Abstract
Accurate assessment of Trees outside forest (TOF) is an essential input for the management and preservation of these vast resources, due to their importance in carbon sequestration and biodiversity conservation. Many studies have demonstrated the use of High-resolution satellite (HRS) imageries for mapping and monitoring of TOF in urban and rural landscapes. The conventional per-pixel classifier is not a suitable option for HRS data classification, owing to inherent high intra-class variability and high interclass similarity. In the present study, a convolution neural network-based approach was employed for TOF mapping using HRS images, predominantly in the urban landscape of Bengaluru city, India. We developed a semi-automated procedure for the generation of labelled training samples using object-based image analysis (OBIA), minimizing time requirement for input training data preparation for deep learning (DL) model development. These inputs were utilized to develop a DL model for the classification of TOF using U-Net, which is a semantic segmentation-based DL architecture. The results indicated that the model performed well for the classification of urban TOF with an overall classification accuracy of 89.65 percent and an F1 score of 93.03 percent, in comparison with OBIA (overall accuracy of 80.73 percent & F1 score of 86.44 percent). We demonstrated utilisation of a developed methodology for the assessment of TOF in a distinctive urban landscape, which can be extended to agriculture dominated regions in diverse landscapes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
Comply with standards.
References
Atif, N., Bhuyan, M., & Ahamed, S. (2019). A review on semantic segmentation from a modern perspective. International Conference on Electrical Electronics and Computer Engineering (UPCON). https://doi.org/10.1109/UPCON47278.2019.8980189]
Brandt, J., & Stolle, F. (2020). A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery. International Journal of Remote Sensing, 42(5), 1713–1737. https://doi.org/10.1080/01431161.2020.1841324
Brandt, M., et al. (2020). An unexpectedly large count of trees in the West African Sahara and Sahel. Nature, 587, 78–82. https://doi.org/10.1038/s41586-020-2824-5
Chakravarty, S., Pala, N. A., Tamang, B., Sarkar, B. C., Abha Manohar, K., Rai, P., Puri, A., & Vineeta, G. S. (2019). Ecosystem Services of Trees Outside Forest. In M. K. Jhariya, A. Banerjee, R. S. Meena, & D. K. Yadav (Eds.), Sustainable Agriculture, Forest and Environmental Management (pp. 327–352). Singapore: Springer Singapore. https://doi.org/10.1007/978-981-13-6830-1_10
Cheng, G., Han, J., & Lu, X. (2017). Remote sensing image scene classification: benchmark and state of the art. Proceedings of the IEEE, 105, 1865–1883. https://doi.org/10.1109/JPROC.2017.2675998
FAO, (2013). Towards the assessment of trees outside forests. Forest resources assessment, working paper 183. A thematic report prepared in the framework of the global forest resources assessment 2010, Rome. p 335.
FSI. (2019). India State of Forest Report. Dehradun, India: Forest Survey of India.
FSI. (2020). Trees outside forests resources in india. Forest Survey of India Technical Information Series, 2(1), 1–30.
Ganesha, R. K., Shivam, T., Ramesh, K. S., Sudha, R., Rama, S. S., Ravishankar, H. M., & Vidya, A. (2020). Assessment of Vegetation Cover of Bengaluru City, India, Using Geospatial Techniques. Journal of the Indian Society of Remote Sensing. https://doi.org/10.1007/s12524-020-01259-5
He, K., Zhang, X., Ren, S., Sun, J. (2015). Deep residual learning for image recognition, https://arxiv.org/abs/1512.03385
Hebbar, R., Ravishankar, H. M., Trivedi Shivam, Subramoniam, S. R., Uday, R., & Dadhwal, V. K. (2014). Object oriented classification of high resolution data for inventory of horticultural crops. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Hyderabad, XL–8, 745–749.
Hebbar, R., Ravishankar, H. M., Trivedi, S., Manjula, V. B., Kumar, N. M., Mukharib, D. S., Mote, J. K., Sudeesh, S., Raj, U., Raghuramulu, Y., & Raj, K.G. (2019). National level inventory of coffee plantations using high resolution satellite data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3/W6, 293–298.
Immitzer, M., Atzberger, C., & Koukal, T. (2012). Tree species classification with random forest using very high spatial resolution 8-band worldview-2 satellite data. Remote Sensing, 4, 2661–2693. https://doi.org/10.3390/rs4092661
Jha, C. S., Fararoda, R., Rajasekar, G., Singh, S., Dadhwal, V. K. (2015). Spatial distribution of biomass in Indian forests using spectral modelling. Geospatial Information Systems for Multi-Scale Forest Biomass Assessment and Monitoring in Hindu Kush Himalayan region, ICIMOD, Special Science Publication, Nepal, p 139–156.
Lal, R. (2002). Soil carbon sequestration in China through agricultural intensification, and restoration of degraded and desertified ecosystems. Land Degradation & Development., 13, 469–478. https://doi.org/10.1002/ldr.531
Lantzanakis, G., Mitraka, Z., & Chrysoulakis, N. (2021). X-SVM: An extension of C-SVM algorithm for classification of high-resolution satellite imagery. IEEE Transactions on Geoscience and Remote Sensing, 59(5), 3805–3815. https://doi.org/10.1109/TGRS.2020.3017937
Maa, L., Liuc, Y., Zhanga, X., Yuanxin, Y., Gaofei, Y., & Alan Johnson, B. (2019). Deep learning in remote sensing applications: A meta-analysis and review. ISPRS Journal of Photogrammetry and Remote Sensing, 152, 166–177. https://doi.org/10.1016/j.isprsjprs.2019.04.015
Pujar, G. S., Dadhwal, V. K., Murthy, M. S. R., Shivam, T., Reddy, P. M., Swapna, D., & Jha, C. S. (2016). Geospatial approach for national level TOF assessment using IRS high resolution imaging: Early Results. Journal of the Indian Society of Remote Sensing. https://doi.org/10.1007/s12524-015-0476-y
Pujar, G. S., Reddy, P. M., Jha, C. S., & Dadhwal, V. K. (2014). Estimation of trees outside forests using IRS high resolution data by object based image analysis. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences., 40(8), 623–628. https://doi.org/10.5194/isprsarchives-XL-8-623-2014
Ramachandra, T.V., Aithal, B.H., Kulkarni, G., Vinay, S. (2014). Green spaces in Bengaluru: Quantification through geospatial techniques. http://ces.iisc.ernet.in/energy; http://ces.iisc.ernet.in/foss.
Ray, S. S., Sanapala, M., Handique, B. K. (2018). Horticultural crops assessment and development using remote sensing, shaping future of indian horticulture. 8th Indian Horticulture Congress, Indira Gandhi Krishi Vishwavidyalaya, Raipur, Chhattisgarh.
Rizvi, R. H., Handa, A. K., Sridhar, K. B., Kumar, A., Bhaskar, S., Chaudhari, S. K. (2020). Mapping agroforestry and trees outside forest. Jointly published by the ICAR, Central Agroforestry Research Institute (CAFRI), Jhansi and World Agroforestry (ICRAF), South Asia Regional Programme, New Delhi.
Ronneberger, O., Fisher, P., Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation https://arxiv.org/abs/1505.04597
Roy, P. S., Behera, M. D., Murthy, M. S. R., Roy, A., Sarnam Singh, S. P. S., Kushwaha, C. S., Jha, S., Sudhakar, P. K., Joshi, Ch., Reddy, S., Gupta, S., Girish Pujar, C. B. S., Dutt, V. K., Srivastava, M. C. P., Poonam Tripathi, J. S., Singh, V. C., Skidmore, A. K., Rajshekhar, G., Kushwaha, D., … Ramachandran, R. M. (2015). New vegetation type map of India prepared using satellite remote sensing: Comparison with global vegetation maps and utilities. International Journal of Applied Earth Observation and Geoinformation, 39, 142–159. https://doi.org/10.1016/j.jag.2015.03.003
Schnell, S., Altrell, D., Stahl, G., & Kleinn, C. (2014). The contribution of trees outside forests to national tree biomass and carbon stocks: A comparative study across three continents. Environmental Monitoring and Assessment., 187, 1–18. https://doi.org/10.1007/s10661-014-4197-4
Smith, L.N. (2017). Cyclical Learning Rates for Training Neural Networks arXiv.1506.01186v6 [cs.CV]
Smith, L.N., (2018). A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay. arXiv.1803.09820v2 [cs. LG]
Tanksale, N. (2018). Finding Good Learning Rate and the One Cycle Policy. https://towardsdatascience.com/finding-good-learning-rate-and-the-one-cycle-policy-7159fe1db5d6
Zhang, C., Sargent, I., Pan, X., Li, H., Gardiner, A., Hare, J., & Atkinson, P. M. (2018). An object-based convolutional neural network (OCNN) for urban landuse classification. Remote Sensing of Environment., 216(10), 57–70. https://doi.org/10.1016/j.rse.2018.06.034
Zhao, Z. Q., Zheng Peng, Xu., & Xindong, S.-T. (2019). Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems., 30(11), 3212–3232. https://doi.org/10.1109/TNNLS.2018.2876865
Acknowledgements
The authors express their gratitude to Director, National Remote Sensing Centre, Indian Space Research Organization for his valuable guidance and constant encouragement during this study. They are also grateful to all technical, administrative and support staff of RRSC-South/NRSC for their support during this study.
Funding
The study was completed as an in-house research activity without any external funding.
Author information
Authors and Affiliations
Contributions
All authors have contributed, have been informed and consented about manuscript submission.
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Vinod, P.V., Trivedi, S., Hebbar, R. et al. Assessment of Trees Outside Forest (TOF) in Urban Landscape Using High-Resolution Satellite Images and Deep Learning Techniques. J Indian Soc Remote Sens 51, 549–564 (2023). https://doi.org/10.1007/s12524-022-01646-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12524-022-01646-0