Mapping Soil Organic Carbon in Degraded Ecosystems Through Upscaled Multispectral Unmanned Aerial Vehicle–Satellite Imagery

  1. Salgado, Lorena 1
  2. Moriano González, Lidia 1
  3. R. Gallego, José Luis 1
  4. López Sánchez, Carlos A. 2
  5. Colina, Arturo 13
  6. Forján, Rubén 12
  1. 1 Environmental Biogeochemistry & Raw Materials Group, Institute of Natural Resources and Territorial Planning (INDUROT), University of Oviedo. Spain
  2. 2 SMartForest Group, Department of Organisms and Systems Biology, University of Oviedo. Spain
  3. 3 Department of Geography, University of Oviedo. Spain
Show affiliations +
Journal:
Land

ISSN: 2073-445X

Year of publication: 2025

Volume: 14

Issue: 2

Pages: 377

Type: Article

DOI: 10.3390/LAND14020377 GOOGLE SCHOLAR lock_openOpen access editor

More publications in: Land

Abstract

Soil organic carbon (SOC) is essential for maintaining ecosystem health, and its depletion is widely recognized as a key indicator of soil degradation. Activities such as mining and wildfire disturbances significantly intensify soil degradation, leading to quantitative and qualitative declines in SOC. Accurate SOC monitoring is critical, yet traditional methods are often costly and time-intensive. Advances in technologies like Unmanned Aerial Vehicles (UAVs) and satellite remote sensing (SRS) now offer efficient and scalable alternatives. Combining UAV and satellite data through machine learning (ML) techniques can improve the accuracy and spatial resolution of SOC monitoring, facilitating better soil management strategies. In this context, this study proposes a methodology that integrates geochemical data (SOC) with UAV-derived information, upscaling the UAV data to satellite platforms (GEOSAT-2 and SENTINEL-2) using ML techniques, specifically random forest (RF) algorithms. The research was conducted in two distinct environments: a reclaimed open-pit coal mine, representing a severely degraded ecosystem, and a high-altitude region prone to recurrent wildfires, both characterized by extreme environmental conditions and diverse soil properties. These scenarios provide valuable opportunities to evaluate the effects of soil degradation on SOC quality and to assess the effectiveness of advanced monitoring approaches. The RF algorithm, optimized with cross-validation (CV) techniques, consistently outperformed other models. The highest performance was achieved during the UAV-to-SENTINEL-2 upscaling, with an R2 of 0.761 and an rRMSE of 8.6%. Cross-validation mitigated overfitting and enhanced the robustness and generalizability of the models. UAV data offered high-resolution insights for localized SOC assessments, while SENTINEL-2 imagery enabled broader-scale evaluations, albeit with a smoothing effect. These findings underscore the potential of integrating UAV and satellite data with ML approaches, providing a cost-effective and scalable framework for SOC monitoring, soil management, and climate change mitigation efforts.

€ View funding

Funding information

Funders

Bibliographic References

  • Lal, (2015), Sustainability, 7, pp. 5875, 10.3390/su7055875
  • Lal, (2003), Environ. Int., 29, pp. 437, 10.1016/S0160-4120(02)00192-7
  • Wang, (2023), Int. J. Environ. Sci. Technol., 20, pp. 13635, 10.1007/s13762-023-04915-8
  • Rouhani, (2023), Environ. Geochem. Health, 45, pp. 7459, 10.1007/s10653-023-01700-x
  • Covelo, (2018), Environ. Sci. Pollut. Res., 25, pp. 1294, 10.1007/s11356-017-0559-0
  • Feng, (2019), Earth-Sci. Rev., 191, pp. 12, 10.1016/j.earscirev.2019.02.015
  • Company, J., Fortesa, J., García-Comendador, J., and Estrany, J. (2022, January 12–16). Effects of Wildfires Recurrency on Soil Erosion in a Terraced Burned Mediterranean Catchment. Proceedings of the 10th International Conference on Geomorphology, Coimbra, Portugal.
  • Salgado, (2024), J. Environ. Manag., 354, pp. 120293, 10.1016/j.jenvman.2024.120293
  • Cobelo, (2023), Environ. Res., 224, pp. 115522, 10.1016/j.envres.2023.115522
  • Arunrat, N., Sereenonchai, S., Kongsurakan, P., Iwai, C.B., Yuttitham, M., and Hatano, R. (2023). Post-Fire Recovery of Soil Organic Carbon, Soil Total Nitrogen, Soil Nutrients, and Soil Erodibility in Rotational Shifting Cultivation in Northern Thailand. Front. Environ. Sci., 11.
  • Aumtong, S., Chotamonsak, C., and Glomchinda, T. (2023). Study of the Interaction of Dissolved Organic Carbon, Available Nutrients, and Clay Content Driving Soil Carbon Storage in the Rice Rotation Cropping System in Northern Thailand. Agronomy, 13.
  • Chen, (2023), Geoderma, 439, pp. 116671, 10.1016/j.geoderma.2023.116671
  • Asensio, (2014), J. Geochem. Explor., 147, pp. 91, 10.1016/j.gexplo.2014.10.004
  • Asensio, (2014), Chemosphere, 95, pp. 511, 10.1016/j.chemosphere.2013.09.108
  • Asensio, (2016), J. Soils Sediments, 16, pp. 1529, 10.1007/s11368-016-1358-9
  • Fusaro, (2019), PeerJ, 7, pp. e7897, 10.7717/peerj.7897
  • Cambardella, (1994), Soil Sci. Soc. Am. J., 58, pp. 1505, 10.2136/sssaj1994.03615995005800050033x
  • Wen, (2015), Earth Sci., 73, pp. 239, 10.1007/s12665-014-3518-9
  • Blackburn, K.W., Libohova, Z., Adhikari, K., Kome, C., Maness, X., and Silman, M.R. (2022). Influence of Land Use and Topographic Factors on Soil Organic Carbon Stocks and Their Spatial and Vertical Distribution. Remote Sens., 14.
  • Wang, (2023), J. For. Res., 28, pp. 324, 10.1080/13416979.2023.2225240
  • Castro Cillero, C., Gómez Domínguez, J.A., Martín Delgado, J., Sánchez Hinojo, B.A., Arango Cereijo, J.L.C., Tuya Cheda, F.A., and Díaz-Varela, R. (2020). An UAV and Satellite Multispectral Data Approach to Monitor Water Quality in Small Reservoirs. Remote Sens., 12.
  • Vaudour, E., Gholizadeh, A., Castaldi, F., Saberioon, M., Borůvka, L., Urbina-Salazar, D., Fouad, Y., Arrouays, D., Richer-De-forges, A.C., and Biney, J. (2022). Satellite Imagery to Map Topsoil Organic Carbon Content over Cultivated Areas: An Overview. Remote Sens., 14.
  • Boente, (2022), CATENA, 208, pp. 105730, 10.1016/j.catena.2021.105730
  • Jia, (2021), Environ. Pollut., 270, pp. 116281, 10.1016/j.envpol.2020.116281
  • Leung, (2018), Sci. Total Environ., 633, pp. 836, 10.1016/j.scitotenv.2018.03.049
  • (2006), J. Mach. Learn. Res., 7, pp. 1
  • Chakraborty, (2015), Sci. Total Environ., 514, pp. 399, 10.1016/j.scitotenv.2015.01.087
  • Emadi, M., Taghizadeh-Mehrjardi, R., Cherati, A., Danesh, M., Mosavi, A., and Scholten, T. (2020). Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran. Remote Sens., 12.
  • Gao, (2022), Int. J. Appl. Earth Obs. Geoinf., 108, pp. 102742
  • Troncoso, (2015), Neurocomputing, 167, pp. 24, 10.1016/j.neucom.2014.09.091
  • Salgado, (2023), Environ. Pollut., 333, pp. 122066, 10.1016/j.envpol.2023.122066
  • Chabrillat, (2019), Surv. Geophys., 40, pp. 361, 10.1007/s10712-019-09524-0
  • Buma, W., Abelev, A., and Merrick, T. (2024). Vegetation Spectra as an Integrated Measure to Explain Underlying Soil Characteristics: A Review of Recent Advances. Front. Environ. Sci., 12.
  • Delegido, (2022), Plant Soil, 479, pp. 159, 10.1007/s11104-022-05506-1
  • Dean, (2024), Environ. Sci. Process. Impacts, 26, pp. 161, 10.1039/D3EM00480E
  • Mao, (2022), ISPRS J. Photogramm. Remote Sens., 192, pp. 361, 10.1016/j.isprsjprs.2022.08.021
  • Novo-Fernández, A., Barrio-Anta, M., Recondo, C., Cámara-Obregón, A., and López-Sánchez, C.A. (2019). Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain. Remote Sens., 11.
  • Gobierno del Principado de Asturias (2020). Estrategia Integral de Prevención y Lucha Contra Los Incendios Forestales En Asturias (2020–2025), Servicio de Emergencias del Principado de Asturias.
  • AEMET Valores Climatológicos Normales—Agencia Estatal de Meteorología—AEMET (2024, November 18). Gobierno de España. Available online: https://www.aemet.es/es/serviciosclimaticos/datosclimatologicos/valoresclimatologicos.
  • Panagos, (2022), Eur. J. Soil Sci., 73, pp. e13315, 10.1111/ejss.13315
  • González Menéndez, L., Heredia, N., and Marcos, A. (2008). Mapa Geológico Digital Continuo E. 1: 50.000, Zona Asturoccidental-Leonesa (Zona-1100), Mapa Geológico Digital Continuo de España.
  • Boente, C., Salgado, L., Romero-Macías, E., Colina, A., López-Sánchez, C.A., and Gallego, J.L.R. (2020). Correlation between Geochemical and Multispectral Patterns in an Area Severely Contaminated by Former Hg-As Mining. ISPRS Int. J. Geo-Inf., 9.
  • Handique, (2020), Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., 43, pp. 67, 10.5194/isprs-archives-XLIII-B3-2020-67-2020
  • Calleja, (2023), Rev. Teledetec., 2023, pp. 83
  • Drusch, (2012), Remote Sens. Environ., 120, pp. 25, 10.1016/j.rse.2011.11.026
  • Pettorelli, (2005), Trends Ecol. Evol., 20, pp. 503, 10.1016/j.tree.2005.05.011
  • Hmimina, (2013), Remote Sens. Environ., 132, pp. 145, 10.1016/j.rse.2013.01.010
  • Rondeaux, (1996), Remote Sens. Environ., 55, pp. 95, 10.1016/0034-4257(95)00186-7
  • Baret, (1989), Photogrammetria, 43, pp. 241, 10.1016/0031-8663(89)90001-X
  • Rouse, (1974), NASA Spec. Publ., 1, pp. 309
  • Huete, (1988), Remote Sens. Environ., 25, pp. 295, 10.1016/0034-4257(88)90106-X
  • Huete, (1988), Remote Sens. Environ., 25, pp. 89, 10.1016/0034-4257(88)90043-0
  • Marsett, (2006), Rangel. Ecol. Manag., 59, pp. 530, 10.2111/05-201R.1
  • Barnes, E.M., Clarke, T.R., Richards, S.E., Colaizzi, P.D., Haberland, J., Kostrzewski, M., Waller, P., Choi, C., Riley, E., and Thompson, T. (2000, January 16–19). Coincident Detection of Crop Water Stress, Nitrogen Status and Canopy Density Using Ground-Based Multispectral Data. Proceedings of the Fifth International Conference on Precision Agriculture, Madison, WI, USA.
  • Blackburn, (1998), Int. J. Remote Sens., 19, pp. 657, 10.1080/014311698215919
  • Penuelas, (1995), Photosynthetica, 31, pp. 221
  • Haboudane, (2002), Remote Sens. Environ., 81, pp. 416, 10.1016/S0034-4257(02)00018-4
  • Buschmann, (1993), Int. J. Remote Sens., 14, pp. 711, 10.1080/01431169308904370
  • Gitelson, (1994), J. Photochem. Photobiol. B Biol., 22, pp. 247, 10.1016/1011-1344(93)06963-4
  • Gitelson, (1996), J. Plant Physiol., 148, pp. 501, 10.1016/S0176-1617(96)80285-9
  • Daughtry, (2000), Remote Sens. Environ., 74, pp. 229, 10.1016/S0034-4257(00)00113-9
  • Bausch, (1996), Trans. ASAE, 39, pp. 1869, 10.13031/2013.27665
  • Main, (2011), ISPRS J. Photogramm. Remote Sens., 66, pp. 751, 10.1016/j.isprsjprs.2011.08.001
  • Huete, A., Didan, K., and Van Leeuwen, W. (1999). MODIS Vegetation Index (MOD 13) ATBD Version 3.1.
  • Huete, (2002), Remote Sens. Environ., 83, pp. 195, 10.1016/S0034-4257(02)00096-2
  • Nagler, (2005), Remote Sens. Environ., 97, pp. 337, 10.1016/j.rse.2005.05.011
  • Dorigo, (2007), Int. J. Appl. Earth Obs. Geoinf., 9, pp. 165
  • Glenn, (2010), Surv. Geophys., 31, pp. 531, 10.1007/s10712-010-9102-2
  • Birth, (1968), Agron. J., 60, pp. 640, 10.2134/agronj1968.00021962006000060016x
  • Roujean, (1995), Remote Sens. Environ., 51, pp. 375, 10.1016/0034-4257(94)00114-3
  • Crippen, (1990), Remote Sens. Environ., 34, pp. 71, 10.1016/0034-4257(90)90085-Z
  • Chen, (1996), Can. J. Remote Sens., 22, pp. 229, 10.1080/07038992.1996.10855178
  • Chen, (2014), Environ. Sci. Technol., 48, pp. 13751, 10.1021/es503669u
  • Richardson, (1977), Photogramm. Eng. Remote Sens., 43, pp. 1541
  • Kooistra, (2010), Int. J. Remote Sens., 24, pp. 4995, 10.1080/0143116031000080769
  • Thaler, (2019), Soil Sci. Soc. Am. J., 83, pp. 1443, 10.2136/sssaj2018.09.0318
  • Bartholomeus, (2008), Geoderma, 145, pp. 28, 10.1016/j.geoderma.2008.01.010
  • Mandal, U.K. (2016, January 12–19). Spectral Color Indices Based Geospatial Modeling of Soil Organic Matter in Chitwan District, Nepal. Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Prague, Czech Republic.
  • Escadafal, R. (1989). Caractérisation de La Surface Des Sols Arides Par Observations de Terrain et Par Télédétection. Applications: Exemple de La Région de Tataouine (Tunisie), Université Pierre et Marie Curie.
  • Qi, (1994), Remote Sens. Environ., 48, pp. 119, 10.1016/0034-4257(94)90134-1
  • Jordan, (1969), Ecology, 50, pp. 663, 10.2307/1936256
  • Nellis, (1992), Trans. Kans. Acad. Sci., 95, pp. 93, 10.2307/3628024
  • Tucker, (1979), Remote Sens. Environ., 8, pp. 127, 10.1016/0034-4257(79)90013-0
  • Xiao, (2004), Remote Sens. Environ., 91, pp. 256, 10.1016/j.rse.2004.03.010
  • Xu, Z., and Wang, X. (2010, January 7–10). Research for Information Extraction Based on Wrapper Model Algorithm. Proceedings of the 2nd International Conference on Computer Research and Development, ICCRD 2010, Washington, DC, USA.
  • Chung, (2020), IEEE Access, 8, pp. 118315, 10.1109/ACCESS.2020.2999910
  • Ghazali, (2010), Environ. Monit. Assess., 165, pp. 475, 10.1007/s10661-009-0960-3
  • Breiman, (2001), Mach. Learn., 45, pp. 5, 10.1023/A:1010933404324
  • Boser, B.E., Guyon, I.M., and Vapnik, V.N. (1992, January 27–29). Training Algorithm for Optimal Margin Classifiers. Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, USA.
  • Ihaka, (1996), J. Comput. Graph. Stat., 5, pp. 299, 10.1080/10618600.1996.10474713
  • Vohland, (2011), Geoderma, 166, pp. 198, 10.1016/j.geoderma.2011.08.001
  • Wei, L., Yuan, Z., Yu, M., Huang, C., and Cao, L. (2019). Estimation of Arsenic Content in Soil Based on Laboratory and Field Reflectance Spectroscopy. Sensors, 19.
  • Sun, (2024), Sci. Total Environ., 926, pp. 171931, 10.1016/j.scitotenv.2024.171931
  • Wang, (2018), Sci. Total Environ., 630, pp. 367, 10.1016/j.scitotenv.2018.02.204
  • Sheykhmousa, (2020), IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 13, pp. 6308, 10.1109/JSTARS.2020.3026724
  • Heil, J., Jörges, C., and Stumpe, B. (2022). Fine-Scale Mapping of Soil Organic Matter in Agricultural Soils Using UAVs and Machine Learning. Remote Sens., 14.
  • Akay, (2022), Earth Sci. Inform., 15, pp. 2239, 10.1007/s12145-022-00876-7
  • Kior, A., Sukhov, V., and Sukhova, E. (2021). Application of Reflectance Indices for Remote Sensing of Plants and Revealing Actions of Stressors. Photonics, 8.
  • Bradford, (2013), Biogeochemistry, 113, pp. 271, 10.1007/s10533-012-9822-0
  • Gholizadeh, (2018), Remote Sens. Environ., 218, pp. 89, 10.1016/j.rse.2018.09.015
  • Simkin, (2022), Photosynth. Res., 152, pp. 23, 10.1007/s11120-021-00892-6
  • Dakora, (2002), Plant Soil, 245, pp. 35, 10.1023/A:1020809400075
  • Karim, (2024), Geotechnics, 4, pp. 78, 10.3390/geotechnics4010005
  • Jiang, Q., Chen, Y., Hu, J., and Liu, F. (2020). Use of Visible and Near-Infrared Reflectance Spectroscopy Models to Determine Soil Erodibility Factor (K) in an Ecologically Restored Watershed. Remote Sens., 12.
  • Gao, (1996), Remote Sens. Environ., 58, pp. 257, 10.1016/S0034-4257(96)00067-3
  • Asner, (2002), Int. J. Remote Sens., 23, pp. 3939, 10.1080/01431160110115960
  • (2004), Int. J. Appl. Earth Obs. Geoinf., 5, pp. 55