Artificial Intelligence based Detection and Mapping Cloud and Cloud-shadow in the Saranda Sal Forest during the Monsoon Season using Google Earth Engine
DOI:
https://doi.org/10.36808/if/2026/v152i7/171355Keywords:
Sentinel-2, Tropical Moist Deciduous Forest, Google Earth Engine, Saranda Forest, Monsoon Season Forest Monitoring.Abstract
Persistent monsoon cloud cover limits the effective use of optical satellite imagery for forest monitoring in tropical regions. This study was conducted to develop Artificial Intelligence (AI) based Random Forest algorithm using Google Earth Engine (GEE)-based framework for cloud and cloud-shadow detection in the Saranda Forest, the largest Sal (Shorea robusta) forest in Asia. Sentinel-2 imagery acquired during the 2025 monsoon season was used for cloud and cloud-shadow mapping. Cloud pixels were identified using cloud probability information together with spectral reflectance characteristics, while cloud shadows were detected using solar azimuth geometry and low reflectance values. Spectral analysis revealed that forest vegetation exhibited Near Infrared (NIR) reflectance approximately twice those of the red band, whereas cloud features showed high reflectance across all spectral bands. Cloud-shadow regions displayed spectral characteristics similar to forest vegetation but with comparatively lower reflectance values. The results indicated that approximately 45% and 15% of the study area were covered by clouds and cloud shadows, respectively. The proposed framework achieved an overall accuracy of 95.0%, an F1-score of 94.43%, and a Kappa coefficient of 0.89. ROC analyses confirmed excellent cloud detection performance, demonstrating the suitability of the proposed framework for operational forest monitoring in cloud-prone tropical environments.
References
Abera T.A., Heiskanen J., Maeda E.E., Muhammed M.A., Bhandari N., Vakkari V., Hailu B.T., Pellikka P.K.E., Hemp A., van Zyl P.G. and Zeuss D. (2024). Deforestation amplifies climate change effects on warming and cloud level rise in African montane forests. Nature Communications, 15(1): 1–10. https://doi.org/10.1038/s41467-024-51324-7 DOI: https://doi.org/10.1038/s41467-024-51324-7
Anthony G., Greg H., Tshilidzi M., Engineering I. and Africa S. (2003). Classification of Images Using Support Vector Machines, 9: 121-145.
Bach H., Klug P., Ruf T., Migdall S., Schlenz F., Hank T. and Mauser W. (2015). Satellite image simulations for modelsupervised , dynamic retrieval of crop type and land use intensity. Xl(may), 11–15. https://doi.org/10.5194/ isprsarchives-XL-7-W3-1-2015 DOI: https://doi.org/10.5194/isprsarchives-XL-7-W3-1-2015
Beale R. and Jackson T. (1990). Neural Computing: An Introduction. In Neural Computing: An Introduction.
https://doi.org/10.1887/0852742622 DOI: https://doi.org/10.1887/0852742622
Bonan G., Levis S. and Sitch S. (2003). A dynamic global vegetation model for use with climate models: concepts and description of simulated vegetation dynamics. Global Change …, 9: 1543–1566. https://doi.org/10.1046/j.1529-8817.2003.00681.x DOI: https://doi.org/10.1046/j.1365-2486.2003.00681.x
Breiman L. (2001). Random forests. Machine Learning, 45(1): 5–32. DOI: https://doi.org/10.1023/A:1010933404324
Cal A. (2026). CLOSDI: A novel spectral index for cloud shadow detection in Sentinel-2 imagery using NDVI and EVI2. Remote Sensing Applications: Society and Environment, 42(March). https://doi.org/10.1016/j.rsase.2026.101990 DOI: https://doi.org/10.1016/j.rsase.2026.101990
Candra D.S., Phinn S. and Scarth P. (2020). Cloud and cloud shadow masking for Sentinel-2 using multitemporal images in global area. International Journal of Remote Sensing, 41(8): 2877–2904. DOI: https://doi.org/10.1080/01431161.2019.1697006
Cutler D.R., Edwards T.C., Beard K.H., Cutler A., Hess K.T., Gibson J. and Lawler J.J. (2007). Random forests for classification in ecology. Ecology, 88(11): 2783–2792. https://doi.org/10.1890/07-0539.1 DOI: https://doi.org/10.1890/07-0539.1
Franklin S.E., Ahmed O.S., Wulder M.A., White J.C., Hermosilla T., Coops N.C., Steven E., Oumer F., Ahmed S., Michael A. and Wulder J.C.W. (2015). Large Area Mapping of Annual Land Cover Dynamics Using Multitemporal Change Detection and Classification of Landsat Time Series Data. Canadian Journal of Remote Sensing, 41 (4): 293–314. https://doi.org/ Http://dx.doi.org/10.1080/07038992.2015.1089401, DOI: https://doi.org/10.1080/07038992.2015.1089401
Friedman J.H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 1189–1232. DOI: https://doi.org/10.1214/aos/1013203451
Giri C., Pengra B., Long J. and Loveland T.R. (2013). Next generation of global land cover characterization, mapping, and monitoring. International Journal of Applied Earth Observation and Geoinformation. https://doi.org/10.1016/j.jag.2013.03.005 Gong P., Wang J., Yu L., Zhao Y., Zhao Y., Liang L., Niu Z., Huang X., Fu H., Liu S., Li C., Li X., Fu W., Liu C., Xu Y., Wang X., Cheng Q., Hu L., Yao W. and Chen J. (2013). Finer resolution observation and monitoring of global land cover: First mapping results with Landsat TM and ETM+ data. International Journal of Remote Sensing, 34(7): 2607–2654. https://doi.org/10.1080/01431161.2012.748992 DOI: https://doi.org/10.1080/01431161.2012.748992
Huang C., Davis L.S. and J.R.G.T. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23.4(December 2012), 725–749. https://doi.org/10.1080/01431160110040323 DOI: https://doi.org/10.1080/01431160110040323
Jin Chen, Per Jonsson, Masayuki Tamura, Zhihui Gu and Bunkei Matsushita L.E. (2014). A simple method for reconstructing a high quality NDVI time-series data set based on the Savitzky-Golay filter (pp. 19, 332–344). Remote Sensing and Environment. https://doi.org/10.1016/j.rse.2004.03.014 DOI: https://doi.org/10.1016/j.rse.2004.03.014
Lavania P., Singh R.K., Kumar P., Savad K., Gupta G., Dobriyal M., Pandey A.K., Kumar M. and Singh S. (2024). Unveiling the green guardians: Mapping and identification of Azadirachta indica trees with semantic segmentation deep learning neural network technique. The Egyptian Journal of Remote Sensing and Space Sciences, 27(3): 491–500. DOI: https://doi.org/10.1016/j.ejrs.2024.06.002
Lemmouchi F., Cuesta J., Eremenko M., Derognat C., Siour G., Dufour G., Sellitto P., Turquety S., Tran D. and Liu X. (2022). Three-dimensional distribution of biomass burning aerosols from Australian wildfires observed by TROPOMI satellite observations. Remote Sensing, 14(11): 2582. DOI: https://doi.org/10.3390/rs14112582
Li Y., Chen R., He B. and Veraverbeke S. (2022). Forest foliage fuel load estimation from multi-sensor spatiotemporal features. International Journal of Applied Earth Observation and Geoinformation, 115, 103101. https://doi.org/https:// doi.org/10.1016/j.jag.2022.103101 DOI: https://doi.org/10.1016/j.jag.2022.103101
Main-Knorn M., Pflug B., Louis J., Debaecker V., Müller-Wilm U.and Gascon F. (2017). Sen2Cor for sentinel-2. Image and Signal Processing for Remote Sensing XXIII, 10427, 37–48. DOI: https://doi.org/10.1117/12.2278218
Parihar S.M. and Singh R.K. (2014). Mapping of Glaciers Sensitivity Spatial Topology in North-West Himalaya using Spatial Modeling, IJARSGG (2014) 2(2):1-10, Research Paper (2014). International Journal of Advancement in Remote Sensing, GIS and Geography, 1–10.
Singh R.K., Drews M., la Sen M., Srivastava P.K., Trisasongko B.H., Kumar M., Pandey M.K., Anand A., Singh S.S., Pandey A.K. and others. (2021). Highlighting the compound risk of COVID-19 and environmental pollutants using geospatial technology. Scientific Reports, 11(1): 1–12. DOI: https://doi.org/10.1038/s41598-021-87877-6
Singh R.K., Kumar P., Kumar M., Tyagi K. and Jain H. (2022). Artificial Machine Learning–Based Classification of Land Cover and Crop Types Using Sentinel 2A Imagery. Sustainable Agriculture Systems and Technologies, 326–336. DOI: https://doi.org/10.1002/9781119808565.ch16
Singh R.K., Shankar V., Sinha P., Joshi P.K. and Kumar M. (2019). Use of Savitzky - Golay Filters to Minimize Multitemporal Data Anomaly in Land use Land cover mapping. 42(4): 362–368. DOI: https://doi.org/10.54207/bsmps1000-2019-650ST3
Singh R.K., Singh P., Drews M., Kumar P., Singh H., Gupta A.K., Govil H., Kaur A. and Kumar M. (2021). A machine learningbased classification of LANDSAT images to map land use and land cover of India. Remote Sensing Applications: Society and Environment, 24, 100624. DOI: https://doi.org/10.1016/j.rsase.2021.100624
Singh R.K., Singh S., Kumar M., Singh Y. and Kumar P. (2024). Drone Technology in Perspective of Data Capturing. In P. Kumar & Aishwarya (Eds.), Technological Approaches for Climate Smart Agriculture (pp. 363–374). Springer International Publishing. https://doi.org/10.1007/978-3-031-52708-1_18 DOI: https://doi.org/10.1007/978-3-031-52708-1_18
Singh R.K., Sinha V.S.P., Joshi P.K. and Kumar M. (2021). A multinomial logistic model-based land use and land cover classification for the South Asian Association for Regional Cooperation nations using Moderate Resolution Imaging Spectroradiometer product. Environment, Development and Sustainability, 23(4): 6106–6127. DOI: https://doi.org/10.1007/s10668-020-00864-1
Veglio P., Fu D., Holz R., Meyer K., Platnick S., Borbas E.E. and Dutcher S. (2025). MODIS-VIIRS Cloud Mask (CLDMSK) User’s Guide.
Xu R., Li Y., Teuling A.J., Zhao L., Spracklen D.V., Garcia- Carreras L., Meier R., Chen L., Zheng Y., Lin H. and Fu B. (2022). Contrasting impacts of forests on cloud cover based on satellite observations. Nature Communications, 13(1). https://doi.org/10.1038/s41467-022-28161-7 DOI: https://doi.org/10.1038/s41467-022-28161-7
Zhai H., Zhang H., Zhang L. and Li P. (2018). Cloud/shadow detection based on spectral indices for multi/hyperspectral optical remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 144: 235–253. DOI: https://doi.org/10.1016/j.isprsjprs.2018.07.006
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Unless otherwise stated, copyright or similar rights in all materials presented on the site, including graphical images, are owned by Indian Forester.
