Machine learning approaches for clear-sky Land Surface Albedo (LSA) retrieval using OCM-3 data over diverse Indian landscapes

Authors

  • ALIYA M. KURESHI Sir P. T. Sarvajanik College of Science, Veer Narmad South Gujarat University, Surat 395007, Gujarat, India
  • VISHAL N. PATHAK National Monsoon Mission, Indian Institute of Tropical Meteorology, Pune 411008, Maharashtra India
  • DISHA B. KARDANI Sir P. T. Sarvajanik College of Science, Veer Narmad South Gujarat University, Surat 395007, Gujarat, India
  • JALPESH A. DAVE N. V. Patel College of Pure and Applied Sciences, CVM University, Anand 388120, Gujarat, India
  • DHIRAJ B. SHAH Sir P. T. Sarvajanik College of Science, Veer Narmad South Gujarat University, Surat 395007, Gujarat, India
  • TEJAS P. TURAKHIA Department of Instrumentation and Control Engineering, LDCE, GTU, Ahmedabad 380015, Gujarat, India
  • ASHWIN GUJRATI Space Applications Centre, Indian Space Research Organisation, Ahmedabad 380015, Gujarat, India
  • MEHUL R. PANDYA Space Applications Centre, Indian Space Research Organisation, Ahmedabad 380015, Gujarat, India
  • HIMANSHU J. TRIVEDI N. V. Patel College of Pure and Applied Sciences, CVM University, Anand 388120, Gujarat, India

DOI:

https://doi.org/10.54386/jam.v27i4.3174

Keywords:

Land Surface Albedo, Ocean Colour Monitor-3 (OCM-3), 6s (Second Simulation of a Satellite Signal in the Solar Spectrum), Machine learning, Random Forest

Abstract

This study presents reliable methods for estimating clear-sky land surface albedo (LSA) using machine learning (ML) and satellite data, aiming to improve climate models and environmental monitoring. Top-of-atmosphere (TOA) radiance data from the Ocean Colour Monitor-3 (OCM-3) sensor aboard the Earth Observing Satellite (EOS-06) satellite containing 13 spectral bands were used, supported by 2.4 million synthetic simulations generated via the 6S (Second Simulation of a Satellite Signal in the Solar Spectrum) Radiative Transfer Model (RTM). The simulations spanned diverse land covers, atmospheric states, sun and viewing geometries covering wavelengths from 0.4 to 2.5 µm. Three ML models namely Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Multiple Linear Regression (MLR) were tested. Models were trained on 70% of the simulated data and tested on 30%. Validation with actual OCM-3 data included additional aerosol and water vapor information from MODIS. LSA estimations were compared to the MODIS standard product (MCD43A3). Among the three models, RF achieved the best performance, with the lowest RMSE (0.00036) and strong agreement across various land types with MODIS data. The results confer the potential of ML models, especially RF, combined with radiative simulations, and can be used for operational estimation of LSA for OCM-3 data.

References

Belgiu, M., and Drăguț, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS J. Photog. Remote Sens., 114: 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011

Bijlwan, A., Pokhriyal, S., Ranjan, R., Singh, R. K., and Jha, A. (2024). Machine learning methods for estimating reference evapotranspiration. J. Agrometeorol., 26(1): 63–68. https://doi.org/10.54386/jam.v26i1.2462

Boussetta, S., Balsamo, G., Dutra, E., Beljaars, A., and Albergel, C. (2015). Assimilation of surface albedo and vegetation states from satellite observations and their impact on numerical weather prediction. Remote Sens. Environ., 163: 111–126. https://doi.org/10.1016/j.rse.2015.03.009

Breiman, L. (2001). Random forests. Mach. Learn., 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324

Chen, H., Lin, X., Sun, Y., Wen, J., Wu, X., You, D., Cheng, J., Zhang, Z., Zhang, Z., Wu, C., Zhang, F., Yin, K., Jian, H., and Guan, X. (2023). Performance assessment of four data-driven machine learning models: A case to generate Sentinel-2 albedo at 10 meters. Remote Sens., 15 (10): 2684. https://doi.org/10.3390/rs15102684

Chen, T., and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785

Dave, J. A., Pandya, M. R., Shah, D. B., Varchand, H. K., Parmar, P. N., Trivedi, H. J., Pathak, V. N., Singh, M., and Kardani, D. B. (2023). Comparative analysis of two parameter-dependent split window algorithms for the land surface temperature retrieval using MODIS TIR observations. J. Agrometeorol., 25(4): 510–516. https://doi.org/10.54386/jam.v25i4.2286

He, T., Wang, D., and Qu, Y. (2018). Land surface albedo. In S. Liang (Ed.), Comprehensive remote sensing (Vol. 5, Earth’s energy budget, pp. 140–162). Oxford, UK: Elsevier. https://doi.org/10.1016/B978-0-12-409548-9.10370-7

ICAR. (2025, August). Indian Council of Agricultural Research, Gujarat. https://icar.org.in/en/node/17264

Kumar, P., Bhattacharya, B. K., Nigam, R., Kishtawal, C. M., and Pal, P. K. (2014). Impact of Kalpana-1 derived land surface albedo on short-range weather forecasting over the Indian subcontinent. Remote Sens. Environ., 152: 227–239. https://ui.adsabs.harvard.edu/link_gateway/2014JGRD..119.2764K/doi:10.1002/2013JD020534

Lohare, J., Nair, R., Sharma, S. K., Pandey, S. K., and Ramakrishnan, S. (2023). Geospatial-based land use/land cover change detection in Jabalpur district, Madhya Pradesh. Biol. Forum Int. J., 15 (10), 585–592.

Liang, S. (2001). Narrowband to broadband conversions of land surface albedo I: Algorithms. Remote Sens. Environ., 76 (2), 213–238. https://doi.org/10.1016/S0034-4257(00)00205-4

Liang, S. (2003). A direct algorithm for estimating land surface broadband albedos from MODIS imagery. IEEE Trans. Geosci. Remote Sens., 41 (1): 136–145. http://dx.doi.org/10.1109/TGRS.2002.807751

Lin, X., Liu, Y., Zhang, L., Li, X., Wu, W., and Chen, Y. (2022). Estimating 10-m land surface albedo from Sentinel-2 satellite observations using a direct estimation approach with Google Earth Engine. ISPRS J. Photog. Remote Sens., 194: 1–20. https://doi.org/10.1016/j.isprsjprs.2022.09.016

Lyapustin, A., and Wang, Y. (2022). MCD19A2 MODIS/Terra+Aqua land aerosol optical depth daily L2G global 1km SIN grid V061. NASA EOSDIS Land Processes Distributed Active Archive Center. https://doi.org/10.5067/MODIS/MCD19A2.061

Martonchik, J. V., Diner, D. J., Pinty, B., Verstraete, M. M., Myneni, R. B., Knyazikhin, Y., and Gordon, H. R. (1998). Determination of land and ocean reflective, radiative, and biophysical properties using multiangle imaging. IEEE Trans. Geosci. Remote Sens., 36 (4): 1266–1281. https://doi.org/10.1109/36.701077

Meerdink, S.K., Hook, S.J., Roberts, D.A. and Abbott, E.A. (2019). The ECOSTRESS spectral library version 1.0. Remote Sens. Environ., 230: 111196.

Mehta, A., Sinha, V. K., and Ayachit, G. (2012). Land-use/land-cover study using remote sensing and GIS in an arid environment. Bull. Environ. Sci. Res., 1 (3–4), 4–8.

Montgomery, D. C., Peck, E. A., and Vining, G. G. (2012). Introduction to linear regression analysis (5th ed.). Wiley.

NASA. (2015). MODIS/Terra+Aqua BRDF/Albedo daily L3 global 500 m SIN grid V006 (MCD43A3). USGS/Earth Resources Observation and Science Center. https://doi.org/10.5067/MODIS/MCD43A3.006

Pandya, M. R., and Pathak, V. N. (2021). Algorithm theoretical basis document (ATBD) of vegetation indices (NDVI, EVI) and vegetation fraction retrieval from OCM-3 payload onboard Oceansat-3 (Version 1.0). Space Applications Centre, Indian Space Research Organisation. https://bhoonidhi.nrsc.gov.in/bhoonidhi_resources/help/docs/EOS06-ATBD-Vegetation_Indices_and_Fraction-V1.pdf

Qu, Y., Liu, Q., Liang, S., Wang, L., Liu, N., and Liu, S. (2014). Direct-estimation algorithm for mapping daily land-surface broadband albedo from MODIS data. IEEE Trans. Geosci. Remote Sens., 52 (2): 907–919. https://doi.org/10.1109/TGRS.2013.2245670

Schaaf, C. B., Gao, F., Strahler, A. H., Lucht, W., Li, X., Tsang, T., and Roy, D. (2002). First operational BRDF, albedo nadir reflectance products from MODIS. Remote Sens. Environ., 83 (1–2): 135–148. . https://doi.org/10.1016/S0034-4257(02)00091-3

Sharma, H., Burark, S. S., and Meena, G. L. (2015). Land degradation and sustainable agriculture in Rajasthan, India. J. Indus. Poll. Control, 31 (1): 7–11.

Shuai, Y., Masek, J. G., Gao, F., Schaaf, C. B., and He, T. (2014). An approach for the long-term 30-m land surface snow-free albedo retrieval from historic Landsat surface reflectance and MODIS-based a priori anisotropy knowledge. Remote Sens. Environ., 152: 467–479. https://doi.org/10.1016/j.rse.2014.07.009

Singh, J., Mansi, Baweja, P., Neha, Arya, I., Chopra, H., Gupta, S., Gandhi, P. B., Singh, P., and Rena, V. (2023). An insight into application of land use land cover analysis towards sustainable agriculture within Jhajjar District, Haryana. Int. J. Exp. Biol. Agric. Sci., 11 (4): 756–766. https://doi.org/10.18006/2023.11(4).756.766

Vermote, E. F., Tanré, D., Deuzé, J. L., Herman, M., and Morcrette, J. J. (1997). Second Simulation of the Satellite Signal in the Solar Spectrum, 6S: An overview. IEEE Trans. Geosci. Remote Sens., 35 (3): 675–686. https://doi.org/10.1109/36.581987

Wang, D., Liang, S. L., He, T., and Yu, Y. (2013). Direct estimation of land surface albedo from VIIRS data: Algorithm improvement and preliminary validation. J. Geophys. Res.: Atmos., 118: 12,577–12: 586. https://doi.org/10.1002/2013JD020417

Downloads

Published

01-12-2025

How to Cite

KURESHI, A. M., PATHAK, V. N., KARDANI, D. B., DAVE, J. A., SHAH, D. B., TURAKHIA, T. P., GUJRATI, A., PANDYA, M. R., & TRIVEDI, H. J. (2025). Machine learning approaches for clear-sky Land Surface Albedo (LSA) retrieval using OCM-3 data over diverse Indian landscapes. Journal of Agrometeorology, 27(4), 454–463. https://doi.org/10.54386/jam.v27i4.3174

Issue

Vol. 27 No. 4 (2025): December

Section

Research Paper

Categories

License

Copyright (c) 2025 ALIYA M. KURESHI, VISHAL N. PATHAK, DISHA B. KARDANI, JALPESH A. DAVE, DHIRAJ B. SHAH, TEJAS P. TURAKHIA, ASHWIN GUJRATI, MEHUL R. PANDYA, HIMANSHU J. TRIVEDI

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

This is a human-readable summary of (and not a substitute for) the license. Disclaimer.

You are free to:

Share — copy and redistribute the material in any medium or format

Adapt — remix, transform, and build upon the material

The licensor cannot revoke these freedoms as long as you follow the license terms.

    Under the following terms:

    Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.

    NonCommercial — You may not use the material for commercial purposes.

    ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.

    No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

    Notices:

    You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.

    No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.

    Most read articles by the same author(s)