Detection and Removal of Climatic Noise from Remotely Sensed Images through LANDSAT8/OLI/TIRS with Ground Truth Validation using MLC, MDC, and RF

Detection and Removal of Climatic Noise from Remotely Sensed Images through LANDSAT8/OLI/TIRS with Ground Truth Validation using MLC, MDC, and RF
  IJETT-book-cover           
  
© 2023 by IJETT Journal
Volume-71 Issue-2
Year of Publication : 2023
Author : Renuka Sandeep Gound, Sudeep D. Thepade
DOI : 10.14445/22315381/IJETT-V71I2P214

How to Cite?

Renuka Sandeep Gound, Sudeep D. Thepade, "Detection and Removal of Climatic Noise from Remotely Sensed Images through LANDSAT8/OLI/TIRS with Ground Truth Validation using MLC, MDC, and RF," International Journal of Engineering Trends and Technology, vol. 71, no. 2, pp. 111-120, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I2P214

Abstract
The remotely sensed images acquired through the satellites play a significant role in various crop management applications in agriculture, security and defense activities, monitoring disasters, and change detection on Land with LULC. Sometimes these images carry the climatic noise occurrences over the ground surface, which may occlude the regions. This article presents a novel method for detecting and removing climatic noise from remotely sensed images acquired from LANDSAT8/OLI/TIRS with accurate Ground Truth Validation. The proposed system identifies the climatic noise by using the combination of empirical pixel values of the Quality Assessment Band and Band-9 of LANSAT8/OLI/TIRS. Land cover obtained is classified using Maximum Likelihood Classifier (MLC), Random Forest Classifier (RF) and Minimum Distance Classification (MDC), with NDVI and NDWI thresholds. The image is reconstructed after collecting and replacing the pixel values, with the influence of Climatic Noise using the reference image. The performance measurements used for the proposed system depict the desired results. The Standard Error (SE) is almost close to zero for all the scenes. User Accuracies and Producer Accuracies are also more than 90 %. The K-hat statistics are also closer to one for all scenes, and the overall accuracy achieved is also more than 90% for most of the scenes. It is seen from the statistics and findings achieved with the proposed system; the ground cover obtained with the proposed system can be further utilised in the applications of the remote sensing field.

Keywords
Climatic Noise, Maximum Likelihood Classifier (MLC), Minimum Distance Classification (MDC), Normalised Difference Vegetation Index (NDVI, Normalised Difference Water Index (NDWI), Random Forest Classifier (RF).

References
[1] Daniel Schläpfer, Rudolf Richter, and Peter Reinartz, “Elevation-Dependent Removal of Cirrus Clouds in Satellite Imagery,” Remote Sensing, vol. 12, no. 3, p. 494, 2020. Crossref, https://doi.org/10.3390/rs12030494
[2] Bo-Cai Gao, and Rong-Rong Li, “Removal of Thin Cirrus Scattering Effects in Landsat 8 OLI Images Using the Cirrus Detecting Channel,” Remote Sensing, vol. 9, no. 8, p. 834, 2017. Crossref, https://doi.org/10.3390/rs9080834
[3] Binxing Zhou, and Yong Wang, “A Thin-Cloud Removal Approach Combining the Cirrus Band and RTM-Based Algorithm for Landsat-8 OLI Data,” IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, pp. 1434-1437, 2019. Crossref, https://doi.org/10.1109/igarss.2019.8898644
[4] Yang Shen et al., “Removal of Thin Clouds in Landsat-8 OLI Data with Independent Component Analysis,” Remote Sensing, vol. 7, pp. 11481-11500, 2015. Crossref, https://doi.org/10.3390/rs70911481
[5] Ratna Prastyani, and Abdul Basith, "Cirrus Cloud Correction in Landsat 8 Image Using the Image-Based Approach: A Case Study in Sumba Island, Indonesia," 2018 4th International Conference on Science and Technology (ICST), Yogyakarta, pp. 1-5, 2018. Crossref, https://doi.org/10.1109/ICSTC.2018.8528629
[6] Jing Wei et al., “Cloud Detection for Landsat Imagery by Combining the Random Forest and Superpixels Extracted via EnergyDriven Sampling Segmentation Approaches,” Remote Sensing of Environment, vol. 248, p. 112005, 2020. Crossref, https://doi.org/10.1016/j.rse.2020.112005
[7] Nan Ma et al., “Cloud Detection Algorithm for Multi-Satellite Remote Sensing Imagery Based on a Spectral Library and 1D Convolutional Neural Network,” Remote Sensing, vol. 13, no. 16, p. 3319, 2021. Crossref, https://doi.org/10.3390/rs13163319
[8] Lam Pham et al., “Remote Sensing Image Classification using Transfer Learning and Attention Based Deep Neural Network,” arXiv, 2022. Crossref, https://doi.org/10.48550/arXiv.2206.13392
[9] Cengis Hasan et al., “Cloud Removal from Satellite Imagery Using Multispectral Edge-Filtered Conditional Generative Adversarial Networks,” International Journal of Remote Sensing, vol. 43, no. 5, pp. 1881-1893, 2022. Crossref, https://doi.org/10.1080/01431161.2022.2048915
[10] Sergii Skakun et al., “Cloud Mask Intercomparison eXercise (CMIX): An Evaluation of Cloud Masking Algorithms for Landsat 8 and Sentinel-2,” Remote Sensing of Environment, vol. 274, p. 112990, 2022. Crossref, https://doi.org/10.1016/j.rse.2022.112990
[11] Zhiwei Li et al., “Cloud and Cloud Shadow Detection for Optical Satellite Imagery: Features, Algorithms, Validation, and Prospects,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 188, pp. 89-108, 2022. Crossref, https://doi.org/10.1016/j.isprsjprs.2022.03.020
[12] Hélène Chepfer et al., “Cirrus Cloud Properties Derived from POLDER-1/ADEOS Polarized Radiances: First Validation Using a Ground-Based Lidar Network,” Journal of Applied Meteorology, vol. 39, pp. 154-168, 2000. Crossref, https://doi.org/10.1175/1520- 0450(2000)0392.0.CO;2
[13] Amy Tal Rose, Lance Sherry, and Donglian Sun, “Methodology and Case Study for Validation of Aircraft-Induced Clouds from Hyperspectral Imagery,” Atmosphere, vol. 13, no. 8, p. 1257, 2022. Crossref, https://doi.org/10.3390/atmos13081257
[14] Tran Thi Ngoc Trieu et al., “Influences of Aerosols and Thin Cirrus Clouds on GOSAT XCO2 and XCH4 Using Total Carbon Column Observing Network, Sky Radiometer, and Lidar Data,” International Journal of Remote Sensing, vol. 43, no. 5, pp. 1770- 1799, 2022. Crossref, https://doi.org/10.1080/01431161.2022.2038395
[15] Qiang Li, and Silke Groß, “Satellite Observations of Seasonality and Long-Term Trend in Cirrus Cloud Properties over Europe: Investigation of Possible Aviation Impacts,” EGUsphere, 2022. Crossref, https://doi.org/10.5194/egusphere-2022-628, 2022
[16] Saleem Ali et al., “Temporal and Vertical Distributions of the Occurrence of Cirrus Clouds over a Coastal Station in the Indian Monsoon Region,” Atmospheric Chemistry and Physics, vol. 22, pp. 8321–8342, 2022. Crossref, https://doi.org/10.5194/acp-22-8321-2022.
[17] Shuang Liang et al., “Accurate Monitoring of Submerged Aquatic Vegetation in a Macrophytic Lake Using Time-Series Sentinel-2 Images,” Remote Sensing, vol. 14, no. 3, p. 640, 2022. Crossref, https://doi.org/10.3390/rs14030640
[18] Junmei Kang et al., “Collaborative Extraction of Paddy Planting Areas with Multi-Source Information Based on Google Earth Engine: A Case Study of Cambodia,” Remote Sensing, vol. 14, no. 8, p. 1823, 2022. Crossref, https://doi.org/ 10.3390/rs14081823
[19] Renuka S. Gound, and Dr. Sudeep D. Thepade, “Removal of Cloud and Shadow Influence from Remotely Sensed Images Through LANDSAT8/OLI/TIRS Using Minimum Distance Supervised Classification,” Indian Journal of Computer Science and Engineering, vol. 12, pp. 1734-1748, 2021. Crossref, https://doi.org/10.21817/indjcse/2021/v12i6/211206118
[20] Y.Vishnu Tej et al., "A Novel Methodology for Denoising Impulse Noise in Satellite Images through Isolated Vector Median Filter with k-means Clustering," International Journal of Engineering Trends and Technology, vol. 70, no. 8, pp. 272-283, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I8P229
[21] Huong Thi Thanh Nguyen et al., “Land Use/Land Cover Mapping Using Multitemporal Sentinel-2 Imagery and Four Classification Methods—A Case Study from Dak Nong, Vietnam,” Remote Sensing, vol. 12, no. 9, p. 1367, 2020. Crossref, https://doi.org/10.3390/rs12091367
[22] Yuhendra, and Eva Yulianti, “Multi-Temporal Sentinel-2 Images for Classification Accuracy,” Journal of Computer Science, vol. 15, no. 2, pp. 258-268, 2019. Crossref, https://doi.org/10.3844/jcssp.2019.258.268
[23] Ju Zeng et al., “Comparison of Landsat 8, Sentinel-2 and spectral indices combinations for Google Earth Engine-based land use mapping in the Johor River Basin, Malaysia,” Malaysian Journal of Society and Space, vol. 17, no. 3, 2021. Crossref, https://doi.org/10.17576/geo-2021-1703-03
[24] LANDSAT8. [Online]. Available: https://earthexplorer.usgs.gov/scene/metadata/full/5e81f14f59432a27/LC81440462018037LGN00/
[25] Aniekan Eyoh, and Francis Okeke, "Evaluation of the Relationship between Land Use/Land Cover Dynamics and Land Surface Temperature across the Niger Delta Region of Nigeria," SSRG International Journal of Geoinformatics and Geological Science, vol. 4, no. 3, pp. 1-12, 2017. Crossref, https://doi.org/10.14445/23939206/IJGGS-V4I5P101
[26] LANDSAT8. [Online]. Available: https://earthexplorer.usgs.gov/scene/metadata/full/5e81f14f59432a27/LC81440462018101LGN00
[27] Anish Anurag et al., "Local Attention-Based Descriptor Definition using Vision Transformer for Breast Cancer Identification," International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 317-327, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P230
[28] HB Kekre, Sudeep D Thepade, and Tejas Chopra, "Face and Gender Recognition Using Principal Component Analysis", International Journal on Computer Science and Engineering, vol. 2, no. 4, pp. 959-964, 2010.
[29] HB Kekre, Sudeep D Thepede, and Akshay Maloo, "Eigenvectors of Covariance Matrix using Row Mean and Column Mean Sequences for Face Recognition,” International Journal of Biometrics and Bioinformatics, vol. 4, no. 2, pp. 42-50, 2010.
[30] HB Kekre, Sudeep D Thepade, and Akshay Maloo, "Comprehensive Performance Comparison of Cosine, Walsh, Haar, Kekre, Sine, Slant and Hartley Transforms for CBIR with Fractional Coefficients of Transformed Image," International Journal of Image Processing, vol. 5, no. 3, pp. 336-351, 2011.
[31] HB Kekre, Sudeep D Thepade, and Parkar Adib, "An Extended Performance Comparison of Colour to Grey and Back using the Haar, Walsh, and Kekre Wavelet Transforms," International Journal of Advanced Computer Science and Applications, vol. 3, pp. 92- 99, 2011. Crossref, https://doi.org/10.14569/SpecialIssue.2011.010315
[32] LANDSAT8. [Online]. Available: https://earthexplorer.usgs.gov/scene/metadata/full/5e81f14f59432a27/LC81440462018053LGN00/
[33] Renuka S. Gound, and Dr. Sudeep D. Thepade, “Validation of Ground Truth of Remotely Sensed Data from SENTINEL-2 (MSI) Using Supervised Classification, After Combined Cloud and Shadow Effect Removal,” Indian Journal of Computer Science and Engineering, vol. 13, pp. 860-868, 2022. Crossref, https://doi.org/10.21817/indjcse/2022/v13i3/221303164