Spatial Identification of Spruce Cultivation Areas in Rural Regions (Case Study: Ziābar Rural District, the City of Sowme'eh Sarā)

Document Type : Research Article - Case Study

Authors

1 Assistant Professor, Department of Regional Studies, Environmental Research Institute of Academic Center for Education Culture & Research (ACECR), Rasht, Iran.

2 Ph.D.in geography and rural planning, research expert, Jihad Daneshgahi Higher Education Institute of Guilan Province, Rasht, Iran.

3 Assistant Professor, Department of Civil Engineering and Surveying, Higher Education Institute of Guilan Province.

10.22124/gscaj.2026.26159.1276

Abstract

Wood cultivation and attention to sustainable development are of great importance in countries experiencing forest scarcity. Meanwhile, demand for wood products is steadily increasing at both national and international levels. Spruce is one of the most widely cultivated fast-growing tree species and is commonly used in forest plantations. This study aimed to improve the accuracy of optical image classification using machine learning by integrating optical and radar imagery. It also represented an effort toward the monitoring, control, and spatial management of rural areas, particularly from the perspective of agricultural activities, and can be considered a novel approach to rural development in the era of the information and technology revolution. In this research, Sentinel-1 and Sentinel-2 satellite imagery, including spectral bands and radar polarizations, along with a digital elevation model (DEM), were utilized. The Random Forest algorithm was employed as a powerful method for classifying large and imbalanced datasets. By integrating optical and radar satellite data and applying the Random Forest machine learning algorithm, spruce plantation areas were zoned. The area under spruce cultivation in the Ziābar Rural District was estimated at 2,650 hectares. The overall classification accuracy and Kappa coefficient were obtained as 83.2% and 0.754, respectively. Accordingly, the proposed method can be regarded as a robust approach for the monitoring, control, and spatial management of agricultural activities in rural areas at various spatial scales.

Highlights

  • The capabilities of the Google Earth Engine (GEE) platform were utilized for zoning spruce plantation areas.
  • Simultaneous overlay of processed satellite imagery, such as Sentinel data, with Google Earth imagery was performed within the platform.
  • This approach significantly reduced the extent of fieldwork required.

Keywords

Main Subjects

References

Ahmadloo, F., Rezaei, A., Farahpour, M., Calagari, M., & Mehrabi, A. (2021). Investigating the area and production of poplar plantations in Sowmeeh Sara city using field data and GIS. Ecology of Iranian Forest, 9(18), 159-168. [In Persian]
Alimohammadi, A., & Asadi, F. (2019). Evaluation of the growth performance of native poplar trees from Kermanshah and Zanjan provinces at the Alborz research station. Ecology of Iranian Forests, 7(14), 80-89. [In Persian]
Alizadeh Anaraki, K., Lashkarara, F., & Kiadaliri, H. (2012). Socio-economic factors affecting poplar cultivation development in Gilan province (Sowmehsara county). Iranian Journal of Forest and Poplar Research, 20(2), 346-356. [In Persian]
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Burkov, A. (2020). Machine learning engineering (Vol. 1). True Positive Incorporated.
Corona, P., Fattorini, L., Franceschi, S., Mastronardi, A., & Chirici, G. (2020). Probabilistic sampling and estimation for large-scale assessment of poplar plantations in Northern Italy. European Journal of Forest Research, 139(6), 981–988.
Colkesen, I., Lango, R., Khomutov, P., & G P. (2022). Poplar Tree Index (PTI): A New Vegetation Index for Monitoring Poplar Cultivated Areas. In IGARSS 2022—2022 IEEE International Geoscience and Remote Sensing Symposium (pp. 1234–1237). IEEE.
Chong, L., et al.,(2021). Monthly composites from Sentinel-1 and Sentinel-2 images for regional major crop mapping with Google Earth Engine. Journal of Integrative Agriculture, 20(7), pp, 1944-1957.
D’Amico, G., et al.,(2021). A deep learning approach for automatic mapping of poplar plantations using Sentinel-2 imagery. GIScience & Remote Sensing, 58(8), pp. 1352-1368.
Dobrinić, D., D. Medak, and M. Gašparović,(2020). Integration of multitemporal Sentinel-1 and Sentinel-2 imagery for land-cover classification using machine learning methods. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 43, pp. 91-98.
Erfani-fard, S. Y., & Lotfi-nasirabadi, M. (2023). Zonation of mangrove forest extent in Iran using Sentinel-2 imagery. Iranian Journal of Forest and Poplar Research, 2(31), 98-112. [In Persian]
Eslami, A.R,Sobhen Zahedi,Sh.,(2011). Providing poplar plantation map by Indian remote sensing (IRS) satellite imagery in Northern Iran. African Journal of Agricultural Research, 6(20), pp. 4769-4774.
Foga, S., et al.,(2017). Cloud detection algorithm comparison and validation for operational Landsat data products. Remote sensing of environment, 194, 379-390.
Ge, G., et al.,(2020). Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms. Global Ecology and Conservation, 22, pp. e00971.
Gong, P., et al.,(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), pp. 2607-2654.
Goudarzi, G., Ahmadloo, F., & Tabari, M. (2011). Investigation of growth, survival, and uniformity of different poplar clones in the selection nursery in Markazi province. Iranian Journal of Forest and Poplar Research, 19(4), 572-585. [In Persian]Hosienzadeh, O., Hajarian, M., & Parbar, S. (2016). Analysis of the aggregation coefficient of the poplar wood processing chain in Iran. Iranian Journal of Wood and Paper Industries, 7(1), 141-154. [In Persian]
Huang, Y., et al.,(2018). Agricultural remote sensing big data: Management and applications. Journal of Integrative Agriculture, 17(9), pp. 1915-1931.
Heide, S.C. (2002). Comparison of methods to detect conifer encroachment into aspen stands using Landsat 7 ETM+ satellite imagery, University of Idaho.
Jaafari, A. (2023). Mapping high poplar growth areas for bioenergy cultivation: A swarm-optimized approach. Renewable and Sustainable Energy Reviews, 187(9), pp. 11374-0.
Joshi, R., et al.,(2016). Transcription factors and plants response to drought stress: current understanding and future directions. Frontiers in Plant Science, 7, pp. 1029-1038.
Jin, X., et al.,(2018). A review of data assimilation of remote sensing and crop models. European Journal of Agronomy, 92, pp. 141-152.
Jia, M., et al.,(2021). Rapid, robust, and automated mapping of tidal flats in China using time series Sentinel-2 images and Google Earth Engine. Remote Sensing of Environment, 255, pp. 112285.
Kavzoglu, T., I. Colkesen, A. Atesoglu, H. Tonbul, E. Yilmaz, S. Ozlusoylu & M. Yusuf Ozturk (2024) Construction and implementation of a poplar spectral library based on phenological stages for land cover classification using high-resolution satellite images. International Journal of Remote Sensing, 45(6), 2049-2072.
Keshtkar, H., W. Voigt, and E. Alizadeh,(2017). Land-cover classification and analysis of change using machine-learning classifiers and multi-temporal remote sensing imagery. Arabian Journal of Geosciences, 10(6), pp. 1-15.
Luo, C., et al.,(2021). Using time series Sentinel-1 images for object-oriented crop classification in Google earth engine. Remote Sensing, 13(4), p. 561.
Mazzia, V., A. Khaliq, and M. Chiaberge,(2019). Improvement in land cover and crop classification based on temporal features learning from Sentinel-2 data using recurrent-convolutional neural network (R-CNN). Applied Sciences, 10(1): p. 238.
Machala, M. and L. Zejdová,(2014). Forest mapping through object-based image analysis of multispectral and LiDAR aerial data. European Journal of Remote Sensing, 47(1), pp. 117-131.
Matinfar, H., et al.,(2021). Evaluation of Machine Learning Methods in Digital Mapping of Soil Organic Carbon (part of Khorramabad Plain). JWSS-Isfahan University of Technology, 24(4), pp. 327-342.
Miraki, M., Sohrabi, H., Fatehi, P., and et al. (2024). Coupling UAV and satellite data for tree species identification to map the distribution of Caspian poplar. Landsc Ecol, 39, pp. 30-36.
Orynbaikyzy, A., U. Gessner, and C. Conrad, (2019). Crop type classification using a combination of optical and radar remote sensing data: A review. International journal of remote sensing, 40(17), pp. 6553-6595.
Ozturk, M. Y., & Colkesen, I. (2020). Mapping of poplar tree growing fields with machine learning algorithms using multi-temporal Sentinel-2A imagery. In 41th Asian Conference on Remote Sensing (ACRS) (pp. 1-4). Deqing, China.
Petropoulos, G.P., K. Arvanitis, and N. Sigrimis,(2012). Hyperion hyperspectral imagery analysis combined with machine learning classifiers for land use/cover mapping. Expert systems with Applications, 39(3), pp. 3800-3809.
Tonbul, H., I. Colkesen, and T. Kavzoglu,(2020). Classification of poplar trees with object-based ensemble learning algorithms using Sentinel-2A imagery. Journal of Geodetic Science, 10(1), pp. 14-22.
Vuolo, F., et al.,(2018). How much does multi-temporal Sentinel-2 data improve crop type classification? International journal of applied earth observation and geoinformation, 72, pp. 122-130.
Xu, Y., et al.,(2019). Advanced multi-sensor optical remote sensing for urban land use and land cover classification: Outcome of the 2018 IEEE GRSS data fusion contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(6), pp. 1709-1724.
Zurqani, H.A., et al.,(2020). Evaluating the integrity of forested riparian buffers over a large area using LiDAR data and Google Earth Engine. Scientific Reports, 10(1), pp. 1-16.

Files

Share

How to cite

Statistics