Search published articles


Showing 2 results for Vegetation Indices
Comparison of Rangeland Vegetation Cover and Soil Properties Variations Affected by Flood Spreading, Enclosure and Grazing Uses
F. Jalilian, B. Behmanesh, M. Mohammad Esmaeili, P. Gholami,
Volume 21, Issue 2 (8-2017)
Abstract

In this study, different indices of vegetation cover variations and different physicochemical properties of soil in three treatments of flood spreading, enclosure and grazing (control) were investigated and compared in in the region of Peshert in Mazandaran province. In order to measure different soil characteristics, 18 soil samples (six withdrawals at any treatment) from a depth of zero to 30 cm were taken from the desired treatments. In order to investigate different vegetation indices, a total of 90 plots (nine transects of 100 m) were run using systematic random sampling in the studied treatments and the necessary measurements were done (30 plots at any treatment). Then, in each of these plots, canopy coverage percentage was determined separately for each species and to evaluate and assess the diversity and richness in all three treatments, Shannon-Wiener and Simpson diversity indices and Menhink and Margalef richness indices were used. Finally, the data obtained from both sections of soil and vegetation in three studied treatments were compared and analyzed using one-way ANOVA and Duncan test. The results showed that floodwater spreading and enclosure significantly increased the percentage of sand and total Nitrogen, and significantly reduced the percentage of silt and potassium compared to control treatment. Also, percentage of clay and organic matter, soil pH levels, conductivity and soil phosphorus showed no significant differences in the treatments under study. The results of variance analysis of various indices of diversity, richness and species evenness showed that all indicators had significant responses in three treatments and the highest diversity and species richness were observed in flood spreading and enclosure treatments. Due to changes in soil properties and vegetation in flood spreading and enclosure treatments compared to the control treatment, it can be stated that operations of floodwater spreading and enclosure in the studied region has had positive effect on modification of soil texture, increasing the permeability of the soil and ultimately improvement of the vegetation.


Wheat Production Simulation Using Sentinel 2 Images and Machine Learning Techniques
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.

Page 1 from 1     

© 2025 CC BY-NC 4.0 | Journal of Water and Soil Science

Designed & Developed by: Yektaweb