Production and Evaluation of Land Use and Crop Type Maps using Satellite Imagery and Data-Driven Learning-Based Models in the Isin Plain, Hormozgan Province

Document Type : Research Paper

Authors

1 M.Sc. Graduate, Department of Natural Resources Engineering, Faculty of Agriculture and Natural Resources, University of Hormozgan, Bandar Abbas, Iran.

2 Associate Professor, Department of Natural Resources Engineering, Faculty of Agriculture and Natural Resources, University of Hormozgan, Bandar Abbas, Iran.

3 , Associate Professor, Department of Natural Resources Engineering, Faculty of Agriculture and Natural Resources, University of Hormozgan, Bandar Abbas, Iran.

10.29252/aridbiom.2026.4231

Abstract

The aim of this study was to evaluate the performance of machine learning models in producing land use maps and identifying crop types, as well as to analyze land use changes during the 2014–2024 period in the Isin Plain, Hormozgan Province, Iran. Owing to its abundant freshwater resources and fertile soils, the Isin Plain has long been recognized as one of the major agricultural regions of the province. During field surveys, 898 ground truth points were collected for land use mapping, including orchards (mango, lemon, and date palm), croplands, fallow lands, barren lands, and built-up areas. In addition, 513 ground truth points were collected for crop type mapping, including eggplant, bell pepper, orchards, and barren lands. Landsat 8 imagery was used for land use mapping, while Sentinel-2 imagery was employed for crop type identification. Spectral vegetation indices were calculated to improve the discrimination accuracy of land use classes and crop types. Multicollinearity analysis and the Boruta algorithm were applied for feature selection. Random Forest (RF) and Support Vector Machine (SVM) algorithms were used for classification. The results showed that the SVM model achieved higher accuracy in land use classification (Overall Accuracy 87.48% and Kappa 83.64% in 2024) , whereas the RF model outperformed SVM in crop type classification (Overall Accuracy 89.29% and Kappa  84.59%). During the 10-year period, orchard, cropland, and fallow areas decreased, whereas barren lands and built-up areas increased. These changes resulted from the combined effects of natural and human factors. Reduced precipitation, prolonged drought, and declining groundwater resources led to the reduction of agricultural lands and orchards and the expansion of barren lands. In addition, increasing production costs, the proximity of the Isin Plain to Bandar Abbas, and urban expansion contributed to land use changes. Overall, the results demonstrate the high effectiveness of machine learning algorithms in producing accurate and practical land use and crop type maps.

Keywords

Main Subjects

References

[1]. Byerlee, D., Janvry, A., Sadoulet, E., Townsend, R. & Klytchnikova, I. (2008). Agriculture for Development. World Bank Washington ,DC ,pp: 2. doi: 10.1596/978-0-8213-6807-7
[2]. Congalton, R. G., & Green, K. (2019). Assessing the accuracy of remotely sensed data: principles and practices. CRC press. doi: 10.1201/9780429052729
[3]. Diek, S., Fornallaz, F., Schaepman, M. E., & De Jong, R. (2017). Barest pixel composite for agricultural areas using landsat time series. Remote Sensing, 9(12), 1245. doi: 10.3390/rs9121245
[4]. Ebrahimi-Khusfi, Z., Nafarzadegan, A. R., & Dargahian, F. (2021). Predicting the number of dusty days around the desert wetlands in southeastern Iran using feature selection and machine learning techniques. Ecological Indicators, 125, 107499. doi: 10.1016/j.ecolind.2021.107499
[5]. Gómez, C., White, J. C., & Wulder, M. A. (2016). Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of photogrammetry and Remote Sensing, 116, 55-72. doi: 10.1016/j.isprsjprs.2016.03.008
[6]. Haji Elyasi, A., Nasseri, M., & Badiei, P. (2024). Assessment of Land Use Changes Based on the Integration of Machine Learning Method and Spectral Angle Mapper Algorithm Using Training Samples Migration: A Case Study of Anzali Wetland Basin. Physical Geography Research, 56(4), 39-56. doi: 10.22059/jphgr.2025.384462.1007848 (in Farsi).
[7]. Han, X., Ye, H., Zhang, Y., Nie, C., & Wen, F. (2024). Study on the method of vineyard information extraction based on spectral and texture features of GF-6 satellite imagery. Agronomy, 14(11), 2542. doi: 10.3390/agronomy14112542
[8]. Huete, A., Didan, K., Miura, T., Rodriguez, E. P., Gao, X., & Ferreira, L. G. (2002). Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote sensing of environment, 83(1-2), 195-213. doi: 10.1016/S0034-4257(02)00096-2
[9]. Jensen, J. R. (1996). Introductory digital image processing: a remote sensing perspective.
[10]. Khalfi, J., & Davarpanah, G. R. (2006). Estimating the area and preparing a map of the lands under rainfed wheat cultivation using GIS and remote sensing in the Zanjan-Rood watershed. (in Farsi).
[11]. Khosravi, I. (2024). Crop Mapping from Landsat-8 Images Time Series Using Machine-Learning Methods (Case Study: Marvdasht in Fars Province). Geography and Environmental Planning, 35(2), 45-66. doi: 10.22108/gep.2024.138615.1601 (in Farsi).
[12]. Li, Y., Wang, W., Wang, G., & Tan, Q. (2022). Actual evapotranspiration estimation over the Tuojiang River Basin based on a hybrid CNN-RF model. Journal of Hydrology, 610, 127788. doi: 10.1016/j.jhydrol.2022.127788
[13]. McFeeters, S. K. (1996). The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7), 1425-1432. doi: 10.1080/01431169608948714
[14]. Moharmi, M., & Nisani, S. N. (1401/2022). Comparing the performance of partitioning and random forest methods in urban land cover classification (Case study: Tabriz city). (in Farsi).
[15]. Rashidi, F., & Jafari, A. (2014). Investigating the efficiency of supervised algorithms in land cover mapping using Sentinel 2 images in the Zagros forest habitat. Iranian Forest Journal, 16(1), 25–36. doi: 10.22034/ijf.2023.328404.1849 (in Farsi).
[16]. Rouse, J. W., Hass, R. H., Schell, J. A., & Deering, D. W. (1973). Monitoring vegetation systems in the Great Plains with ERTS. Proceedings of the third ERTS symposium, NASA SP-351, pp. 309−317.
[17]. Salehi, M., Mahdavi Najaf Abadi, R., Rezai, M., Nafarzadegan, A. R., & Ghorbani, M. (2025). Prediction of the Aquifer Status in the Isin-Bandar Abbas Plain Using a System Dynamics Model. Journal of Arid Biome, 15(1), 103-119. (in Farsi). doi: 10.29252/aridbiom.2026.3996
[18]. Singh, G., Singh, S., Sethi, G., & Sood, V. (2022). Deep learning in the mapping of agricultural land use using Sentinel-2 satellite data. Geographies, 2(4), 691-700. doi: 10.3390/geographies2040042
[19]. Sun, C., Bian, Y., Zhou, T., & Pan, J. (2019). Using of multi-source and multi-temporal remote sensing data improves crop-type mapping in the subtropical agriculture region. Sensors, 19(10), 2401. doi: 10.3390/s19102401
[20]. Xie, G., & Niculescu, S. (2022). Mapping Crop Types Using Sentinel-2 Data Machine Learning and Monitoring Crop Phenology with Sentinel-1 Backscatter Time Series in Pays de Brest, Brittany, France. Remote Sensing, 14(18), 4437. doi: 10.3390/rs14184437 
[21]. Xue, J., & Su, B. (2017). Significant remote sensing vegetation indices: A review of developments and applications. Journal of Sensors, 2017(1), 1353691. doi: 10.1155/2017/1353691
[22]. Yi, Z., Jia, L., & Chen, Q. (2020). Crop classification using multi-temporal Sentinel-2 data in the Shiyang River Basin of China. Remote Sensing, 12(24), 4052. doi: 10.3390/rs12244052
[23]. Zha, Y., Gao, J., & Ni, S. (2003). Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International journal of remote sensing, 24(3), 583-594. doi: 10.1080/01431160304987
[24]. Zhu, L., Radeloff, V. C., & Ives, A. R. (2017). Improving the mapping of crop types in the Midwestern US by fusing Landsat and MODIS satellite data. International journal of applied earth observation and geoinformation, 58, 1-11. doi: 10.1016/j.jag.2017.01.012
 
Journal of Arid Biome
Volume 16, Issue 1
March 2026
Pages 17-35

Files

Share

How to cite

Statistics