Self-Trained Deep Forest with Limited Samples for Urban Impervious Surface Area Extraction in Arid Area Using Multispectral and PolSAR Imageries
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area
2.2. Data
2.3. Method
2.3.1. Feature Extraction
2.3.2. Self-Trained Deep Forest
- Input the labeled samples (initial training set) and unlabeled samples into the cascade forest with RF and ExtraTrees as the basic estimators in a certain proportion.
- Train the classifier and make predictions for unlabeled samples. The pseudo-labels with prediction probabilities greater than a threshold are added to the training set.
- Repeat the previous step. The classifier will continue iterating until the specified maximum number of iterations is reached.
3. Results and Discussion
3.1. Experimental Setup
- Parameter Settings: (a) By verifying the accuracy of the number of 10–100 samples per class (10 groups in total) and the proportion of labeled samples to training samples (0.1–1.0), 30 training pixels per class, a total of 150, were randomly selected from labeled samples. Additionally, in the training set, the proportion of labeled samples was 0.8. (b) In verifying the extraction accuracy, the bright ISA and dark ISA were selected as impervious samples, while vegetation, water and bare land were selected as pervious samples. Then, 8000 test pixels per class, a total of 16,000, were randomly selected to examine the extraction accuracy for ISA. (c) The optimal parameters were determined by the grid search method, which optimizes the model by traversing the given parameters and using a cross-validation method. The number of estimators in each cascade layer is 2; the number of trees in each estimator is 125; and the maximum number of cascade layers is 25. In DF, the base classifiers are set as default by RF and ExtraTrees.
- Comparison with Other Methods: In this study, three classification methods, including RF, self-trained RF (STRF) and DF, were compared to evaluate the performance of the STDF algorithm. In order to test the superiority of the combination of the multispectral image features and PolSAR features proposed in this paper, the results for the use of multispectral image features alone were added for comparison. In addition, PISIs, for which the best performance was achieved with Sentinel-2 [75], NBAIs and land cover datasets (FROM-GLC10) were used for comparison. PISI and NBAI are, respectively, expressed as below [13,15]:
- Accuracy Assessment: To evaluate the performance for ISA extraction, ground reference data were collected by visual interpretation of high-spatial-resolution Google Earth images from the same period. The labeled samples were divided into five land-cover types (bright ISA, dark ISA, water, vegetation and bare land) and were evenly distributed in the study area. Subsequently, the training and testing samples were randomly selected among the labeled samples. The accuracy of ISA extraction was assessed by overall accuracy (OA), Kappa coefficient, commission error (CE) and omission error (OE) based on the confusion matrix. In addition, receiver operating characteristic (ROC) and area under ROC curve (AUC) were used for classification performance assessment.
3.2. Performance of PolSAR in ISA Enhancement
3.3. Results for ISA Extraction and Accuracy Assessment
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Weng, Q. Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends. Remote Sens. Environ. 2012, 117, 34–49. [Google Scholar] [CrossRef]
- Xu, H. Analysis of impervious surface and its impact on urban heat environment using the normalized difference impervious surface index (NDISI). Photogramm. Eng. Remote Sens. 2010, 76, 557–565. [Google Scholar] [CrossRef]
- Shuster, W.D.; Bonta, J.; Thurston, H.; Warnemuende, E.; Smith, D. Impacts of impervious surface on watershed hydrology: A review. Urban Water J. 2005, 2, 263–275. [Google Scholar] [CrossRef]
- Arnold, C.L., Jr.; Gibbons, C.J. Impervious surface coverage: The emergence of a key environmental indicator. J. Am. Plan. Assoc. 1996, 62, 243–258. [Google Scholar] [CrossRef]
- Ridd, M.K. Exploring a VIS (vegetation-impervious surface-soil) model for urban ecosystem analysis through remote sensing: Comparative anatomy for cities. Int. J. Remote Sens. 1995, 16, 2165–2185. [Google Scholar] [CrossRef]
- Wu, C.; Murray, A.T. Estimating impervious surface distribution by spectral mixture analysis. Remote Sens. Environ. 2003, 84, 493–505. [Google Scholar] [CrossRef]
- Weng, Q.; Hu, X.; Lu, D. Extracting impervious surfaces from medium spatial resolution multispectral and hyperspectral imagery: A comparison. Int. J. Remote Sens. 2008, 29, 3209–3232. [Google Scholar] [CrossRef]
- Wu, C. Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery. Remote Sens. Environ. 2004, 93, 480–492. [Google Scholar] [CrossRef]
- Wu, C. Quantifying high-resolution impervious surfaces using spectral mixture analysis. Int. J. Remote Sens. 2009, 30, 2915–2932. [Google Scholar] [CrossRef]
- Deng, C.; Wu, C. A spatially adaptive spectral mixture analysis for mapping subpixel urban impervious surface distribution. Remote Sens. Environ. 2013, 133, 62–70. [Google Scholar] [CrossRef]
- Xu, H. A new remote sensing index for fastly extracting impervious surface information. Geomat. Inf. Sci. Wuhan Univ. 2008, 33, 1150–1153. [Google Scholar]
- Deng, C.; Wu, C. BCI: A biophysical composition index for remote sensing of urban environments. Remote Sens. Environ. 2012, 127, 247–259. [Google Scholar] [CrossRef]
- Tian, Y.; Chen, H.; Song, Q.; Zheng, K. A Novel Index for Impervious Surface Area Mapping: Development and Validation. Remote Sens. 2018, 10, 1521. [Google Scholar] [CrossRef]
- Zha, Y.; Gao, J.; Ni, S. Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. Int. J. Remote Sens. 2003, 24, 583–594. [Google Scholar] [CrossRef]
- Waqar, M.M.; Mirza, J.F.; Mumtaz, R.; Hussain, E. Development of new indices for extraction of built-up area & bare soil from landsat data. Open Access Sci. Rep 2012, 1, 2–4. [Google Scholar]
- Liu, C.; Shao, Z.; Chen, M.; Luo, H. MNDISI: A multi-source composition index for impervious surface area estimation at the individual city scale. Remote Sens. Lett. 2013, 4, 803–812. [Google Scholar] [CrossRef]
- Plunk, D.E.; Morgan, K.; Newland, L. Mapping impervious cover using Landstat TM data. J. Soil Water Conserv. 1990, 45, 589–591. [Google Scholar]
- Hodgson, M.E.; Jensen, J.R.; Tullis, J.A.; Riordan, K.D.; Archer, C.M. Synergistic use of lidar and color aerial photography for mapping urban parcel imperviousness. Photogramm. Eng. Remote Sens. 2003, 69, 973–980. [Google Scholar] [CrossRef]
- Sun, Z.; Guo, H.; Li, X.; Lu, L.; Du, X. Estimating urban impervious surfaces from Landsat-5 TM imagery using multilayer perceptron neural network and support vector machine. J. Appl. Remote Sens. 2011, 5, 053501. [Google Scholar] [CrossRef]
- Zhang, H.; Zhang, Y.; Lin, H. A comparison study of impervious surfaces estimation using optical and SAR remote sensing images. Int. J. Appl. Earth Obs. Geoinf. 2012, 18, 148–156. [Google Scholar] [CrossRef]
- Wang, B.; Chen, Z.; Zhu, A.-X.; Hao, Y.; Xu, C. Multi-level classification based on trajectory features of time series for monitoring impervious surface expansions. Remote Sens. 2019, 11, 640. [Google Scholar] [CrossRef]
- Zhang, Y.; Zhang, H.; Lin, H. Improving the impervious surface estimation with combined use of optical and SAR remote sensing images. Remote Sens. Environ. 2014, 141, 155–167. [Google Scholar] [CrossRef]
- Torbick, N.; Corbiere, M. Mapping urban sprawl and impervious surfaces in the northeast United States for the past four decades. GIScience Remote Sens. 2015, 52, 746–764. [Google Scholar] [CrossRef]
- Shao, Z.; Fu, H.; Fu, P.; Yin, L. Mapping urban impervious surface by fusing optical and SAR data at the decision level. Remote Sens. 2016, 8, 945. [Google Scholar] [CrossRef]
- Weng, Q.; Hu, X. Medium spatial resolution satellite imagery for estimating and mapping urban impervious surfaces using LSMA and ANN. IEEE Trans. Geosci. Remote Sens. 2008, 46, 2397–2406. [Google Scholar] [CrossRef]
- Mohapatra, R.P.; Wu, C. High resolution impervious surface estimation. Photogramm. Eng. Remote Sens. 2010, 76, 1329–1341. [Google Scholar] [CrossRef]
- Huang, F.; Yu, Y.; Feng, T. Automatic extraction of impervious surfaces from high resolution remote sensing images based on deep learning. J. Vis. Commun. Image Represent. 2019, 58, 453–461. [Google Scholar] [CrossRef]
- Sun, Z.; Zhao, X.; Wu, M.; Wang, C. Extracting urban impervious surface from worldView-2 and airborne LiDAR data using 3D convolutional neural networks. J. Indian Soc. Remote Sens. 2019, 47, 401–412. [Google Scholar] [CrossRef]
- Parekh, J.R.; Poortinga, A.; Bhandari, B.; Mayer, T.; Saah, D.; Chishtie, F. Automatic detection of impervious surfaces from remotely sensed data using deep learning. Remote Sens. 2021, 13, 3166. [Google Scholar] [CrossRef]
- Tang, P.; Du, P.; Lin, C.; Guo, S.; Qie, L. A novel sample selection method for impervious surface area mapping using JL1-3B nighttime light and Sentinel-2 imagery. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 3931–3941. [Google Scholar] [CrossRef]
- Shao, Z.; Liu, C. The integrated use of DMSP-OLS nighttime light and MODIS data for monitoring large-scale impervious surface dynamics: A case study in the Yangtze River Delta. Remote Sens. 2014, 6, 9359–9378. [Google Scholar] [CrossRef]
- Tan, W.; Liao, R.; Du, Y.; Lu, J.; Li, J. Improving urban impervious surface classification by combining Landsat and PolSAR images: A case study in Kitchener-Waterloo, Ontario, Canada. In Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, 26–31 July 2015; pp. 1917–1920. [Google Scholar]
- Guo, H.; Yang, H.; Sun, Z.; Li, X.; Wang, C. Synergistic use of optical and PolSAR imagery for urban impervious surface estimation. Photogramm. Eng. Remote Sens. 2014, 80, 91–102. [Google Scholar] [CrossRef]
- Lin, Y.; Zhang, H.; Lin, H.; Gamba, P.E.; Liu, X. Incorporating synthetic aperture radar and optical images to investigate the annual dynamics of anthropogenic impervious surface at large scale. Remote Sens. Environ. 2020, 242, 111757. [Google Scholar] [CrossRef]
- Zhang, H.; Zhang, Y.; Lin, H. Compare different levels of fusion between optical and SAR data for impervious surfaces estimation. In Proceedings of the 2012 Second International Workshop on Earth Observation and Remote Sensing Applications, Shanghai, China, 8–11 June 2012; pp. 26–30. [Google Scholar]
- Zhang, H.; Xu, R. Exploring the optimal integration levels between SAR and optical data for better urban land cover mapping in the Pearl River Delta. Int. J. Appl. Earth Obs. Geoinf. 2018, 64, 87–95. [Google Scholar] [CrossRef]
- Zhang, H.; Lin, H.; Li, Y.; Zhang, Y. Impervious surfaces estimation using dual-polarimetric SAR and optical data. In Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada, 13–18 July 2014; pp. 4812–4815. [Google Scholar]
- Gong, P.; Li, X.; Zhang, W. 40-Year (1978–2017) human settlement changes in China reflected by impervious surfaces from satellite remote sensing. Sci. Bull. 2019, 64, 756–763. [Google Scholar] [CrossRef]
- Sun, Z.; Du, W.; Jiang, H.; Weng, Q.; Guo, H.; Han, Y.; Xing, Q.; Ma, Y. Global 10-m impervious surface area mapping: A big earth data based extraction and updating approach. Int. J. Appl. Earth Obs. Geoinf. 2022, 109, 102800. [Google Scholar] [CrossRef]
- Tuia, D.; Ratle, F.; Pacifici, F.; Kanevski, M.F.; Emery, W.J. Active learning methods for remote sensing image classification. IEEE Trans. Geosci. Remote Sens. 2009, 47, 2218–2232. [Google Scholar] [CrossRef]
- Hong, D.; Yokoya, N.; Xia, G.-S.; Chanussot, J.; Zhu, X.X. X-ModalNet: A semi-supervised deep cross-modal network for classification of remote sensing data. ISPRS J. Photogramm. Remote Sens. 2020, 167, 12–23. [Google Scholar] [CrossRef]
- Chen, J.; Sun, J.; Li, Y.; Hou, C. Object detection in remote sensing images based on deep transfer learning. Multimed. Tools Appl. 2022, 81, 12093–12109. [Google Scholar] [CrossRef]
- Li, X.; Deng, J.; Fang, Y. Few-shot object detection on remote sensing images. IEEE Trans. Geosci. Remote Sens. 2021, 60, 1–14. [Google Scholar] [CrossRef]
- Lal, A.M.; Anouncia, S.M. Semi-supervised change detection approach combining sparse fusion and constrained k means for multi-temporal remote sensing images. Egypt. J. Remote Sens. Space Sci. 2015, 18, 279–288. [Google Scholar] [CrossRef]
- Zhang, W.; Lu, X.; Li, X. A coarse-to-fine semi-supervised change detection for multispectral images. IEEE Trans. Geosci. Remote Sens. 2018, 56, 3587–3599. [Google Scholar] [CrossRef]
- Hou, B.; Wang, Y.; Liu, Q. A saliency guided semi-supervised building change detection method for high resolution remote sensing images. Sensors 2016, 16, 1377. [Google Scholar] [CrossRef] [Green Version]
- Dópido, I.; Li, J.; Plaza, A.; Gamba, P. Semi-supervised classification of hyperspectral data using spectral unmixing concepts. In Proceedings of the 2012 Tyrrhenian Workshop on Advances in Radar and Remote Sensing (TyWRRS), Naples, Italy, 12–14 September 2012; pp. 353–358. [Google Scholar]
- Liu, Y.; Zhang, B.; Wang, L.-M.; Wang, N. A self-trained semisupervised SVM approach to the remote sensing land cover classification. Comput. Geosci. 2013, 59, 98–107. [Google Scholar] [CrossRef]
- Guo, H.; Shi, Q.; Marinoni, A.; Du, B.; Zhang, L. Deep building footprint update network: A semi-supervised method for updating existing building footprint from bi-temporal remote sensing images. Remote Sens. Environ. 2021, 264, 112589. [Google Scholar] [CrossRef]
- Protopapadakis, E.; Doulamis, A.; Doulamis, N.; Maltezos, E. Stacked autoencoders driven by semi-supervised learning for building extraction from near infrared remote sensing imagery. Remote Sens. 2021, 13, 371. [Google Scholar] [CrossRef]
- Zhang, L.; Weng, Q.; Shao, Z. An evaluation of monthly impervious surface dynamics by fusing Landsat and MODIS time series in the Pearl River Delta, China, from 2000 to 2015. Remote Sens. Environ. 2017, 201, 99–114. [Google Scholar] [CrossRef]
- Zhang, L.; Zhang, M.; Yao, Y. Mapping seasonal impervious surface dynamics in Wuhan urban agglomeration, China from 2000 to 2016. Int. J. Appl. Earth Obs. Geoinf. 2018, 70, 51–61. [Google Scholar] [CrossRef]
- Yarowsky, D. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, Cambridge, MA, USA, 26–30 June 1995; pp. 189–196. [Google Scholar]
- Li, Y.; Xing, R.; Jiao, L.; Chen, Y.; Chai, Y.; Marturi, N.; Shang, R. Semi-supervised PolSAR image classification based on self-training and superpixels. Remote Sens. 2019, 11, 1933. [Google Scholar] [CrossRef]
- Li, F.; Clausi, D.A.; Xu, L.; Wong, A. ST-IRGS: A region-based self-training algorithm applied to hyperspectral image classification and segmentation. IEEE Trans. Geosci. Remote Sens. 2017, 56, 3–16. [Google Scholar] [CrossRef]
- Wu, Y.; Mu, G.; Qin, C.; Miao, Q.; Ma, W.; Zhang, X. Semi-supervised hyperspectral image classification via spatial-regulated self-training. Remote Sens. 2020, 12, 159. [Google Scholar] [CrossRef]
- Banerjee, B.; Bovolo, F.; Bhattacharya, A.; Bruzzone, L.; Chaudhuri, S.; Mohan, B.K. A new self-training-based unsupervised satellite image classification technique using cluster ensemble strategy. IEEE Geosci. Remote Sens. Lett. 2014, 12, 741–745. [Google Scholar] [CrossRef]
- Zhou, Z.-H.; Feng, J. Deep forest: Towards an alternative to deep neural networks. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 19–25 August 2017; pp. 3553–3559. [Google Scholar]
- Wang, W.; Dai, Q.; Li, F.; Xiong, Y.; Wei, D.-Q. MLCDForest: Multi-label classification with deep forest in disease prediction for long non-coding RNAs. Brief. Bioinform. 2021, 22, bbaa104. [Google Scholar] [CrossRef] [PubMed]
- Yin, L.; Zhao, L.; Yu, T.; Zhang, X. Deep forest reinforcement learning for preventive strategy considering automatic generation control in large-scale interconnected power systems. Appl. Sci. 2018, 8, 2185. [Google Scholar] [CrossRef]
- Boualleg, Y.; Farah, M.; Farah, I.R. Remote sensing scene classification using convolutional features and deep forest classifier. IEEE Geosci. Remote Sens. Lett. 2019, 16, 1944–1948. [Google Scholar] [CrossRef]
- Yang, F.; Xu, Q.; Li, B.; Ji, Y. Ship detection from thermal remote sensing imagery through region-based deep forest. IEEE Geosci. Remote Sens. Lett. 2018, 15, 449–453. [Google Scholar] [CrossRef]
- Mao, S.; Yang, J.; Gou, S.; Jiao, L.; Xiong, T.; Xiong, L. Multi-Scale Fused SAR Image Registration Based on Deep Forest. Remote Sens. 2021, 13, 2227. [Google Scholar] [CrossRef]
- Xia, J.; Ming, Z.; Iwasaki, A. Multiple sources data fusion via deep forest. In Proceedings of the IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22–27 July 2018; pp. 1722–1725. [Google Scholar]
- Yin, X.; Wang, R.; Liu, X.; Cai, Y. Deep forest-based classification of hyperspectral images. In Proceedings of the 2018 37th Chinese Control Conference (CCC), Wuhan, China, 25–27 July 2018; pp. 10367–10372. [Google Scholar]
- Zhang, J.; Song, H.; Zhou, B. SAR target classification based on deep forest model. Remote Sens. 2020, 12, 128. [Google Scholar] [CrossRef]
- Chen, B.; Xu, B.; Zhu, Z.; Yuan, C.; Suen, H.P.; Guo, J.; Xu, N.; Li, W.; Zhao, Y.; Yang, J. Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. Sci. Bull. 2019, 64, 370–373. [Google Scholar]
- Myneni, R.B.; Hall, F.G.; Sellers, P.J.; Marshak, A.L. The interpretation of spectral vegetation indexes. IEEE Trans. Geosci. Remote Sens. 1995, 33, 481–486. [Google Scholar] [CrossRef]
- Gao, B.-C. NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sens. Environ. 1996, 58, 257–266. [Google Scholar] [CrossRef]
- Liao, W.; Mura, M.; Chanussot, J.; Bellens, R.; Philips, W. Morphological Attribute Profiles With Partial Reconstruction. IEEE Trans. Geosci. Remote Sens. 2016, 54, 1738–1756. [Google Scholar] [CrossRef]
- Liao, W.; Chanussot, J.; Mura, M.; Xin, H.; Bellens, R, Gautama, S; Philips, W. Taking optimal advantage of fine spatial resolution: Promoting partial image reconstruction for the morphological analysis of very-high-resolution images. IEEE Geosci. Remote Sens. Mag. 2017, 2, 8–28. [Google Scholar] [CrossRef]
- Freeman, A.; Durden, S.L. A three-component scattering model for polarimetric SAR data. IEEE Trans. Geosci. Remote Sens. 1998, 36, 963–973. [Google Scholar] [CrossRef] [Green Version]
- Pang, M.; Ting, K.; Zhao, P.; Zhou, Z. Improving Deep Forest by Confidence Screening. In Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), Singapore, 17–20 November 2018; pp. 1194–1199. [Google Scholar]
- Samat, A.; Li, E.; Du, P.; Liu, S.; Miao, Z. Improving Deep Forest via Patch-Based Pooling, Morphological Profiling, and Pseudo Labeling for Remote Sensing Image Classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 9334–9349. [Google Scholar] [CrossRef]
- Li, C.; Shao, Z.; Zhang, L.; Huang, X.; Zhang, M. A Comparative Analysis of Index-Based Methods for Impervious Surface Mapping Using Multiseasonal Sentinel-2 Satellite Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 3682–3694. [Google Scholar] [CrossRef]
- Zhang, H.; Lin, H.; Wang, Y. A new scheme for urban impervious surface classification from SAR images. ISPRS J. Photogramm. Remote Sens. 2018, 139, 103–118. [Google Scholar] [CrossRef]
- Lee, J.-S.; Pottier, E. Polarimetric Radar Imaging: From Basics to Applications; CRC Press: Boca Raton, FL, USA, 2017. [Google Scholar]
Study Area | Sensor | Acquisition Dates | Pass | Resolution |
---|---|---|---|---|
Bishkek | Sentinel-2A | 7 August 2017 | 10 m | |
GF-3 | 9 November 2017 | Ascending | 8 m | |
Tashkent | Sentinel-2A | 8 November 2017 | 10 m | |
GF-3 | 25 October 2017 | Descending | 8 m | |
Nursultan | Sentinel-2B | 17 September 2017 | 10 m | |
GF-3 | 30 August 2017 | Descending | 8 m |
Source | Feature Set | Descriptions | N |
---|---|---|---|
Sentinel-2A multispectral bands (B2, B3, B4 and B8) | Spectral features | NDVI | 1 |
NDWI | 1 | ||
Spatial features | Morphological attribute profiles with partial reconstruction | 120 | |
GF-3 quad-polarized SAR | Polarimetric features | T3 matrix | 9 |
H/A/α decomposition (entropy, anisotropy and alpha) | 3 | ||
Freeman decomposition (Freeman_DBL, Freeman_VOL and Freeman_SURF) | 3 |
STDF | STRF | DF | RF | STDF (Spectral) | PISI | ||
---|---|---|---|---|---|---|---|
Bishkek | Kappa | 0.9406 | 0.9249 | 0.9266 | 0.9174 | 0.7506 | 0.7394 |
OA (%) | 97.03 | 96.24 | 96.33 | 95.87 | 87.53 | 86.97 | |
OE (%) | 2.16 | 2.39 | 2.61 | 2.58 | 9.59 | 17.56 | |
CE (%) | 3.72 | 4.99 | 4.63 | 5.52 | 14.51 | 9.35 | |
Tashkent | Kappa | 0.9043 | 0.8110 | 0.8363 | 0.8474 | 0.8429 | 0.7819 |
OA (%) | 95.21 | 90.55 | 91.81 | 92.37 | 92.14 | 89.09 | |
OE (%) | 6.38 | 11.58 | 12.71 | 12.88 | 10.13 | 16.65 | |
CE (%) | 3.30 | 7.65 | 4.03 | 2.67 | 5.85 | 5.83 | |
Nursultan | Kappa | 0.9498 | 0.9266 | 0.9395 | 0.9280 | 0.9100 | 0.7595 |
OA (%) | 97.49 | 96.33 | 96.98 | 96.40 | 95.50 | 87.98 | |
OE (%) | 0.98 | 0.61 | 0.88 | 1.34 | 3.63 | 11.74 | |
CE (%) | 3.93 | 6.34 | 4.96 | 5.61 | 5.28 | 12.24 |
Study Area | Sensor | Acquisition Dates |
---|---|---|
Bishkek | Sentinel-2A | 8 June 2017 |
Sentinel-2A | 7 August 2017 | |
Sentinel-2B | 1 November 2017 | |
Tashkent | Sentinel-2A | 16 July 2017 |
Sentinel-2A | 2 September2017 | |
Sentinel-2A | 8 November2017 | |
Nursultan | Sentinel-2A | 18 January 2017 |
Sentinel-2A | 18 May 2017 | |
Sentinel-2B | 17 September 2017 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 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 (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, X.; Samat, A.; Li, E.; Wang, W.; Abuduwaili, J. Self-Trained Deep Forest with Limited Samples for Urban Impervious Surface Area Extraction in Arid Area Using Multispectral and PolSAR Imageries. Sensors 2022, 22, 6844. https://doi.org/10.3390/s22186844
Liu X, Samat A, Li E, Wang W, Abuduwaili J. Self-Trained Deep Forest with Limited Samples for Urban Impervious Surface Area Extraction in Arid Area Using Multispectral and PolSAR Imageries. Sensors. 2022; 22(18):6844. https://doi.org/10.3390/s22186844
Chicago/Turabian StyleLiu, Ximing, Alim Samat, Erzhu Li, Wei Wang, and Jilili Abuduwaili. 2022. "Self-Trained Deep Forest with Limited Samples for Urban Impervious Surface Area Extraction in Arid Area Using Multispectral and PolSAR Imageries" Sensors 22, no. 18: 6844. https://doi.org/10.3390/s22186844
APA StyleLiu, X., Samat, A., Li, E., Wang, W., & Abuduwaili, J. (2022). Self-Trained Deep Forest with Limited Samples for Urban Impervious Surface Area Extraction in Arid Area Using Multispectral and PolSAR Imageries. Sensors, 22(18), 6844. https://doi.org/10.3390/s22186844