Abstract
Comprehensive land cover information is valuable in complex land cover mapping. Optical satellite data play an essential role for monitoring dynamic land surface processes in a timely manner. Sentinel-2A is one of the advancements in optical satellite data possessing multi-spectral imaging and high resolution which supports the monitoring of distinct land cover classes. The fair selection of appropriate input features, which may be as important as the choice of data and classifier, is another ongoing study area in addition to the progress of classification algorithms. In the past studies, the role of distinct features like MSI bands, spectral indices, GLCM (gray-level co-occurrence matrix) features and Gabor features have been analyzed individually and each of the feature set have shown their own significance, but the value proposition of all these features collectively in land cover mapping still needs to be explored. For satellite image classification, distinct machine learning algorithms have already been explored and current trend has shifted towards deep learning. But owing to deep learning models’ computationally expensive nature, requirement of expert knowledge, and abundance training data, machine learning techniques are preferred choices due to their lower computational complexity and higher interpretability capabilities compared to deep learning models. Hence, in this work, Sentinel-2A data-based land cover mapping has been executed by utilizing random forest (RF) classifier. Different feature sets have been composed and evaluated for achieving the maximum mapping accuracy. The best feature set has been selected for the classification model. The RF hyper-parameters have also been optimized using Bayesian optimization to achieve the best classification accuracy. The developed land cover mapping model has been applied on a four-year time series data (2018–2021) of Roorkee region of Uttarakhand, to explore the changes appeared in the past four years in distinct land cover classes.
Similar content being viewed by others
References
Kavzoglu T, Mather PM. The use of backpropagating artificial neural networks in land cover classification. Int J Remote Sens. 2003;24(23):4907–38.
Kadavi PR, Lee C-W. Land cover classification analysis of volcanic island in Aleutian Arc using an artificial neural network (ANN) and a support vector machine (SVM) from Landsat imagery. Geosci J. 2018;22(4):653–65.
Zhang C, et al. A multi-level context-guided classification method with object-based convolutional neural network for land cover classification using very high resolution remote sensing images. Int J Appl Earth Observ Geoinform. 2020;88:102086.
Singh A, Singh KK. Satellite image classification using Genetic Algorithm trained radial basis function neural network, application to the detection of flooded areas. J Vis Commun Image Represent. 2017;42:173–82.
Chen W, Li X, Wang L. Fine land cover classification in an open pit mining area using optimized support vector machine and worldview-3 imagery. Remote Sensing. 2020;12(1):82.
Huang C, Davis LS, Townshend JRG. An assessment of support vector machines for land cover classification. Int J Rem Sens. 2002;23(4):725–49.
Liu Y, Huang L. A novel ensemble support vector machine model for land cover classification. Int J Distrib Sens Netw. 2019;15(4):1550147719842732.
Phan TN, Kappas M. Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery. Sensors. 2018;18(1):18.
Khosravi I, et al. Enhanced decision tree ensembles for land-cover mapping from fully polarimetric SAR data. Int J Rem Sens. 2017;38(23):7138–60.
Yang C, et al. Improving land use/land cover classification by integrating pixel unmixing and decision tree methods. Rem Sens. 2017;9(12):1222.
Sohn Y, Morán E, Gurri F. Deforestation in North-Central Yucatan (1985–1995)- Mapping secondary succession of forest and agricultural land use in Sotuta using the cosine of the angle concept. Photogramm Eng Remote Sens. 1999;65:947–58.
Sohn Y, Sanjay Rebello N. Supervised and unsupervised spectral angle classifiers. Photogramm Eng Rem Sens. 2002;68(12):1271–82.
Dymova L, Sevastianov P, Bartosiewicz P. A new approach to the rule-base evidential reasoning: Stock trading expert system application. Expert Syst Appl. 2010;37(8):5564–76.
Yang J-B, et al. Belief rule-base inference methodology using the evidential reasoning approach-RIMER. IEEE Transact Syst Man Cyber -Part A Syst Humans. 2006;36(2):266–85.
Gupta S, Singh D, Kumar S. Fusion of texture and wavelet features of PALSAR image using LDA and PCA for land cover classification. Int J Image Data Fusion. 2017;8(4):354–74.
Luqman H, El-Alfy E-S, BinMakhashen GM. Joint space representation and recognition of sign language fingerspelling using Gabor filter and convolutional neural network. Multimed Tools Appl. 2021;80(7):10213–34.
Gupta S, et al. An Approach to Classify Tall Vegetation and Urban Using Deoriented PALSAR Image. IEEE Geosci Remote Sens Lett. 2017;14(12):2185–9.
Castillo-Santiago MA, Ricker M, de Jong BHJ. Estimation of tropical forest structure from SPOT-5 satellite images. Int J Remote Sens. 2010;31(10):2767–82.
Johansen K, et al. Application of high spatial resolution satellite imagery for riparian and forest ecosystem classification. Remote Sens Environ. 2007;110(1):29–44.
Haralick RM, Shanmugam K, Dinstein IH. Textural features for image classification. IEEE Transact Syst Man Cybernet. 1973;6:610–21.
Zhang Y, et al. Remote-sensing image classification based on an improved probabilistic neural network. Sensors. 2009;9(9):7516–39.
Huang T, Yang GJTGY, Tang G. "A fast two-dimensional median filtering algorithm. IEEE Transact Acoust, Speech, Sig Process. 1979;27(1):13–8.
Lee C-J, Wang S-D. Fingerprint feature extraction using Gabor filters. Electron Lett. 1999;35(4):288–90.
Munawar HS, et al. Big data and its applications in smart real estate and the disaster management life cycle: A systematic analysis. Big Data and Cogn Comp. 2020;4(2):4.
Li, Weitao, et al. (2010) Selection of gabor filters for improved texture feature extraction."2010 IEEE International Conference on Image Processing. IEEE
Alshehhi R, et al. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. ISPRS J Photogram Remote Sens. 2017;130:139–49.
Sarwar, Syed Shakib, Priyadarshini Panda, and Kaushik Roy. "Gabor filter assisted energy efficient fast learning convolutional neural networks." 2017 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED). IEEE, 2017.
Bonfatti BR, et al. Digital mapping of soil parent material in a heterogeneous tropical area. Geomorphology. 2020;367:107305.
Cui B, et al. A new integrated vegetation index for the estimation of winter wheat leaf chlorophyll content. Remote Sens. 2019;11(8):974.
Bárta V, Lukeš P, Homolová L. Early detection of bark beetle infestation in Norway spruce forests of Central Europe using Sentinel-2. Int J Appl Earth Obs Geoinf. 2021;100: 102335.
Sonobe R, et al. Crop classification from Sentinel-2-derived vegetation indices using ensemble learning. J Appl Remote Sens. 2018;12(2):026019.
Meivel S, Maheswari S. Remote Sensing Analysis of Agricultural Drone. Journal of the Indian Society of Remote Sensing. 2021;49(3):689–701.
Taloor AK, Manhas DS, Kothyari GC. Retrieval of land surface temperature, normalized difference moisture index, normalized difference water index of the Ravi basin using Landsat data. Appl Comp Geosci. 2021;9:100051.
Singh KK, Singh A. Identification of flooded area from satellite images using Hybrid Kohonen Fuzzy C-Means sigma classifier. Egy J Remote Sens Space Sci. 2017;20(1):147–55.
Taylor JA, Bates TR. Comparison of Different Vegetative Indices for Calibrating Proximal Canopy Sensors to Grapevine Pruning Weight. Am J Enol Vitic. 2021;72(3):279–83.
Liu P, Shi R, Gao W. Estimating leaf chlorophyll contents by combining multiple spectral indices with an artificial neural network. Earth Sci Inf. 2018;11(1):147–56.
Guo Z, et al. Estimation of Photosynthetic and Non-Photosynthetic Vegetation Coverage in the Lower Reaches of Tarim River Based on Sentinel-2A Data. Remote Sens. 2021;13(8):1458.
Ramos AP, Marques, et al. A random forest ranking approach to predict yield in maize with uav-based vegetation spectral indices. Comp Electr Agricult. 2020;178:105791.
Hassan MA, et al. Time-series multispectral indices from unmanned aerial vehicle imagery reveal senescence rate in bread wheat. Remote Sens. 2018;10(6):809.
Pesaresi M, Corbane C, Julea A, Florczyk AJ, Syrris V, Soille P. Assessment of the added-value of Sentinel-2 for detecting built-up areas. Remote Sens. 2016;8:299.
Sekertekin A, Marangoz A, Akcin H. Pixel-Based Classification Analysis of Land Use Land Cover Using SENTINEL-2 and LANDSAT-8 Data. Int Arch Photogramm Remote Sens Spatial Inf Sci. 2017;42:91–3.
Topaloğlu RH, Sertel E, Musaoğlu N. Assessment of classification accuracies of Sentinel-2 and Landsat-8 data for land cover/use mapping. Int Arch Photogramm Rem Sens Spat Informat Sci. 2016;41:1055–9.
Jin Y, Liu X, Chen Y, Liang X. Land-cover mapping using Random Forest classification and incorporating NDVI time-series and texture: a case study of central Shandong. Int J Rem Sens. 2018;39(23):8703–23.
Sánchez-Espinosa A, Schröder C. Land use and land cover mapping in wetlands one step closer to the ground: Sentinel-2 versus landsat 8. J Environ Manage. 2019;247:484–98.
Kumar A, et al. Monitoring the Land Use, Land Cover Changes of Roorkee Region (Uttarakhand, India) Using Machine Learning Techniques. Int J Soc Ecol Sustain Develop (IJSESD). 2023;14(1):1–16.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kumar, A., Garg, R.D. Land Cover Mapping and Change Analysis Using Optimized Random Forest Classifier Incorporating Fusion of Texture and Gabor Features. SN COMPUT. SCI. 4, 685 (2023). https://doi.org/10.1007/s42979-023-02111-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-02111-6