H. Ramezani Etedali, M. Ahmadi,
Volume 29, Issue 2 (7-2025)
Abstract
change, accurately predicting wheat production is essential for developing precision agriculture. Remote sensing enables the indirect prediction of crop production before harvest. This research investigates the application of the random forest method and support vector regression for simulating wheat production across ten selected farms in Qazvin Plain from 2019 to 2020, employing NDVI, MSAVI, and EVI vegetation indices. Sentinel 2 satellite data was utilized for the vegetation indices. Production data for the ten wheat fields was obtained from the Agricultural Jihad Organization of Qazvin Province. Evaluation of support vector regression and random forest to assess both the observed and simulated wheat production data was conducted using R2, MBE, RMSE, and MAE statistics. To explore the simulation of wheat production using vegetation indices, seven methods were defined: methods 1 to 3 examine each index separately; methods 4 to 6 focus on binary combinations of the indices; and method 7 considers the combined effects of all three indices. The support vector regression model provided good estimates of wheat production in all methods, except methods one and four, in the test phase, with a coefficient of determination of more than 0.98 and a low RMSE. The random forest model showed significant results in all methods except methods two and six during the test phase, achieving a 95% probability (P-value=0.00) with a coefficient of determination greater than 0.8. Overall, this research highlights the importance and potential of machine learning techniques for timely crop production prediction as a strong foundation for regional food security.
Mehdi Feyzolahpour, Manizheh Ahmadi,
Volume 29, Issue 3 (10-2025)
Abstract
Drought is a hazard that can have widespread impacts on biodiversity, wildlife habitats, and ecosystem stability. The present study investigated the drought situation in the Bonab rural district. To assess the drought situation during the period 2013 to 2024, the Normalized Difference Vegetation Index (NDVI), Water Index (NDWI), Moisture Index (NDMI), Soil Adjusted Vegetation Index (MSAVI), and Land Surface Temperature (LST) were used. The results showed that the maximum value of the NDWI index reached from 0.16 in 2013 to 0.14 in 2024, which indicates an intensification of drought. However, the maximum value of the NDVI increased from 0.53 in 2013 to 0.58 in 2024, and the value for the MSAVI index for the years 2013 and 2024 was 0.69 and 0.73, respectively. All indices except the NDWI index had a negative correlation with the LST index, and the MSAVI index had the highest negative correlation with a Pearson coefficient of -0.39 in 2013. The results are also consistent with the results obtained from the SVM model. It is also observed that the area of barren lands has decreased from 887 square kilometers in 2013 to 851 square kilometers in 2024.
Homa Chegini, Chooghi Bairam Komaki, Majid Owneq, Hamidreza Asgari, Khalil Ghorbani,
Volume 30, Issue 1 (3-2026)
Abstract
This study aimed to analyze the spatial–temporal correlation between the Vegetation Health Index (VHI) and climatic variables, including precipitation, potential evapotranspiration (PET), and mean temperature, in Golestan Province during the period 2000–2024. MODIS satellite products were used for vegetation and land surface temperature data, while the TerraClimate dataset provided precipitation and PET variables. After spatial–temporal alignment, the Cross-Correlation Function (CCF) was applied to identify optimal time lags, and the Random Forest model was employed to assess the relative importance of the climatic drivers. Turning to the results, increasing trends in mean temperature and PET were observed, alongside a significant decrease in precipitation, which led to intensified climatic stress and reduced VHI across the province, especially during summer in croplands and rangelands. The relationship between VHI and precipitation was positive (maximum correlation of 0.299 in croplands), negative with PET (−0.287), and non-linear with temperature (0.275). Notably, VHI responded to precipitation with short-term lags (0–1 month), whereas PET and temperature effects emerged with longer lags (2–4 months). The Random Forest analysis highlighted precipitation as the most influential factor on VHI, followed by PET and temperature, achieving strong predictive performance (R² = 0.78, RMSE = 0.09). Overall, these findings emphasize precipitation as the immediate driver of vegetation health, while PET and temperature act as secondary, cumulative stressors. The results provide valuable insights for developing climate adaptation and sustainable resource management strategies in agriculture and natural ecosystems of Golestan Province.
