Making the distinction between different plantation tree species is crucial for creating reliable and trustworthy information, which is critical in forestry administration and upkeep. Over the years, forest delineation and mapping have been done using the conventional techniques, such as the utilization of ground truth facts together with orthophotos. These techniques have been proven to be very precise, but they are expensive, cumbersome, and challenging to employ in remote regions. To resolve this shortfall, this research investigates the potential of data from the commercial, PlanetScope CubeSat and the freely available, Sentinel 2 data from Copernicus to discriminate commercial forest tree species in the Usutu Forest, Eswatini. Two approaches for image classification, Random Forest (RF) and the Support Vector Machine (SVM) were investigated at different levels of the forest database classification which is the genus (family of tree species) and species levels. The result of the study indicates that, the Sentinel 2 images had the highest species classification accuracy compared to the PlanetScope image. Both classification methods achieved a 94% maximum OA and 0.90 kappa value at the genus level with the Sentinel 2 imagery. At the species level, the Sentinel 2 imagery again showed highly acceptable results with the SVM method, with an OA of 82%. The PlanetScope images performed badly with less than 64% OA for both RF and SVM at the genus level and poorer at the species level with a low OA figure, 47% and 53% for the SVM and RF respectively. Our results suggest that the freely available Sentinel 2 data together with the SVM method has a high potential for identifying differences between commercial tree species than the PlanetScope. The study uncovered that both classification methods are highly capable of classifying species under the gum genus group (esmi, egxu, and egxn) using both imageries. However, it was difficult to separate species types under the pine genus group, particularly discriminating the hybrid species such as pech and pell since pech is a hybrid species for pell.
References
[1]
Ngwenya, P. and Hassan, R. (2005) An Environmental Accounting Approach to Valuing the Services of Natural Forests and Woodlands in Swaziland. Agrekon, 44, 264-283. https://doi.org/10.1080/03031853.2005.9523713
[2]
Hassan, R. and Ngwenya, P. (2006) Valuing Forest Services Missing from the National Accounts: The Contribution of Cultivated Forests to Wealth Accumulation in Swaziland. Forest Policy and Economics, 9, 249-260. https://doi.org/10.1016/j.forpol.2005.06.013
[3]
Sithole, G. (2013) Access to and Utilisation of Forest Resources: Evidence from Common Property Forest Management in Swaziland. International Journal of Agricultural Sciences, 5, 92-108.
[4]
FAO (2015) Global Forest Resources Assessment 2015—Swaziland. http://www.fao.org/3/a-az345e.pdf
[5]
Sheeren, D., Fauvel, M., Planque, C., Willm, J. and Dejoux, J.F. (2015) Tree Species Discrimination in Temperate Woodland Using High Spatial Resolution Formosat-2 Time Series. 2015 8th International Workshop on the Analysis of Multitemporal Remote Sensing Images (Multi-Temp), Annecy, 22-24 July 2015, 1-4. https://doi.org/10.1109/multi-temp.2015.7245792
[6]
Raczko, E. and Zagajewski, B. (2018) Tree Species Classification of the UNESCO Man and the Biosphere Karkonoski National Park (Poland) Using Artificial Neural Networks and APEX Hyperspectral Images. Remote Sensing, 10, Article No. 1111. https://doi.org/10.3390/rs10071111
[7]
Gyamfi-Ampadu, E., Gebreslasie, M. and Mendoza-Ponce, A. (2021) Evaluating Multi-Sensors Spectral and Spatial Resolutions for Tree Species Diversity Prediction. Remote Sensing, 13, Article No. 1033. https://doi.org/10.3390/rs13051033
[8]
Khanal, S., KC, K., Fulton, J.P., Shearer, S. and Ozkan, E. (2020) Remote Sensing in Agriculture—Accomplishments, Limitations, and Opportunities. Remote Sensing, 12, Article No. 3783. https://doi.org/10.3390/rs12223783
[9]
Peerbhay, K.Y., Mutanga, O. and Ismail, R. (2013) Commercial Tree Species Discrimination Using Airborne AISA Eagle Hyperspectral Imagery and Partial Least Squares Discriminant Analysis (PLS-DA) in Kwazulu-Natal, South Africa. ISPRS Journal of Photogrammetry and Remote Sensing, 79, 19-28. https://doi.org/10.1016/j.isprsjprs.2013.01.013
[10]
Cho, M.A., Mathieu, R., Asner, G.P., Naidoo, L., van Aardt, J., Ramoelo, A., et al. (2012) Mapping Tree Species Composition in South African Savannas Using an Integrated Airborne Spectral and Lidar System. Remote Sensing of Environment, 125, 214-226. https://doi.org/10.1016/j.rse.2012.07.010
[11]
Dlamini, W.M. (2017) Mapping Forest and Woodland Loss in Swaziland: 1990-2015. Remote Sensing Applications: Society and Environment, 5, 45-53. https://doi.org/10.1016/j.rsase.2017.01.004
[12]
Naidoo, L., Cho, M.A., Mathieu, R. and Asner, G. (2012) Classification of Savanna Tree Species, in the Greater Kruger National Park Region, by Integrating Hyperspectral and Lidar Data in a Random Forest Data Mining Environment. ISPRS Journal of Photogrammetry and Remote Sensing, 69, 167-179. https://doi.org/10.1016/j.isprsjprs.2012.03.005
[13]
Reyes-Palomeque, G., Dupuy, J.M., Portillo-Quintero, C.A., Andrade, J.L., Tun-Dzul, F.J. and Hernández-Stefanoni, J.L. (2021) Mapping Forest Age and Characterizing Vegetation Structure and Species Composition in Tropical Dry Forests. Ecological Indicators, 120, Article ID: 106955. https://doi.org/10.1016/j.ecolind.2020.106955
[14]
Gyamfi-Ampadu, E., Gebreslasie, M. and Mendoza-Ponce, A. (2020) Mapping Natural Forest Cover Using Satellite Imagery of Nkandla Forest Reserve, Kwazulu-Natal, South Africa. Remote Sensing Applications: Society and Environment, 18, Article ID: 100302. https://doi.org/10.1016/j.rsase.2020.100302
[15]
Peerbhay, K., Mutanga, O., Lottering, R., Bangamwabo, V. and Ismail, R. (2016) Detecting Bugweed (Solanum mauritianum) Abundance in Plantation Forestry Using Multisource Remote Sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 121, 167-176. https://doi.org/10.1016/j.isprsjprs.2016.09.014
[16]
Grabska, E., Hostert, P., Pflugmacher, D. and Ostapowicz, K. (2019) Forest Stand Species Mapping Using the Sentinel-2 Time Series. Remote Sensing, 11, Article No. 1197. https://doi.org/10.3390/rs11101197
[17]
Ramoelo, A., Cho, M., Mathieu, R. and Skidmore, A.K. (2015) Potential of Sentinel-2 Spectral Configuration to Assess Rangeland Quality. Journal of Applied Remote Sensing, 9, Article ID: 094096. https://doi.org/10.1117/1.jrs.9.094096
[18]
Wang, M., Zheng, Y., Huang, C., Meng, R., Pang, Y., Jia, W., et al. (2022) Assessing Landsat-8 and Sentinel-2 Spectral-Temporal Features for Mapping Tree Species of Northern Plantation Forests in Heilongjiang Province, China. Forest Ecosystems, 9, Article ID: 100032. https://doi.org/10.1016/j.fecs.2022.100032
[19]
Rösch, M., Sonnenschein, R., Buchelt, S. and Ullmann, T. (2022) Comparing Planetscope and Sentinel-2 Imagery for Mapping Mountain Pines in the Sarntal Alps, Italy. Remote Sensing, 14, Article No. 3190. https://doi.org/10.3390/rs14133190
[20]
Korhonen, L., Hadi, Packalen, P. and Rautiainen, M. (2017) Comparison of Sentinel-2 and Landsat 8 in the Estimation of Boreal Forest Canopy Cover and Leaf Area Index. Remote Sensing of Environment, 195, 259-274. https://doi.org/10.1016/j.rse.2017.03.021
[21]
Forkuor, G., Dimobe, K., Serme, I. and Tondoh, J.E. (2017) Landsat-8 vs. Sentinel-2: Examining the Added Value of Sentinel-2’s Red-Edge Bands to Land-Use and Land-Cover Mapping in Burkina Faso. GIScience & Remote Sensing, 55, 331-354. https://doi.org/10.1080/15481603.2017.1370169
[22]
Sibanda, M., Mutanga, O. and Rouget, M. (2016) Comparing the Spectral Settings of the New Generation Broad and Narrow Band Sensors in Estimating Biomass of Native Grasses Grown under Different Management Practices. GIScience & Remote Sensing, 53, 614-633. https://doi.org/10.1080/15481603.2016.1221576
[23]
Masemola, C., Cho, M.A. and Ramoelo, A. (2020) Sentinel-2 Time Series Based Optimal Features and Time Window for Mapping Invasive Australian Native Acacia Species in Kwazulu Natal, South Africa. International Journal of Applied Earth Observation and Geoinformation, 93, Article ID: 102207. https://doi.org/10.1016/j.jag.2020.102207
[24]
Persson, M., Lindberg, E. and Reese, H. (2018) Tree Species Classification with Multi-Temporal Sentinel-2 Data. Remote Sensing, 10, Article No. 1794. https://doi.org/10.3390/rs10111794
[25]
Axelsson, A., Lindberg, E., Reese, H. and Olsson, H. (2021) Tree Species Classification Using Sentinel-2 Imagery and Bayesian Inference. International Journal of Applied Earth Observation and Geoinformation, 100, Article ID: 102318. https://doi.org/10.1016/j.jag.2021.102318
[26]
Roffey, M. (2019) Vegetation and Tree Species Classification Using Multidate and High-Resolution Satellite Imagery and Lidar Data.
[27]
Cui, B., Huang, W., Ye, H. and Chen, Q. (2022) The Suitability of Planetscope Imagery for Mapping Rubber Plantations. Remote Sensing, 14, Article No. 1061. https://doi.org/10.3390/rs14051061
[28]
Rufin, P., Bey, A., Picoli, M. and Meyfroidt, P. (2022) Large-Area Mapping of Active Cropland and Short-Term Fallows in Smallholder Landscapes Using Planetscope Data. International Journal of Applied Earth Observation and Geoinformation, 112, Article ID: 102937. https://doi.org/10.1016/j.jag.2022.102937
[29]
Shimizu, K., Ota, T., Mizoue, N. and Saito, H. (2020) Comparison of Multi-Temporal Planetscope Data with Landsat 8 and Sentinel-2 Data for Estimating Airborne Lidar Derived Canopy Height in Temperate Forests. Remote Sensing, 12, Article No. 1876. https://doi.org/10.3390/rs12111876
[30]
Mudereri, B.T., Dube, T., Adel-Rahman, E.M., Niassy, S., Kimathi, E., Khan, Z., et al. (2019) A Comparative Analysis of Planetscope and Sentinel Sentinel-2 Space-Borne Sensors in Mapping Striga Weed Using Guided Regularised Random Forest Classification Ensemble. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2, 701-708. https://doi.org/10.5194/isprs-archives-xlii-2-w13-701-2019
[31]
Cao, J., Liu, K., Liu, L., Zhu, Y., Li, J. and He, Z. (2018) Identifying Mangrove Species Using Field Close-Range Snapshot Hyperspectral Imaging and Machine-Learning Techniques. Remote Sensing, 10, Article No. 2047. https://doi.org/10.3390/rs10122047
[32]
Adam, E., Deng, H., Odindi, J., Abdel-Rahman, E.M. and Mutanga, O. (2017) Detecting the Early Stage of Phaeosphaeria Leaf Spot Infestations in Maize Crop Using in Situ Hyperspectral Data and Guided Regularized Random Forest Algorithm. Journal of Spectroscopy, 2017, Article ID: 6961387. https://doi.org/10.1155/2017/6961387
[33]
Mureriwa, N., Adam, E., Sahu, A. and Tesfamichael, S. (2016) Examining the Spectral Separability of Prosopis Glandulosa from Co-Existent Species Using Field Spectral Measurement and Guided Regularized Random Forest. Remote Sensing, 8, Article No. 144. https://doi.org/10.3390/rs8020144
[34]
Acharki, S. (2022) Planetscope Contributions Compared to Sentinel-2, and Landsat-8 for LULC Mapping. Remote Sensing Applications: Society and Environment, 27, Article ID: 100774. https://doi.org/10.1016/j.rsase.2022.100774
[35]
Rohde, L.E., Clausell, N., Ribeiro, J.P., Goldraich, L., Netto, R., William Dec, G., et al. (2005) Health Outcomes in Decompensated Congestive Heart Failure: A Comparison of Tertiary Hospitals in Brazil and United States. International Journal of Cardiology, 102, 71-77. https://doi.org/10.1016/j.ijcard.2004.04.006
[36]
Thamaga, K.H. and Dube, T. (2017) Applications and Challenges, Remote Sensing Applications: Society and Environment.
[37]
Vrieling, A., Meroni, M., Darvishzadeh, R., Skidmore, A.K., Wang, T., Zurita-Milla, R., et al. (2018) Vegetation Phenology from Sentinel-2 and Field Cameras for a Dutch Barrier Island. Remote Sensing of Environment, 215, 517-529. https://doi.org/10.1016/j.rse.2018.03.014
[38]
Veloso, A., Mermoz, S., Bouvet, A., Le Toan, T., Planells, M., Dejoux, J., et al. (2017) Understanding the Temporal Behavior of Crops Using Sentinel-1 and Sentinel-2-Like Data for Agricultural Applications. Remote Sensing of Environment, 199, 415-426. https://doi.org/10.1016/j.rse.2017.07.015
[39]
Dlamini, W.M. (2016) Analysis of Deforestation Patterns and Drivers in Swaziland Using Efficient Bayesian Multivariate Classifiers. Modeling Earth Systems and Environment, 2, 1-14. https://doi.org/10.1007/s40808-016-0231-6
[40]
Wu, Y. and Zhang, X. (2019) Object-Based Tree Species Classification Using Airborne Hyperspectral Images and LiDAR Data. Forests, 11, Article No. 32. https://doi.org/10.3390/f11010032
[41]
Zhu, J., Pan, Z., Wang, H., Huang, P., Sun, J., Qin, F., et al. (2019) An Improved Multi-Temporal and Multi-Feature Tea Plantation Identification Method Using Sentinel-2 Imagery. Sensors, 19, Article No. 2087. https://doi.org/10.3390/s19092087
[42]
Cui, B., Huang, W., Ye, H. and Chen, Q. (2022) The Suitability of Planetscope Imagery for Mapping Rubber Plantations. Remote Sensing, 14, Article No. 1061. https://doi.org/10.3390/rs14051061
[43]
Wang, M., Zheng, Y., Huang, C., Meng, R., Pang, Y., Jia, W., et al. (2022) Assessing Landsat-8 and Sentinel-2 Spectral-Temporal Features for Mapping Tree Species of Northern Plantation Forests in Heilongjiang Province, China. Forest Ecosystems, 9, Article ID: 100032. https://doi.org/10.1016/j.fecs.2022.100032
[44]
Marcinkowska, A., Zagajewski, B., Ochtyra, A., Jarocińska, A., Raczko, E., Kupková, L., et al. (2014) Mapping Vegetation Communities of the Karkonosze National Park Using APEX Hyperspectral Data and Support Vector Machines. Miscellanea Geographica, 18, 23-29. https://doi.org/10.2478/mgrsd-2014-0007
[45]
George, R., Padalia, H. and Kushwaha, S.P.S. (2014) Forest Tree Species Discrimination in Western Himalaya Using EO-1 Hyperion. International Journal of Applied Earth Observation and Geoinformation, 28, 140-149. https://doi.org/10.1016/j.jag.2013.11.011
[46]
Mureriwa, N., Adam, E., Sahu, A. and Tesfamichael, S. (2016) Examining the Spectral Separability of Prosopis Glandulosa from Co-Existent Species Using Field Spectral Measurement and Guided Regularized Random Forest. Remote Sensing, 8, Article No. 144. https://doi.org/10.3390/rs8020144
[47]
Adam, E., Deng, H., Odindi, J., Abdel-Rahman, E.M. and Mutanga, O. (2017) Detecting the Early Stage of Phaeosphaeria Leaf Spot Infestations in Maize Crop Using in Situ Hyperspectral Data and Guided Regularized Random Forest Algorithm. Journal of Spectroscopy, 2017, Article ID: 6961387. https://doi.org/10.1155/2017/6961387
[48]
Richard, K., Abdel-Rahman, E.M., Subramanian, S., Nyasani, J.O., Thiel, M., Jozani, H., et al. (2017) Maize Cropping Systems Mapping Using Rapideye Observations in Agro-Ecological Landscapes in Kenya. Sensors, 17, Article No. 2537. https://doi.org/10.3390/s17112537
[49]
Raczko, E. and Zagajewski, B. (2017) Comparison of Support Vector Machine, Random Forest and Neural Network Classifiers for Tree Species Classification on Airborne Hyperspectral APEX Images. European Journal of Remote Sensing, 50, 144-154. https://doi.org/10.1080/22797254.2017.1299557
[50]
Ghosh, A., Fassnacht, F.E., Joshi, P.K. and Koch, B. (2014) A Framework for Mapping Tree Species Combining Hyperspectral and Lidar Data: Role of Selected Classifiers and Sensor across Three Spatial Scales. International Journal of Applied Earth Observation and Geoinformation, 26, 49-63. https://doi.org/10.1016/j.jag.2013.05.017
[51]
Suess, S., Van der Linden, S., Okujeni, A., Leitão, P., Schwieder, M. and Hostert, P. (2015) Using Class Probabilities to Map Gradual Transitions in Shrub Vegetation from Simulated Enmap Data. Remote Sensing, 7, 10668-10688. https://doi.org/10.3390/rs70810668
[52]
Wang, J., Xiao, X., Liu, L., Wu, X., Qin, Y., Steiner, J.L., et al. (2020) Mapping Sugarcane Plantation Dynamics in Guangxi, China, by Time Series Sentinel-1, Sentinel-2 and Landsat Images. Remote Sensing of Environment, 247, Article ID: 111951. https://doi.org/10.1016/j.rse.2020.111951
[53]
Ma, L., Li, M., Ma, X., Cheng, L., Du, P. and Liu, Y. (2017) A Review of Supervised Object-Based Land-Cover Image Classification. ISPRS Journal of Photogrammetry and Remote Sensing, 130, 277-293. https://doi.org/10.1016/j.isprsjprs.2017.06.001
[54]
Maldonado, S. and Weber, R. (2009) A Wrapper Method for Feature Selection Using Support Vector Machines. Information Sciences, 179, 2208-2217. https://doi.org/10.1016/j.ins.2009.02.014
[55]
Sothe, C., Almeida, C., Liesenberg, V. and Schimalski, M. (2017) Evaluating Sentinel-2 and Landsat-8 Data to Map Sucessional Forest Stages in a Subtropical Forest in Southern Brazil. Remote Sensing, 9, Article No. 838. https://doi.org/10.3390/rs9080838
[56]
Foody, G.M. and Mathur, A. (2004) A Relative Evaluation of Multiclass Image Classification by Support Vector Machines. IEEE Transactions on Geoscience and Remote Sensing, 42, 1335-1343. https://doi.org/10.1109/tgrs.2004.827257
[57]
Bazi, Y. and Melgani, F. (2006) Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 44, 3374-3385. https://doi.org/10.1109/tgrs.2006.880628
[58]
Zagajewski, B., Kluczek, M., Zdunek, K.B. and Holland, D. (2024) Sentinel-2 versus Planetscope Images for Goldenrod Invasive Plant Species Mapping. Remote Sensing, 16, Article No. 636. https://doi.org/10.3390/rs16040636
[59]
Kluczek, M., Zagajewski, B. and Zwijacz-Kozica, T. (2023) Mountain Tree Species Mapping Using Sentinel-2, Planetscope, and Airborne Hyspex Hyperspectral Imagery. Remote Sensing, 15, Article No. 844. https://doi.org/10.3390/rs15030844
[60]
Wang, W., Tang, J., Zhang, N., Wang, Y., Xu, X. and Zhang, A. (2023) Spatiotemporal Pattern of Invasive Pedicularis in the Bayinbuluke Land, China, during 2019-2021: An Analysis Based on Planetscope and Sentinel-2 Data. Remote Sensing, 15, Article No. 4383. https://doi.org/10.3390/rs15184383
[61]
Wessel, M., Brandmeier, M. and Tiede, D. (2018) Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data. Remote Sensing, 10, Article No. 1419. https://doi.org/10.3390/rs10091419
