A Machine Learning Approach for Remote Sensing Data Gap-Filling with Open-Source Implementation: An Example Regarding Land Surface Temperature, Surface Albedo and NDVI
"> Figure 1
<p>Scheme for creating a training sample. To restore the gap in pixel d<sub>1</sub>, based on previous images a training sample is generated for the machine learning algorithm. Predictors for the temperature value in the image for 3 September 2019 in pixel d<sub>1</sub> are pixels with known values a<sub>1</sub>, b<sub>1</sub>, c<sub>1</sub>.</p> "> Figure 2
<p>Biomes matrix from Sentinel-3 land surface temperature (LST) scene and temperature distribution in the image by biomes. The image on the left shows a matrix with land types, which was obtained from the archive with additional matrices for LST data (Sentinel-3 SLSTR). The matrix covers an area with a size of 3 degrees latitude per 3 degrees longitude. On the right is a kernel estimation of the density distribution of the LST in different biomes in this matrix.</p> "> Figure 3
<p>Demonstration of the principle of operation of the local time series approximation algorithm for filling in the gaps. For each gap element, the coefficients of the polynomial function are estimated from the neighborhood of the 5 known values closest to the gap in the time series. The degree of the polynomial is 2.</p> "> Figure 4
<p>Shaded pixels detection; (<b>a</b>) original cloud configuration, (<b>b</b>) the area selected by the algorithm.</p> "> Figure 5
<p>Results of applying gapfilling algorithm for Sentinel-3 LST Vladivostok case (Gap size 50%); (<b>a</b>) source matrix, (<b>b</b>) imitation of the gap, (<b>c</b>) output matrix.</p> "> Figure 6
<p>Vladivostok case. Distribution of temperature in the original image and in the image reconstructed by the model. (<b>a</b>) matrix with gap, (<b>b</b>) reconstructed matrix.</p> "> Figure 7
<p>Vladivostok case with LST data. Biplots with a comparison of actual and predicted values <b>(top row</b>) and a field of calculated bias (<b>bottom row</b>).</p> "> Figure 8
<p>Results of model verification on six different-time images of the Sentinel-3 LST product (Saint Petersburg case).</p> "> Figure 9
<p>The dependence of the mean absolute error (MAE) on the gap size and the amplitude of the temperature in the gap; (<b>a</b>) Saint Petersburg case, (<b>b</b>) Madrid case, (<b>c</b>) Vladivostok case. Indent shows the standard error.</p> "> Figure 10
<p>Results of model verification on normalized difference vegetation index (NDVI) data for three territories: (<b>a</b>) Saint Petersburg case, (<b>b</b>) Madrid case, (<b>c</b>) Vladivostok case.</p> "> Figure 11
<p>Comparison of gapfilling algorithms by root mean squared error (RMSE) on LST data for Madrid case.</p> "> Figure 12
<p>Diagram of the implemented module.</p> "> Figure 13
<p>Time complexity for the gap-filling algorithm (the average image size was 8500 pixels and train sample contains 250–350 layers). Indent shows the standard error.</p> ">
Abstract
:1. Introduction
- Using time series analysis to fill in gaps;
- Using spatial information to fill in gaps;
- Using spatio-temporal analysis.
2. Materials and Methods
2.1. Proposed Approach
Algorithm 1: Pseudocode of the algorithm for restoring gaps in time series using iterative approximation by polynomial functions |
Data: array_with_gaps; n = degree of a polynomial function; k = the number of known elements for evaluating the coefficients of the polynomial; Result: array without gaps gaps ← all gap elements in array_with_gaps for gap in gaps do |
- from 0.459 to 0.479 m;
- from 0.545 to 0.565 m;
- from 1.230 to 1.250 m;
- from 2.105 to 2.155 m.
2.2. Experimental Studies
- “Saint Petersburg”: 30–31°E, 58–59°N;
- “Madrid”: 5–4°W, 39–40°N;
- “Vladivostok”: 132–133°E, 44–45°N;
3. Results
3.1. Validation of the Algorithm on LST Data
3.2. Validation of the Algorithm on NDVI and Albedo Data
- “Saint Petersburg”: 1 NDVI image and 1 albedo image for 5th of June 2019;
- “Madrid”: 1 NDVI image and 1 albedo image for 3rd of September 2019;
- “Vladivostok”: 1 NDVI image and 1 albedo image for 15th of September 2019.
3.3. Comparison with “CRAN Gapfill” and “Gapfilling Rasters”
3.4. Software Implementation
4. Discussion
4.1. Accuracy of Data Recovery
4.2. Applications for Different Remote Sensing Products
4.3. Limitations
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
Abbreviations
LST | Land Surface Temperature |
NDVI | Normalized Difference Vegetation Index |
SLSTR | The Sea and Land Surface Temperature Radiometer |
MODIS | Moderate Resolution Imaging Spectroradiometer |
RMSE | Root Mean Squared Error |
MAE | Mean Absolute Error |
MedAE | Median Absolute Error |
SSGP-toolbox | Simple Spatial Gapfilling Processor toolbox |
References
- Goyal, M.K.; Sharma, A.; Surampalli, R.Y. Remote Sensing and GIS Applications in Sustainability. In Sustainability; John Wiley & Sons, Ltd.: Hoboken, NJ, USA, 2020; Chapter 28; pp. 605–626. [Google Scholar]
- Patino, J.E.; Duque, J.C. A review of regional science applications of satellite remote sensing in urban settings. Comput. Environ. Urban Syst. 2013, 37, 1–17. [Google Scholar] [CrossRef]
- He, M.; Hu, Y.; Chen, N.; Wang, D.; Huang, J.; Stamnes, K. High cloud coverage over melted areas dominates the impact of clouds on the albedo feedback in the Arctic. Sci. Rep. 2019, 9, 1–11. [Google Scholar] [CrossRef] [PubMed]
- Wolfe, R.E.; Roy, D.P.; Vermote, E. MODIS land data storage, gridding, and compositing methodology: Level 2 grid. IEEE Trans. Geosci. Remote Sens. 1998, 36, 1324–1338. [Google Scholar] [CrossRef] [Green Version]
- Wang, K.; Franklin, S.E.; Guo, X.; Cattet, M. Remote sensing of ecology, biodiversity and conservation: A review from the perspective of remote sensing specialists. Sensors 2010, 10, 9647–9667. [Google Scholar] [CrossRef] [PubMed]
- Schmugge, T.J.; Kustas, W.P.; Ritchie, J.C.; Jackson, T.J.; Rango, A. Remote sensing in hydrology. Adv. Water Resour. 2002, 25, 1367–1385. [Google Scholar] [CrossRef]
- Tomlinson, C.J.; Chapman, L.; Thornes, J.E.; Baker, C. Remote sensing land surface temperature for meteorology and climatology: A review. Meteorol. Appl. 2011, 18, 296–306. [Google Scholar] [CrossRef] [Green Version]
- Gupta, R.P. Remote Sensing Geology; Springer: Berlin/Heidelberg, Germany, 2017. [Google Scholar]
- Sun, L.; Chen, Z.; Gao, F.; Anderson, M.; Song, L.; Wang, L.; Hu, B.; Yang, Y. Reconstructing daily clear-sky land surface temperature for cloudy regions from MODIS data. Comput. Geosci. 2017, 105, 10–20. [Google Scholar] [CrossRef]
- Zhang, X.; JiZhou, S.L.; Chai, L.; Wang, D.; Liu, J. Estimation of 1-km all-weather remotely sensed land surface temperature based on reconstructed spatial-seamless satellite passive microwave brightness temperature and thermal infrared data. ISPRS J. Photogramm. Remote Sens. 2020, 167, 321–344. [Google Scholar] [CrossRef]
- Dumitrescu, A.; Brabec, M.; Cheval, S. Statistical Gap-Filling of SEVIRI Land Surface Temperature. Remote Sens. 2020, 12, 1423. [Google Scholar] [CrossRef]
- Koch, J.; Siemann, A.; Stisen, S.; Sheffield, J. Spatial validation of large-scale land surface models against monthly land surface temperature patterns using innovative performance metrics. J. Geophys. Res. Atmos. 2016, 121, 5430–5452. [Google Scholar] [CrossRef]
- Salomonson, V.V.; Barnes, W.; Maymon, P.W.; Montgomery, H.E.; Ostrow, H. MODIS: Advanced facility instrument for studies of the Earth as a system. IEEE Trans. Geosci. Remote Sens. 1989, 27, 145–153. [Google Scholar] [CrossRef]
- Coppo, P.; Ricciarelli, B.; Brandani, F.; Delderfield, J.; Ferlet, M.; Mutlow, C.; Munro, G.; Nightingale, T.; Smith, D.; Bianchi, S.; et al. SLSTR: A high accuracy dual scan temperature radiometer for sea and land surface monitoring from space. J. Mod. Opt. 2010, 57, 1815–1830. [Google Scholar] [CrossRef]
- Dickinson, R.E. Land surface processes and climate—Surface albedos and energy balance. In Advances in Geophysics; Elsevier: Amsterdam, The Netherlands, 1983; Volume 25, pp. 305–353. [Google Scholar]
- Bannari, A.; Morin, D.; Bonn, F.; Huete, A. A review of vegetation indices. Remote Sens. Rev. 1995, 13, 95–120. [Google Scholar] [CrossRef]
- Körner, P.; Kronenberg, R.; Genzel, S.; Bernhofer, C. Introducing Gradient Boosting as a universal gap filling tool for meteorological time series. Meteorol. Z. 2018, 27, 369–376. [Google Scholar] [CrossRef]
- Hippert-Ferrer, A.; Yan, Y.; Bolon, P. EM-EOF: Gap-Filling in Incomplete SAR Displacement Time Series. IEEE Trans. Geosci. Remote. Sens. 2020, 1–18. [Google Scholar] [CrossRef]
- Hou, J.; Huang, C.; Zhang, Y.; Guo, J.; Gu, J. Gap-filling of MODIS fractional snow cover products via non-local spatio-temporal filtering based on machine learning techniques. Remote Sens. 2019, 11, 90. [Google Scholar] [CrossRef] [Green Version]
- Gerber, F.; de Jong, R.; Schaepman, M.E.; Schaepman-Strub, G.; Furrer, R. Predicting missing values in spatio-temporal remote sensing data. IEEE Trans. Geosci. Remote Sens. 2018, 56, 2841–2853. [Google Scholar] [CrossRef] [Green Version]
- Maxwell, S.; Schmidt, G.L.; Storey, J.C. A multi-scale segmentation approach to filling gaps in Landsat ETM+ SLC-off images. Int. J. Remote Sens. 2007, 28, 5339–5356. [Google Scholar] [CrossRef]
- Romero-Sanchez, M.E.; Ponce-Hernandez, R.; Franklin, S.E.; Aguirre-Salado, C.A. Comparison of data gap-filling methods for Landsat ETM+ SLC-off imagery for monitoring forest degradation in a semi-deciduous tropical forest in Mexico. Int. J. Remote Sens. 2015, 36, 2786–2799. [Google Scholar] [CrossRef]
- Chen, J.; Zhu, X.; Vogelmann, J.E.; Gao, F.; Jin, S. A simple and effective method for filling gaps in Landsat ETM+ SLC-off images. Remote Sens. Environ. 2011, 115, 1053–1064. [Google Scholar] [CrossRef]
- Zhu, X.; Liu, D.; Chen, J. A new geostatistical approach for filling gaps in Landsat ETM+ SLC-off images. Remote Sens. Environ. 2012, 124, 49–60. [Google Scholar] [CrossRef]
- Stock, A.; Subramaniam, A.; Van Dijken, G.L.; Wedding, L.M.; Arrigo, K.R.; Mills, M.M.; Cameron, M.A.; Michell, F. Comparison of Cloud-Filling Algorithms for Marine Satellite Data. Remote Sens. 2020, 12, 3313. [Google Scholar] [CrossRef]
- Liu, X.; Wang, M. Gap Filling of Missing Data for VIIRS Global Ocean Color Products Using the DINEOF Method. IEEE Trans. Geosci. Remote Sens. 2018, 56, 4464–4476. [Google Scholar] [CrossRef]
- Slot, K.; Komatowski, L. Fast generation of natural textures with Cellular Neural Networks-based stitching. In Proceedings of the 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA), Berkeley, CA, USA, 3–5 February 2010; pp. 1–4. [Google Scholar]
- Zhang, Q.; Yuan, Q.; Zeng, C.; Li, X.; Wei, Y. Missing data reconstruction in remote sensing image with a unified spatial–temporal–spectral deep convolutional neural network. IEEE Trans. Geosci. Remote Sens. 2018, 56, 4274–4288. [Google Scholar] [CrossRef] [Green Version]
- Cresson, R.; Ienco, D.; Gaetano, R.; Ose, K.; Minh, D.H.T. Optical image gap filling using deep convolutional autoencoder from optical and radar images. In Proceedings of the IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 28 July–2 August 2019; pp. 218–221. [Google Scholar]
- Cui, Y.; Ma, S.; Yao, Z.; Chen, X.; Luo, Z.; Fan, W.; Hong, Y. Developing a Gap-Filling Algorithm Using DNN for the Ts-VI Triangle Model to Obtain Temporally Continuous Daily Actual Evapotranspiration in an Arid Area of China. Remote Sens. 2020, 12, 1121. [Google Scholar] [CrossRef] [Green Version]
- Weiss, D.J.; Atkinson, P.M.; Bhatt, S.; Mappin, B.; Hay, S.I.; Gething, P.W. An effective approach for gap-filling continental scale remotely sensed time-series. ISPRS J. Photogramm. Remote Sens. 2014, 98, 106–118. [Google Scholar] [CrossRef] [Green Version]
- Roerink, G.; Menenti, M.; Verhoef, W. Reconstructing cloudfree NDVI composites using Fourier analysis of time series. Int. J. Remote Sens. 2000, 21, 1911–1917. [Google Scholar] [CrossRef]
- Yang, Y.; Luo, J.; Huang, Q.; Wu, W.; Sun, Y. Weighted double-logistic function fitting method for reconstructing the high-quality sentinel-2 NDVI time series data set. Remote Sens. 2019, 11, 2342. [Google Scholar] [CrossRef] [Green Version]
- Julien, Y.; Sobrino, J.A. Optimizing and comparing gap-filling techniques using simulated NDVI time series from remotely sensed global data. Int. J. Appl. Earth Obs. Geoinf. 2019, 76, 93–111. [Google Scholar] [CrossRef]
- Singh, R. Interpolation of data gaps of SLC-off Landsat ETM+ images using algorithm based on the differential operators. J. Appl. Comput. Sci. Methods 2014, 6, 93–100. [Google Scholar] [CrossRef]
- Zhang, C.; Li, W.; Civco, D. Application of geographically weighted regression to fill gaps in SLC-off Landsat ETM+ satellite imagery. Int. J. Remote Sens. 2014, 35, 7650–7672. [Google Scholar] [CrossRef]
- Llamas, R.M.; Guevara, M.; Rorabaugh, D.; Taufer, M.; Vargas, R. Spatial Gap-Filling of ESA CCI Satellite-Derived Soil Moisture Based on Geostatistical Techniques and Multiple Regression. Remote Sens. 2020, 12, 665. [Google Scholar] [CrossRef] [Green Version]
- Scaramuzza, P.; Micijevic, E.; Chander, G. SLC gap-filled products phase one methodology. Landsat Tech. Notes 2004, 5, 1–5. [Google Scholar]
- Shen, H.; Wu, J.; Cheng, Q.; Aihemaiti, M.; Zhang, C.; Li, Z. A Spatiotemporal Fusion Based Cloud Removal Method for Remote Sensing Images With Land Cover Changes. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2019, 12, 862–874. [Google Scholar] [CrossRef]
- Belgiu, M.; Stein, A. Spatiotemporal Image Fusion in Remote Sensing. Remote Sens. 2019, 11, 818. [Google Scholar] [CrossRef] [Green Version]
- Kang, S.; Running, S.W.; Zhao, M.; Kimball, J.S.; Glassy, J. Improving continuity of MODIS terrestrial photosynthesis products using an interpolation scheme for cloudy pixels. Int. J. Remote Sens. 2005, 26, 1659–1676. [Google Scholar] [CrossRef]
- Poggio, L.; Gimona, A.; Brown, I. Spatio-temporal MODIS EVI gap filling under cloud cover: An example in Scotland. ISPRS J. Photogramm. Remote Sens. 2012, 72, 56–72. [Google Scholar] [CrossRef]
- Gafurov, A.; Bárdossy, A. Cloud removal methodology from MODIS snow cover product. Hydrol. Earth Syst. Sci. 2009, 13, 1361–1373. [Google Scholar] [CrossRef] [Green Version]
- Jönsson, P.; Eklundh, L. TIMESAT—A program for analyzing time-series of satellite sensor data. Comput. Geosci. 2004, 30, 833–845. [Google Scholar] [CrossRef] [Green Version]
- Siabi, N.; Sanaeinejad, S.H.; Ghahraman, B. Comprehensive evaluation of a spatio-temporal gap filling algorithm: Using remotely sensed precipitation, LST and ET data. J. Environ. Manag. 2020, 261, 110228. [Google Scholar] [CrossRef]
- Heaton, M.J.; Datta, A.; Finley, A.; Furrer, R.; Guhaniyogi, R.; Gerber, F.; Gramacy, R.B.; Hammerling, D.; Katzfuss, M.; Lindgren, F.; et al. Methods for Analyzing Large Spatial Data: A Review and Comparison. arXiv 2017, arXiv:171005013. [Google Scholar]
- Lindgren, F.; Rue, H.; Lindström, J. An explicit link between Gaussian fields and Gaussian Markov random fields: The stochastic partial differential equation approach. J. R. Stat. Soc. Ser. B Stat. Methodol. 2011, 73, 423–498. [Google Scholar] [CrossRef] [Green Version]
- Finley, A.O.; Datta, A.; Cook, B.C.; Morton, D.C.; Andersen, H.E.; Banerjee, S. Efficient algorithms for Bayesian Nearest Neighbor Gaussian Processes. 2018. Available online: https://arxiv.org/abs/1702.00434 (accessed on 24 November 2020).
- Nychka, D.; Bandyopadhyay, S.; Hammerling, D.; Lindgren, F.; Sain, S. A multiresolution Gaussian process model for the analysis of large spatial datasets. J. Comput. Graph. Stat. 2015, 24, 579–599. [Google Scholar] [CrossRef] [Green Version]
- Katzfuss, M. A Multi-Resolution Approximation for Massive Spatial Datasets. J. Am. Stat. Assoc. 2017, 112, 201–214. [Google Scholar] [CrossRef] [Green Version]
- Chen, S.; Wang, X.; Guo, H.; Xie, P.; Sirelkhatim, A.M. Spatial and Temporal Adaptive Gap-Filling Method Producing Daily Cloud-Free NDSI Time Series. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 2251–2263. [Google Scholar] [CrossRef]
- Moreno-Martinez, A.; Izquierdo-Verdiguier, E.; Maneta, P.M.; Camps-Valls, G.; Robinson, N.; Munoz-Marí, J.; Sedano, F.; Clinton, N.; Runningb, S.W. Multispectral high resolution sensor fusion for smoothing and gap-filling in the cloud. Remote Sens. Environ. 2020, 247, 111901. [Google Scholar] [CrossRef]
- Kang, M.; Ichii, K.; Kim, J.; Indrawati, Y.; Park, J.; Moon, M.; Lim, J.H.; Chun, J.H. New Gap-Filling Strategies for Long-Period Flux Data Gaps Using a Data-Driven Approach. Atmosphere 2019, 10, 568. [Google Scholar] [CrossRef] [Green Version]
- Kalyuzhnaya, A.V.; Nikitin, N.O.; Vychuzhanin, P.; Hvatov, A.; Boukhanovsky, A. Automatic evolutionary learning of composite models with knowledge enrichment. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, Cancún, Mexico, 8–12 July 2020; pp. 43–44. [Google Scholar]
- Plotnikov, D.; Miklashevich, T.; Bartalev, S. Using local polynomial approximation within moving window for remote sensing data time-series smoothing and data gaps recovery. Sovrem. Probl. Distantsionnogo Zondirovaniya Zemli Iz Kosmosa 2014, 11, 103–110. [Google Scholar]
- Wolfram, S. Statistical mechanics of cellular automata. Rev. Mod. Phys. 1983, 55, 601. [Google Scholar] [CrossRef]
- Liang, S. Narrowband to broadband conversions of land surface albedo I Algorithms. Remote Sens. Environ. 2000, 76, 213–238. [Google Scholar] [CrossRef]
Territory | Sentinel-3 LST | MOD11A1 | MOD11_L2 | ||||||
---|---|---|---|---|---|---|---|---|---|
MAE | RMSE | MedAE | MAE | RMSE | MedAE | MAE | RMSE | MedAE | |
Saint Petersburg | 11% | 16% | 8% | 4% | 5% | 3% | 6% | 9% | 5% |
Madrid | 8% | 10% | 7% | 5% | 6% | 4% | 6% | 8% | 5% |
Vladivostok | 5% | 7% | 4% | 5% | 7% | 4% | 8% | 11% | 6% |
Case (NDVI) | Gap Area, % | MAE | RMSE | MedAE | Amplitude |
---|---|---|---|---|---|
Saint Petersburg | 52 | 0.053 | 0.085 | 0.030 | 1.212 |
Madrid | 50 | 0.028 | 0.053 | 0.016 | 1.128 |
Vladivostok | 50 | 0.037 | 0.059 | 0.025 | 1.491 |
Case (Albedo) | Gap Area, % | MAE | RMSE | MedAE | Amplitude |
Saint Petersburg | 52 | 0.018 | 0.032 | 0.011 | 0.328 |
Madrid | 50 | 0.013 | 0.025 | 0.009 | 0.536 |
Vladivostok | 50 | 0.011 | 0.017 | 0.007 | 0.228 |
Algorithm | Gap Size (Saint Petersburg Case) | ||||||||
---|---|---|---|---|---|---|---|---|---|
4% | 6% | 15% | 28% | 40% | 52% | 70% | 96% | Mean | |
SSGP-toolbox | 0.42 | 0.42 | 0.35 | 0.39 | 0.43 | 0.48 | 0.47 | 0.87 | 0.48 |
CRAN gapfill | 0.8 | 1.28 | 0.94 | 0.99 | 1.31 | 0.98 | 1.08 | 1.07 | 1.06 |
gapfilling rasters | 0.61 | 0.73 | 0.96 | 0.88 | 0.86 | 0.54 | 0.82 | 0.80 | 0.78 |
Nearest neighbour interpolation | 0.59 | 0.68 | 0.55 | 1.10 | 1.12 | 1.02 | 1.00 | 1.22 | 0.91 |
Algorithm | Gap Size (Madrid Case) | ||||||||
5% | 8% | 17% | 29% | 39% | 50% | 78% | 94% | Mean | |
SSGP-toolbox | 0.53 | 0.89 | 0.76 | 0.79 | 0.69 | 0.84 | 1.04 | 0.97 | 0.81 |
CRAN gapfill | 1.03 | 1.19 | 1.39 | 1.17 | 1.11 | 1.19 | 1.32 | 1.42 | 1.23 |
gapfilling rasters | 1.37 | 1.70 | 1.56 | 1.57 | 1.76 | 2.15 | 2.66 | 2.94 | 1.96 |
Nearest neighbour interpolation | 1.26 | 1.74 | 1.41 | 1.91 | 1.75 | 2.20 | 2.90 | 2.77 | 1.99 |
Algorithm | Gap Size (Vladivostok Case) | ||||||||
5% | 10% | 15% | 28% | 44% | 50% | 74% | 93% | Mean | |
SSGP-toolbox | 0.30 | 0.31 | 0.36 | 0.32 | 0.47 | 0.36 | 0.50 | 0.68 | 0.41 |
CRAN gapfill | 0.47 | 0.36 | 0.58 | 0.43 | 0.59 | 0.55 | 0.84 | 0.73 | 0.57 |
gapfilling rasters | 0.67 | 0.63 | 0.66 | 0.72 | 0.77 | 0.81 | 0.85 | 1.24 | 0.79 |
Nearest neighbour interpolation | 0.40 | 0.43 | 0.44 | 0.47 | 0.53 | 0.56 | 0.90 | 1.01 | 0.59 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sarafanov, M.; Kazakov, E.; Nikitin, N.O.; Kalyuzhnaya, A.V. A Machine Learning Approach for Remote Sensing Data Gap-Filling with Open-Source Implementation: An Example Regarding Land Surface Temperature, Surface Albedo and NDVI. Remote Sens. 2020, 12, 3865. https://doi.org/10.3390/rs12233865
Sarafanov M, Kazakov E, Nikitin NO, Kalyuzhnaya AV. A Machine Learning Approach for Remote Sensing Data Gap-Filling with Open-Source Implementation: An Example Regarding Land Surface Temperature, Surface Albedo and NDVI. Remote Sensing. 2020; 12(23):3865. https://doi.org/10.3390/rs12233865
Chicago/Turabian StyleSarafanov, Mikhail, Eduard Kazakov, Nikolay O. Nikitin, and Anna V. Kalyuzhnaya. 2020. "A Machine Learning Approach for Remote Sensing Data Gap-Filling with Open-Source Implementation: An Example Regarding Land Surface Temperature, Surface Albedo and NDVI" Remote Sensing 12, no. 23: 3865. https://doi.org/10.3390/rs12233865