Abstract
Understanding and analyzing the changes in vegetation cover is very important in several aspects including climatic changes, water budget, ecological balance and specially to undertake necessary conservation measures. The concept of neural network has gained much significance in the analysis of vegetation dynamics using remote sensing satellite data. In the current study an attempt has been made to predict the vegetation dynamics using MODIS NDVI time series data sets and long short term memory network, an advanced technique adapted from the artificial neural network. The dataset of 861 NDVI images from January 2000 to June 2016 is used for making the time series. The data is segregated into three sets which comprises of training set (70%), validation set (20%), and testing set (10%). To check the reliability of the experiment we have finalised two different regions after extensive research for investigation. These include different terrains in the Great Nicobar Islands, one region along the coast where vegetation has severe ecological damage due to 2004 Indian Ocean tsunami and the other, an interior region which remained imperturbable during the tsunami. Long short term memory network, an advanced neural network is trained with these NDVI values for both the regions separately to predict the future vegetation dynamics. To measure the accuracy of the LSTM network, root mean square error is calculated. The resulting plots from both the experiments indicate that the long short-term memory neural network follows the series in addition to coinciding with the required time series. Also, an unanticipated change in the trend of the NDVI series were well adapted by the network and was able to predict the future NDVI values with good accuracy maintaining RMSE less than 0.03 without providing any supplementary data. By adopting the prescribed method in the paper, anticipation of vegetation changes can be done accurately much ahead of time and take proactive measures accordingly to safeguard and improve the vegetation in any area.
Similar content being viewed by others
References
Agatonovic-Kustrin S, Beresford R (2000) Basic concepts of artificialneural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal 22(5):717–727
Agone V, Bhamare SM (2012) Change detection of vegetation cover using remote sensing and GIS. J Res Dev 2(4)
Anderson JR (1976) A land use and land cover classification system for use with remote sensor data. US Government Printing Office, Washington, D.C. ).
Anonymous (2000) Understanding the Normalized Difference VegetationIndex (NDVI). Accessed 03 June 2017
Anonymous (2003) Biodiversity characterization at landscape level in Andaman and Nicobar islands using remote sensing and geographic information system. Indian Institute of Remote Sensing, Dehra Dun, p 304
Atkinson PM, Tatnall ARL (1997) Introduction neural networks in remote sensing. Int J Remote Sens 18(4):699–709
Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult IEEE Trans Neural Netw, 5(2):pp 157–166
Budama N (2015) A deep drive into recurrent neural nets. http://nikhilbuduma.com/2015/01/11/a-deep-dive-into-recurrent-neural-networks/. Accessed 19 Jun 2017
Cai S, Liu D (2015) Detecting change dates from dense satellite time series using a sub-annual change detection algorithm. Remote Sens 7:8705–8727
Chen J, Jonsson P, Tamura M et al (2004) A simple method for reconstructing a high-quality NDVI time-series data set based on the Savitzky–Golay filter. Remote Sens Environ 91:332–344
Colah (2015) Understanding LSTM Networks. http://colah.github.io/posts/2015-08-Understanding-LSTMs/. Accessed 19 Apr 2017
Coppin P, Jonckheere I, Nackaerts K, Muys B, Lambin E (2004) Review ArticleDigital change detection methods in ecosystem monitoring: a review. Int J Remote Sens 25(9):1565–1596
Cordeiro C, Cristina S, Goela PC, Danchenko S, Icely J, Lavender S, Newton A (2016) Time series analysis of remote sensing data. http://www.joclad2016.uevora.pt/index.php?/event/content/download/811/4417/file/. Accessed 19 Jan 2017
De Beurs KM, Henebry GM (2005) A statistical framework for the analysis of long image time series. Int J Remote Sens 26(8):1551–1573
Eilers PH (2003) A perfect smoother. Anal Chem 75(14):3631–3636
Eslamian S, Eslamian FA (2017) Handbook of drought and water scarcity: principles of drought and water scarcity. CRC Press, Florida, p 674
Foody GM (2006) Pattern recognition and classification of remotely sensed images by artificial neural networks. In: Ecological informatics. Springer, Berlin, pp 459–477
Gamboa JCB (2017) Deep Learning for Time-Series Analysis. arXiv preprint arXiv:1701.01887
Geng L, Ma M, Wang X, Yu W, Jia S, Wang H (2014) Comparison of eight techniques for reconstructing multi-satellite sensor time-series NDVI data sets in the Heihe river Basin, China. Remote Sens 6:2024–2049
Gershenson C (2003) Artificial neural networks for beginners. arXiv preprint cs/0308031
Gómez C, Wulder MA, White JC, Montes F, Delgado JA (2012) Characterizing 25 years of change in the area, distribution, and carbon stock of Mediterranean pines in Central Spain. Int J Remote Sens 33(17):5546–5573
Gómez C, White JC, Wulder MA, Alejandro P (2014) Historical forest biomass dynamics modelled with Landsat spectral trajectories. ISPRS J Photogramm Remote Sens 93:14–28
Gómez C, White JC, Wulder MA (2016) Optical remotely sensed time series data for land cover classification: a review. ISPRS J Photogramm Remote Sens 116:55–72
Gopal S, Woodcock C (1996) Remote sensing of forest change using artificial neural networks. IEEE Trans Geosci Remote Sens 34(2):398–404
Haas EM, Bartholomé E, Combal B (2009) Time series analysis of optical remote sensing data for the mapping of temporary surface water bodies in sub-Saharan western Africa. J Hydrol 370(1):52–63
Ivits E, Cherlet M, Sommer S, Mehl W (2013) Addressing the complexity in non-linear evolution of vegetation phenological change with time-series of remote sensing images. Ecol Ind 26:49–60
Jana A, Maiti S, Biswas A (2016) Seasonal change monitoring and mapping of coastal vegetation types along Midnapur-Balasore Coast, Bay of Bengal using multi-temporal landsat data Model. Earth Syst Environ 2:7. https://doi.org/10.1007/s40808-015-0062-x
Jeevalakshmi D, Reddy SN, Manikiam B (2016) Land cover classification based on NDVI using LANDSAT8 time series: a case study Tirupati region. In: Communication and Signal Processing (ICCSP), 2016 International Conference on IEEE, pp 1332–1335
Jia Y, Wu Z, Xu Y, Ke D, Su K (2017) Long Short-Term Memory Projection recurrent neural networkarchitectures for Piano’s continuous note recognition. J Robot
Jose E, Ryutaro T, Renchin T (2002) The polynomial least squares operation (PoLeS): a method for reducing noise in NDVI time series data. In: Proceedings of the 23rd Asian conference on remote sensing, section of data processing, algorithm and modelling, Kathmandu, Nepal
Kang L, Di L, Deng M, Yu E, Xu Y (2016) Forecasting vegetation index based on vegetation-meteorological factor interactions with artificial neural network. In: Agro-Geoinformatics (Agro-Geoinformatics), 2016 Fifth International Conference on IEEE, pp 1–6
Kennedy RE, Yang Z, Cohen WB (2010) Detecting trends in forest disturbance and recovery using yearly Landsat time series:1. LandTrendr—Temporal segmentation algorithms. Remote Sens Environ 114(12):2897–2910
Khorasani M, Ehteshami M, Ghadimi H et al (2016) Simulation and analysis of temporal changes of groundwater depth using time series modeling Model. Earth Syst Environ 2:90. https://doi.org/10.1007/s40808-016-0164-0
Kriminger E, Latchman H (2011) Markov chain model of homeplug CSMA MAC for determining optimal fixed contention window size. In: Power Line Communications and Its Applications (ISPLC), 2011 IEEE International Symposium on IEEE, pp 399–404
Lipton ZC, Berkowitz J, Elkan C (2015) A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019
Lyu H, Lu H, Mou L (2016) Learning a transferable change rule from a recurrent neural network for land cover change detection. Remote Sens 8(6):506
Maggiori E, Tarabalka Y, Charpiat G, Alliez P (2016). Fully convolutional neural networks for remote sensing image classification. In:Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International (pp 5071–5074). IEEE
Manobavan M, Lucas NS, Boyd DS, Petford N (2002) Forecasting the interannual trends in terrestrial vegetation dynamics using time series modelling techniques. ForestSAT Symposium Heriot Watt University
Mas JF, Flores JJ (2008) The application of artificial neural networks to the analysis of remotely sensed data. Int J Remote Sens 29(3):617–663
Mehal Z, Van Ryn L, Jess K, Hamilton (2009) http://www.psu.edu/dept/nkbiology/India/Great_Nicobar.pdf. Accessed on 22 Jan 2018
Miller DM, Kaminsky EJ, Rana S (1995) Neural network classification of remote-sensing data. Comput Geosci 21(3):377–386
Nay JJ, Burchfield E, Gilligan J (2016) A machine learning approach to forecasting remotely sensed vegetation health. arXiv preprint arXiv:1602.06335
Obitko M (1999) Prediction using neural networks. http://www.obitko.com/ tutorials/neural-network-prediction/introduction.html. Accessed 20 May 2017
Ordóñez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115
Peckham RJ, Gyozo J (2007) Digital terrain modelling. Springer, Berlin
Petitjean F, Inglada J, Gancarski P (2014) Assessing the quality of temporal high-resolution classifications with low-resolution satellite image time series. Int J Remote Sens 35(7):2693–2712
Porwal MC, Padalia H, Roy PS (2012) Impact of tsunami on the forest and biodiversity richness in Nicobar Islands (Andaman and Nicobar Islands), India. Biodivers Conserv 21(5):1267–1287
Prabakaran N, Paramasivam B (2015) Littoral forest composition and influence of soil characteristics on vegetation succession in the Tsunami impacted coastal habitats of Nicobar Islands, India. J Isl Ecol 1:1–17
Prasad PRC, Nagabhatla N, Reddy CS, Gupta S, Rajan KS, Raza SH, Dutt CBS (2009) Assessing forest canopy closure in a geospatial medium to address management concerns for tropical islands—Southeast Asia. Environ Monit Assess 160:541–553
Prasad PRC, Mamtha Lakshmi P, Rajan KS, Bhole V, Dutt CBS (2012) Tsunami and tropical Island ecosystems—a meta-analysis of the studies in Andaman and Nicobar Islands. Biodivers Conserv 21(2):309–322
Pratap K, Shelja (2013) Artificial Neural Network (ANN) inspired from biological nervous system. Int J Appl Innovation Eng Manag 2
Rembold F, Meroni M, Urbano F, Royer A, Atzberger C, Lemoine G, Haesen D (2015) Remote sensing time series analysis for crop monitoring with the spirits software:New functionalities and use examples. Front Environ Sci 3:46
Rußwurm M, Körner M (2017) Multi-temporal land cover classification with long short-term memory neural networks.International archives of the photogrammetry, remote sensing and spatial information sciences, p 42
Shimabukuro YE, Beuchle R, Grecchi RC, Achard F (2014) Assessment of forest degradation in Brazilian Amazon due to selective logging and fires using time series of fraction images derived from Landsat ETM + images. Remote Sens Lett 5(9):773–782
Silva PR, Acerbi Júnior FW, Carvalho LMTD., Scolforo JRS (2014) Use of artificial neural networks and geographic objects for classifying remote sensing imagery. Cerne 20(2):267–276
Singh (2011) Geography, Tata McGraw Hill Series. TataMcGraw-Hill Education, USA
Skymind (2016) A beginners guide to recurrent networks and LSTMs. http://deeplearning4j.org/lstm.html. Accessed 25 Oct 2016
Solutions HG (2013) Vegetation analysis: using vegetation indices in ENVI. http://www.harrisgeospatial.com/Learn/WhitepapersDetail/TabId/802/ArtMID/2627/ArticleID/13742/Vegetation-Analysis-Using-Vegetation-Indices-in-ENVI.aspx. Accessed 25 Oct 2016
Sridhar R, Thangaradjou T, Kannan L, Ramachandran A, Jayakumar S (2006) Rapid assessment on the impact of tsunami on mangrove vegetation of the Great Nicobar Island. J Indian Soc Remote Sens 34(1):89–93
Stepchenko A (2016) Ndvi index forecasting using a layer recurrent neural net-work coupled with stepwise regression and the pca. The 5th International Virtual Scientific Conference on Informatics and Management Sciences, pp 130–135
Stepchenko A, Chizhov J (2015a) Applying markov chains for NDVI time series forecasting of latvian regions. Inf Technol Manag Sci 18(1):57–61
Stepchenko A, Chizhov J (2015b) NDVI Short-Term Forecasting Using Recurrent Neural Networks. In Environment. Technology.Resources. Proceedings of the International Scientific and Practical Conference 3:180–185
Tulbure MG, Broich M (2013) Spatiotemporal dynamic of surface water bodies using Landsat time-series data from 1999 to 2011. ISPRS J Photogramm Remote Sens 79:44–52
Valtonen A, Molleman F, Chapman CA, Carey JR, Ayres MP, Roininen H (2013) Tropical phenology: Bi-annual rhythms and interannual variation in an Afrotropical butterfly assemblage. Ecosphere 4:36
Velmurugan A, Dam Roy S, Krishnan P, Swarnam TP, Jaisankar I, Singh AK, Biswas TK (2015) Climate change and Nicobar islands: impacts and adaptation strategies. J Andaman Sci Assoc 20(1):7–18
Verbesselt J, Hyndman R, Newnham G, Culvenor D (2010) Detecting trend and seasonal changes in satellite image time series. Remote Sens Environ 114:106–115
Viovy N, Arino O, Belward AS (1992) The Best Index Slope Extraction (BISE): a method for reducing noise in NDVI time-series. Int J Remote Sens 13(8):1585–1590
Vuolo F, Mattiuzzi M, Klisch A, Atzberger C (2012) Data service platform for MODIS Vegetation Indices time series processing at BOKU Vienna: current status and future perspectives. In: SPIE Remote Sensing. International Society for Optics and Photonics, 85380A-85380A
Wagh VM, Panaskar DB, Muley AA et al (2016) Prediction of groundwater suitability for irrigation using artificial neural network model: a case study of Nanded tehsil, Maharashtra, India Model. Earth Syst Environ 2:196. https://doi.org/10.1007/s40808-016-0250-3
Wang S, Yang B, Yang Q, Lu L, Wang X, Peng Y (2016) Temporal trends and spatial variability of vegetation phenology over the northern hemisphere during 1982–2012. PLoS One 11(6):e0157134. https://doi.org/10.1371/journal.pone.0157134
Wildml (2015) Recurrent neural networks tutorial, Part 3 Backpropagation Through Time And Vanishing Gradients. http://www.wildml.com/. Accessed 19 Oct 2016
Wu C-Y, Ahmed A, Beutel A, Smola AJ, Jing H (2017) Recurrent recommender networks. In: Proceedings of the tenth ACM international conference on web search and data mining, pp 495–503
Xu Y, Lili M, Ge L, Yunchuan C, Hao P, Zhi J (2015) Classifying relations via long short term memory networks along shortest dependency paths. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 1785–1794
Xue J, Su B (2017) Significant remote sensing vegetation indices: a review of developments and applications. J Sens, 2017
Zhang SL, Chang TC (2015) A study of image classification of remote sensing based on back-propagation neural network with extended delta bar delta. Math Problems Eng
Zhou L, Yang X (2008) Use of neural networks for land cover classification from remotely sensed imagery.the international archivesof the photogrammetry, remote sensing and spatial information sciences, p 37
Zhou GB, Wu J, Zhang CL, Zhou ZH (2016) Minimal gated unit for recurrent neural networks. Int J Autom Comput 13(3):226–234
Acknowledgements
We are thankful to University of Natural Resources and Life Sciences (BOKU), Vienna for providing us with the MODIS NDVI dataset for free. Also, grateful to anonymous reviewers for their constructive suggestions in revising the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Reddy, D.S., Prasad, P.R.C. Prediction of vegetation dynamics using NDVI time series data and LSTM. Model. Earth Syst. Environ. 4, 409–419 (2018). https://doi.org/10.1007/s40808-018-0431-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-018-0431-3