th International Conference on Information, Communications & Signal Processing.
23. Liu T, Abd-Elrahman A, Morton J & Wilhelm V L (2018). Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system. GIScience & remote sensing, 55(2), 243-264.
24. Liu X, Deng Z & Yang Y (2019). Recent progress in semantic image segmentation. Artificial Intelligence Review, 52, p. 1089-1106.
25. Long J, Shelhamer E & Darrell T (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431–3440.
26. Loshchilov I & Hutter F (2016). Sgdr: Stochastic gradient descent with warm restarts. ICLR 2017, 1-16
27. Merdas M, Ozdogan M, Benbahria Z, Khajour L & Youssoufi E E (2015). Mapping of irrigated crops and monitoring of their evolution using satellite images. GEO OBSERVATEUR, N°22
28. Mnih V (2013). Machine learning for aerial image labeling. PHD Thesis, University of Toronto, Canada
29. Othman E, Bazi Y, Alajlan N, Alhichri H & Melgani F (2016). Using convolutional features and a sparse autoencoder for land-use scene classification. International Journal of Remote Sensing, 37(10), 1977–1995
30. Ozdogan M, Yang Y, Allez G & Cervantes C (2010). Remote sensing of irrigated agriculture: Opportunities and challenges. Remote Sensing, 2, 2274-2304 DOI: 10.3390/rs2092274
31. Paisitkriangkrai S, Sherrah J, Janney P & Hengel V D A (2015). Effective semantic pixel labelling with convolutional networks and conditional random fields. Conference on Computer Vision and Pattern Recognition Workshops, 36-43
32. Pan S J & Yang Q (2010). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345-1359.
33. Panboonyuen T, Jitkajornwanich K, Lawawirojwong S, Srestasathiern P & Vateekul P (2019). Semantic segmentation on remotely sensed images using an enhanced global convolutional network with channel attention and domain specific transfer learning. Remote Sensing, 11(1), 83.
34. Papadomanolaki M, Vakalopoulou M, Zagoruyko S & Karantzalos K (2016). Benchmarking deep learning frameworks for the classification of very high resolution satellite multispectral data. ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences, 3(7), 83-88
35. Pirotti, F. and Sunar, F. and Piragnolo, M. (2016). Benchmark of machine learning methods for classification of a Sentinel-2 image. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 41, 335-340
36. Ronneberger O, Fischer P & Brox T (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, 9351, 234-241. Springer, Cham.
37. Sherrah J (2016). Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery. Computer Vision and Pattern Recognition
38. Smith L N (2017). Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), 464-472
39. Thoma M (2016). A survey of semantic segmentation. Computer Vision and Pattern Recognition
40. Tuia D, Persello C & Bruzzone L (2016). Domain adaptation for the classification of remote sensing data: An overview of recent advances. IEEE geoscience and remote sensing magazine, 4(2), 41-57.
41. Vooban A (2017). https://medium.com/vooban-ai/satellite-image-segmentation-a-workflow-with-u-net-7ff992b2a56e Accessed date 1 May 2020
42. Wu Z, Shen C & Hengel A V D (2016). High-performance semantic segmentation using very deep fully convolutional networks. Computer Vision and Pattern Recognition
43. Wurm M, Stark T, Zhu X X, Weigand M & Taubenböck, H (2019). Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing, 150, 59-69.
44. Xu Y Wu L, Xie Z & Chen Z (2018). Building extraction in very high-resolution remote sensing imagery using deep learning and guided filters. Remote Sensing, 10(1), 144. DOI: 10.3390/rs10010144
45. Yakubovskiy, P. (2018). https://github.com/qubvel/segmentation_models Accessed date :1 May 2020
46. Yang J, Zhao Y, Chan J C W & Yi C (2016). Hyperspectral image classification using two-channel deep convolutional neural network. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 5079-5082.
47. Younis M C & Keedwell E (2019). Semantic segmentation on small datasets of satellite images using convolutional neural networks. Journal of Applied Remote Sensing, 13(4) DOI: 10.1117/1.JRS.13.046510
48. Zhang C, Yue P, Di L & Wu Z (2018). Automatic identification of center pivot irrigation systems from landsat images using convolutional neural networks. Agriculture, 8(10), 147. DOI: 10.3390/agriculture8100147
49. Zhu X X, Tuia D, Mou L, Xia G S, Zhang L, Xu F & Fraundorfer F (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8-36.