Spatio-Temporal Prediction of Vegetation Dynamics Based on Remote Sensing Data Using Deep Learning
Subject Areas : electrical and computer engineering
Elham Zangeneh
1
,
H. Mashayekhi
2
*
,
Saeed Gharachelo
3
1 -
2 - Shahrood University of Technology
3 -
Keywords: Deep learning, time series, remote sensing, vegetation index, sequence modeling,
Abstract :
Understanding and analyzing spatial-temporal data changes is very important in various applications, including the protection and development of natural resources. In the past studies, Markov process and comparison-based methods were mainly used to predict the changes of vegetation indices, whose accuracy still needs improvement. Although time series analysis has been used to predict some indices, the method to extract these indices from remote sensing data and model their sequences with deep learning is rarely observed. In this article, a method for predicting changes in plant indices based on deep learning is presented. The research data includes Landsat satellite images from 2000 to 2018, related to four seasons in the north and east of Shahrood city in Semnan province. The time span of the extracted images makes it possible to predict changes in vegetation cover. Vegetation indices extracted from the data set are NDVI, SAVI and RVI. After performing atmospheric corrections on the images, the desired indicators are extracted and then the data is converted into a time series. Finally, the modeling of the sequence of these data is performed by the Short-Long-Term Memory (LSTM) network. The results of the experiments show that the deep network is able to predict future values with high accuracy. The amount of the model error without additional data is 0.03 for the NDVI index, 0.02 for the SAVI index, and 0.06 for the RVI index.
[1] ع. شمسی‌پور، س. حیدری و ک. باقری، "پایش روند تغییرات پوشش زمین در شهر کرمانشاه با مدل CA مارکوف،" پژوهش‌های جغرافیایی برنامه‌ریزی شهری، جلد 5، شماره 3، صص. 495-514، پاييز ۱۳۹۶.
[2] ع. کاظمی‌نیا، "کاربرد سنجش از دور در بررسی پوشش گیاهی،" نشریه علمی- ترویجی مهندسی نقشه‌برداری و اطلاعات مکانی، جلد 9، شماره 1، صص. 75-85، بهمن ۱۳۹۶.
[3] Q. Zhuang, S. Wu, X. Feng, and Y. Niu, "Analysis and prediction of vegetation dynamics under the background of climate change in Xinjiang, China," Peer J. Computer Science, vol. 23, no. 8, Article ID: 8282. 2020.
[4] K. Nataliia, M. Lavreniuk, S. Skakun, and A. Shelestov, "Deep learning classification of land cover and crop types using remote sensing data," IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, pp. 778-782, May 2017.
[5] O. H. Adedeji, O. O. Tope-Ajayi, and O. L. Abegunde, "Assessing and predicting changes in the status of Gambari forest reserve, Nigeria using remote sensing and GIS techniques," J. of Geographic Information System, vol. 7, no. 3, Article ID: 57588, Jun. 2015.
[6] J. Xue and S. Baofeng, "Significant remote sensing vegetation indices: a review of developments and applications," J. of Sensors, vol. 5, no. 6, pp. 1353691, 2017.
[7] F. Petitjean, J. Inglada, and P. Gancarski, "Assessing the quality of temporal high-resolution classifications with low-resolution satellite image time series," International J. of Remote Sensing, vol. 35, no. 7, pp. 2693-2712, 2014.
[8] A. Calera, C. Martínez, and J. Melia, "A procedure for obtaining green plant cover: relation to NDVI in a case study for barley," International J. of Remote Sensing, vol. 22, no. 17, pp. 3357-3362, 2001.
[9] W. B. Cohen, T. K. Maiersperger, S. Gower, and D. Turner, "An improved strategy for regression of biophysical variables and Landsat ETM + data," Remote Sensing of Environment, vol. 84, no. 4, pp. 561-571, Apr. 2003.
[10] H. C. Gurgel and N. J. Ferreira, "Annual and interannual variability of NDVI in Brazil and its connections with climate," International J. of Remote Sensing, vol. 24, no. 18, pp. 3595-3609, 2003.
[11] S. Z. Hosseini, M. Kappas, and P. Propastin, "Estimating relationship between vegetation dynamic and precipitation in central Iran," in Proc. Int. SWAT Conf.,6 pp., Toledo, Spain, 15-17 Jul. 2011.
[12] J. J. Arsanjani, M. Helbich, W. Kainz, and A. D. Boloorani, "Integration of logistic regression, Markov chain and cellular automata models to simulate urban expansion," International J. of Applied Earth Observation and Geoinformation, vol. 1, no. 21, pp. 265-275, Apr. 2013.
[13] ب. فرخ‌زاد، ش. منصوری و ع. سپهری، "بررسی همبستگی بین شاخص‌های پوشش گیاهی NDVI و EVI با شاخص خشک‌سالی هواشناسی SPI (مطالعه موردی: مراتع استان گلستان)،" هواشناسی کشاورزی، جلد 5، شماره 2، صص. 56-65، پاييز و زمستان 1396.
[14] A. Stepchenko and J. Chizhov, "NDVI short-term forecasting using recurrent neural networks," in Proc. of the 10th Int. Scientific and Practical Conf., vol. 3, pp. 180-185, Rēzekne, Latvija, 18-20 Jun. 2015.
[15] A. Stepchenko, "NDVI index forecasting using a layer recurrent neural network coupled with stepwise regression and the PCA," in Proc. 5th Int. Virtual Scientific Conf. on Informatics and Management Sciences, vol. 5, pp. 130-135, Zilina, Slovakia, 24-25 Apr. 2016.
[16] A. Stepchenko and J. Chizhov, "Applying markov chains for NDVI time series forecasting of Latvian regions," Information Technology and Management Science, vol. 18, no. 1, pp. 57-61, 2015.
[17] E. Kriminger and H. Latchman, "Markov chain model of home-plug CSMA MAC for determining optimal fixed contention window size," in Proc. of the IEEE Int. Symp. on Power Line Communications and Its Applications ISPLC'11, pp. 399-404, Udine, Italy, 3-6 Apr. 2011.
[18] T. Wu, F. Feng, Q. Lin, and H. Bai, "A spatio-temporal prediction of NDVI based on precipitation: an application for grazing management in the arid and semi-arid grasslands," International J. of Remote Sensing, vol. 41, no. 6, pp. 2359-2373, 2020.
[19] P. M. Atkinson and A. R. L. Tatnall, "Introduction neural networks in remote sensing," International J. of Remote Sensing, vol. 18, no. 4, pp. 699-709, 1997.
[20] T. S. Wu, H. P. Fu, G. Jin, H. F. Wu, and H. M. Bai, "Prediction of the livestock carrying capacity using neural network in the meadow steppe," The Rangeland J., vol. 41, no. 1, pp. 65-72, 2019.
[21] A. Stepchenko and J. Chizhov, "Applying Markov chain for NDVI time series for Latvian regions," Information Technology Managements Science, vol. 18, no. 1, pp. 57-61, 2015.
[22] Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 157-166, Mar. 1994.
[23] P. R. Silva, F. W. Acerbi Júnior, L. M. T. de Carvalho, and J. R. S. Scolforo, "Use of artificial neural networks and geographic objects for classifying remote sensing imagery," CERNE J., vol. 20, no. 2, pp. 267-276, Apr. 2014.
[24] D. S. Reddy and P. R. C. Prasad, "Prediction of vegetation dynamics using NDVI time series data and LSTM," Modeling Earth Systems and Environment, vol. 4, pp. 409-419, 018.
[25] D. Phiri and J. Morgenroth, "Developments in Landsat land cover classification methods: a review," International of Remote Sensing, vol. 9, no. 9, Article ID: 967, 2017.
[26] Z. Chen, W. G. Jiang, Z. H. Tang, and K. Jia, "Spatial-temporal pattern of vegetation index change and the relationship to land surface temperature in Zoige," International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B3, pp. 849-852, Jun. 2016.
[27] E. Y. Liang, X. M. Shao, and J. C. He, "Relationships between tree growth and NDVI of grassland in the semiarid grassland of north China," International J. of Remote Sensing, vol. 26, no. 13, pp. 2901-2908, 2005.
[28] A. Graves, Supervised Sequence Labelling with Recurrent Neural Networks, Springer, Berlin-Heidelberg, 2012.
[29] F. A. Gers and J. Schmidhuber, "Recurrent nets that time and count," in Proc. of the IEEE-INNS-ENNS Int. Joint Conf. on Neural Networks, IJCNN'00, 5 pp., Como, Italy, 27-27 Jul. 2000.
[30] ز. پرور و ک. شایسته، "پیش‌بینی روند تغییرات و توسعه شهری با استفاده از تصاویر ماهواره‌ای چندزمانه و سیستم اطلاعات جغرافیایی (مطالعه موردی: شهر بجنورد)،" محیط‌شناسی، جلد 43، شماره 3، صص. 513-527، 1396.
[31] T. Wu, F. Feng, Q. Lin, and H. Bai, "A spatio-temporal prediction of NDVI based on precipitation: an application for grazing management in the arid and semi-arid grasslands," International J. of Remote Sensing, vol. 41, no. 6, pp. 2359-2373, 2020.