https://deej.kashanu.ac.ir/ Desert Ecosystem Engineering en daily 1 Fri, 22 May 2026 00:00:00 +0330 Fri, 22 May 2026 00:00:00 +0330 https://deej.kashanu.ac.ir/article_115383.html Introduction: Knowledge of land use/land cover (LULC) ratios and their temporal change trends constitutes a fundamental prerequisite for environmental planning. Understanding land use change is of particular importance in the context of land development processes. The application of remote sensing science to land use studies and the extraction of land use maps has proven successful in change detection and the formulation of associated management policies. In recent years, various algorithms have been developed for classifying different land use categories using remote sensing imagery. Consequently, identifying the optimal algorithm for a given classification approach is critical to obtaining accurate outputs. Among probability-based algorithms, Maximum Likelihood is the most common and accurate technique and is recognized as one of the most precise classification methods. The Support Vector Machine (SVM) algorithm is less sensitive to multidimensional phenomena. As a result, it is considered an appropriate method for the classification of multispectral and hyperspectral data. One of the advantages of the SVM algorithm is its ability to produce an optimally classified map using a limited number of training samples. Accordingly, this reduces costs and increases classification speed. Random Forest is another machine learning algorithm, based on a complex ensemble of decision trees. In this method, each classification is derived from a random vector that is independent of the input. Each tree assigns a separate class to every vector that exhibits the highest correspondence with that class. Material and Methods: In this research, Landsat 8 (OLI) multitemporal image data from 2013, 2017, and 2019 were utilized to extract land use/land cover (LULC) change detection in the Gorganroud basin, located in Golestan Province. The Landsat 8 data within the study period represent the most stable images for extracting and mapping LULC change detection. Radiometric corrections were applied using the Chavez and Dark Subtraction methods. Furthermore, the Histogram Matching algorithm was employed to prepare satellite imagery for processing purposes. In this method, recent panchromatic data, along with intensity components extracted from RGB multispectral data, were matched using the histograms of the data. To assess the accuracy of the extracted maps, an error matrix was utilized. Accuracy assessment required ground truth images or regions of interest, which were obtained from a field survey conducted in 2017. In the error matrix, the raw data were compared with the classified data. In most studies, the Kappa coefficient is employed to evaluate the accuracy of results derived from different classification methods. To investigate and detect changes, the histogram matching method of multitemporal images was first applied based on a reference year, followed by the image difference method. Results: Evaluation of the results derived from accuracy indices, along with comparison to the locally derived map obtained through in-person field monitoring, demonstrates the high accuracy of the algorithm applied in this study. Furthermore, it confirms the effectiveness of Landsat 8 imagery in extracting land use/land cover (LULC) maps. The results reveal that, between 2013 and 2019, forest lands experienced a slight decrease. Dry lands also underwent gradual changes. Bare soil areas increased significantly; however, after two years, their area expanded further, indicating a reduction in natural plant cover. Should this trend continue, the region will face forest loss and conversion to rainfed agricultural lands.    In the Maximum Likelihood method, rainfed lands, forests, and areas with scattered plant cover followed distinct trends. The forest change trend remained stable, whereas residential areas, rainfed lands, and scattered plant cover areas increased gradually. Based on the accuracy values obtained from the Random Forest and Support Vector Machine methods, it can be concluded that these methods are more accurate than the Maximum Likelihood method. In contrast, wetlands and forests exhibit a declining trend. Discussion and Conclusion: The study area is facing forest destruction and an increase in dry lands at higher elevations. Consequently, land use/land cover change detection must be taken into account in the future to prevent and control flooding in the region. Accordingly, it can be stated that during the study years, land cover in the region has changed gradually; however, no pronounced or significant changes have occurred over the short term. If the current trend continues, it is predictable that forests may convert to agricultural or rainfed lands. Such a transformation could lead to increased water consumption and the decline of wetlands. As water resources diminish, unused lands are likely to expand due to a reduced capacity for water supply. The results of comparing the three classification methods—Random Forest, Support Vector Machine (SVM), and Maximum Likelihood—indicate that Random Forest and SVM yield more comparable results, whereas Maximum Likelihood produces different outputs relative to these two methods. Based on the extracted maps, it is evident that Random Forest and SVM provide more accurate and reliable results. From these findings, it can be concluded that in steeper areas, forests are decreasing while plowed lands are increasing, which may contribute to flooding in the region. Therefore, future water supply for the residents is likely to become a critical issue. https://deej.kashanu.ac.ir/article_115444.html Introduction Analysis of land surfaces and plains plays a crucial role in natural resource studies. From a geomorphological perspective, landforms are generally classified into three major units: mountains, plains, and playas. Pediment plains are further subdivided into three types: bare pediment, coalescing pediment, and concealed pediment. Traditionally, field surveys, visual interpretation, and boundary delineation using Google Earth have been employed to identify pediment types. In this study, a novel approach based on fractal geometry techniques was applied. According to Mandelbrot, fractal geometry is grounded in the concept of objects exhibiting self-similar and repetitive patterns across different scales. The objective of this research is to apply fractal analysis in order to characterize the hydrographic networks of different pediment geomorphological types in desert environments. Research Methodology The study area covers 1,441.91 km² in the Yazd-Ardakan plain, located within Zone 40. Satellite imagery from the Advanced Land Observing Satellite (ALOS) PALSAR was selected through the Earthdata Search portal (earthdata.nasa.gov) due to its high-resolution Digital Elevation Model (DEM) capabilities. Using the Hydrology Toolbox in ArcGIS, the hydrographic network was extracted from the DEM. Random plots of varying sizes were selected on the hydrographic network. Fractalyse software was employed to compute the fractal dimension of plots measuring 1, 4, 9, 16, and 64 km² at a scale of 1:50,000 using the box-counting method. The mean and variance of the fractal dimension across plots in each pediment type were calculated, and diagrams were generated to determine the minimum sampling area. For validation, 10 observed plots and 10 estimated plots were compared within a 9 km² plot (the minimum sample area) in each pediment type. The Kolmogorov–Smirnov test and independent t-test were conducted at the 99% confidence level using SPSS software. Model performance was further evaluated using the Root Mean Square Error (RMSE), Nash–Sutcliffe Efficiency (NSE), Pearson’s correlation coefficient (r), scatter plots, regression equations, slope coefficients, and the coefficient of determination (r²). Results   Table 1. Number and distribution of sampling plots based on size and type of pediment plain Plot side length (km) Plot area (km2) Total number of plots Number of plots in each pediment Bare pediment Coalescing pediment Concealed  pediment 1 1 190 51 84 55 2 4 111 33 44 34 3 9 62 20 22 20 4 16 34 12 12 10 8 64 16 5 5 6     Table 2. Mean fractal dimension of hydrographic networks across plots with different areas. Plot area (km2) Bare pediment Coalescing pediment Concealed  pediment 1 1.168 1.178 1.119 4 1.273 1.277 1.269 9 1.418 1.409 1.363 16 1.427 1.409 1.396 64 1.508 1.499 1.489   Discussion and conclusion The point at which the variance diagrams of the fractal dimension become linear and stabilized—referred to as the turning point of the diagram—indicates the minimum sampling area, which in this study was identified as 9 km² plots. From this threshold onward, the fractal dimension of the hydrographic networks consistently decreased from erosional pediments toward covered pediments. According to the diagrams, the minimum number of samples required for erosional pediments, alluvial fan pediments, and covered pediments is 15, 17, and 18 plots, respectively. The Kolmogorov–Smirnov test confirmed the normality of the data (p > 0.05), while the independent t‑test showed no significant differences between observed and estimated data (p > 0.05) at the 99% confidence level. The RMSE and NSE indices indicated low model error and high predictive accuracy for bare pediment and coalescing pediment. In concealed pediment, RMSE values were close to zero, confirming highly accurate predictions, while NSE also demonstrated acceptable model performance. The results of Pearson's correlation coefficient (r), regression coefficient, and coefficient of determination (r²) for all three pediment types indicate a strong positive correlation between observed and estimated data, reflecting very good model performance. Overall, for the 9 km² plots—identified as the minimum sampling area—the fractal dimensions of bare pediment, coalescing pediment, and concealed pediment were 1.418, 1.409, and 1.363, respectively. These results highlight the effectiveness of the fractal geometry technique in geomorphological characterization and hydrographic network analysis in arid regions. https://deej.kashanu.ac.ir/article_115446.html In the mining and steel industry situated in arid lands, significant concentrations of particulate matter (PM) are emitted from raw material storage sites, particularly from iron ore piles and concentrate storage piles. In this study, the effectiveness of BDS mulches, a novel biopolymer-based mulch, was compared with slurry lime and sugarcane molasses as conventional compounds for covering iron concentrate storage piles to control wind erosion. The experiments were conducted using a factorial design within a randomized complete block design. BDS at concentrations of 1% and 2%, slurry lime at 10%, and molasses at 20% solution concentrations were prepared. Each treatment was sprayed onto three trays filled with concentrate. The prepared sample trays were subjected to wind erosion tests in a wind tunnel after 1, 2, and 3 weeks following preparation. Among the selected treatments, BDS at 2% (BDS2%) exhibited the highest efficiency, reducing wind erosion to 0.34 kg/m²/h compared to 2.1 kg/m²/h in the control treatment, and increasing the erosion threshold velocity to 54 km/h, whereas the control had a threshold of only 26 km/h. Slurry lime offered lower resistance to wind erosion, with an erosion rate of 1.8 kg/m²/h and a threshold velocity of 39.6 km/h. The effectiveness of molasses and BDS at 1% (BDS1%) was similar, with erosion rates of 1.1 and 1.2 kg/m²/h, and threshold velocities of 47.5 and 48.2 km/h, respectively. Moreover, the effectiveness of the mulches diminished over time, with erosion rates increasing by an average of 35–50% from week 1 to week 3. Considering the advantages of the new material—including environmental compatibility, no negative effects on pellet quality, and favorable efficiency in protecting against wind erosion—it can replace conventional compounds as a mulch for iron concentrate piles. https://deej.kashanu.ac.ir/article_115447.html Classification and labeling of satellite images in remote sensing (RS), as well as improvement in their classification accuracy, have received researchers' attention for decades. The present study compares two classification methods—namely, the Rule-Based Fuzzy System and the proposed Wavelet Feature-Based Minimum Distance (W-F-M-D) algorithm—for medium-resolution images, particularly in heterogeneous landscapes. The Advanced Land Imager (ALI) was studied in an area located in southwestern Tehran, Iran. For validation, the land cover map obtained from both methods was compared with ground truth data through confusion matrix analysis, Kappa coefficient, and overall accuracy. The best results for the W-F-M-D algorithm were achieved with an overall accuracy of 93.55% and a Kappa coefficient of 0.89. Meanwhile, the results obtained from the fuzzy method were also satisfactory, with an overall accuracy of 89.27% and a Kappa coefficient of 0.84. However, the simplicity and speed of the proposed W-F-M-D algorithm constitute an additional advantage over the fuzzy method. From a different perspective, in the heterogeneous urban-agricultural area with moderate spatial resolution, the accuracy obtained for the urban area map—compared to that of bare lands—using the W-F-M-D method was evaluated as satisfactory, with producer's accuracy of 99.25% and user's accuracy of 91.67%. https://deej.kashanu.ac.ir/article_115448.html Introduction: Dust storms are considered one of the most significant extreme climate phenomena in arid and semi-arid regions, with widespread consequences for health, the environment, and natural resource management. Despite extensive research efforts, accurately predicting the occurrence and intensity of dust storms remains a substantial scientific challenge due to the nonlinear, multiscale, and highly dynamic interactions among atmospheric, land surface, and climatic factors. Traditional numerical and statistical models often struggle to capture such complex relationships, leading to considerable uncertainties in forecasts. In this context, recent advances in deep learning have opened new avenues for modeling complex environmental phenomena. Deep learning models, particularly those capable of learning long-term temporal dependencies and spatial patterns, offer promising tools for improving dust storm prediction. This research, which aims to evaluate the capabilities of novel deep learning models for predicting dust storms, investigated the performance of two individual models—Autoformer and Fourier Neural Operator (FNO)—as well as a hybrid framework based on the combination of these two models across several temporal configurations. Materials and Methods: This research aims to improve the accuracy of dust storm forecasting by evaluating the predictive performance of advanced deep learning models under different temporal input structures. Two modern architectures were selected for this purpose: the Autoformer model, known for its ability to capture long-term temporal dependencies in time series data, and the Fourier Neural Operator (FNO), which is specifically designed to learn complex spatial-spectral patterns through frequency-domain representations. In addition to assessing these models individually, a hybrid FNO-Autoformer framework was developed to combine their complementary strengths. The dust storm intensity index, representing the severity and frequency of dust events, was selected as the target variable. Ilam Province was chosen as the case study area due to its high exposure to dust storm activity and its climatic vulnerability. To investigate the influence of temporal input structure on model performance, four distinct temporal configurations were designed, ranging from short-term to long-term forecasting horizons. These configurations included time lags from one season up to one year, enabling a comprehensive analysis of how prediction horizon affects model accuracy. Following appropriate pre-processing, the data were divided into training (80%) and testing (20%) sets. Model performance was evaluated using the following statistical metrics: Nash–Sutcliffe efficiency (NS), root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R). Results: The results of this study revealed that the Autoformer model exhibited the weakest performance in predicting the FDSD index across all temporal configurations and was associated with relatively high error in reproducing extreme variations in dust storms. Although the FNO model performed better than Autoformer in extracting spatio-temporal patterns, as a standalone model it still did not achieve acceptable forecasting accuracy and showed no significant difference from Autoformer. In contrast, the hybrid FNO-Autoformer model, by integrating the strengths of FNO in learning spatio-spectral patterns and the capability of Autoformer in modeling long-term temporal dependencies, demonstrably provided the best performance across all evaluation metrics. High values of the NS index, a significant reduction in RMSE and MAE errors, and an increase in the correlation coefficient confirmed the clear superiority of this hybrid framework over the individual models. The results also indicated that short-term temporal configurations, particularly forecasts with a one-season lag, achieved the highest accuracy, and that the models' forecasting accuracy decreased with increasing time lag. This finding highlights the sensitivity of data-driven models to the temporal structure of inputs and the importance of selecting an optimal prediction horizon in dust storm modeling. Discussion and conclusion: Overall, the findings of this research emphasize the crucial role of hybrid spatio-temporal frameworks in predicting extreme climate events and demonstrate that integrating Fourier Neural Operators with transformer-based models can represent an effective step toward developing more accurate forecasting systems and reducing uncertainty in dust hazard management. The study also highlights the strong influence of temporal input configuration on forecasting outcomes, suggesting that careful consideration of time lag selection is essential for optimizing model performance. From a practical perspective, improved dust storm prediction can contribute to more effective early warning systems, risk mitigation strategies, and sustainable environmental management. Moreover, the successful integration of spectral neural operators with transformer-based architectures represents a promising direction for future research in climate hazard modeling. Such hybrid approaches have the potential to reduce predictive uncertainty, support decision-making processes, and enhance resilience to extreme climatic events in vulnerable regions. https://deej.kashanu.ac.ir/article_115449.html Introduction Sorghum is a highly productive forage crop, recognized for its adaptability to a wide range of soils and climatic conditions, its drought tolerance, and its suitability for use as both fresh and dry forage. Abiotic stresses, particularly drought, significantly limit agricultural productivity, especially in arid and semi-arid regions. To mitigate the effects of drought, strategies such as the use of drought-resistant species and mulching can be employed. Furthermore, the construction of windbreaks can help moderate the effects of strong winds. According to our background review, no research has been conducted on the simultaneous effects of mulch and windbreaks in reducing the negative impacts of drought stress on sorghum growth and weed control. The aim of this study is to investigate the effect of mulch and windbreaks on mitigating the negative effects of drought on sorghum, to classify different mulches based on their ability to alleviate stress-related damage, and to evaluate their role in weed control. Materials and Methods Seeds of the forage sorghum variety 'Speed Feed' were obtained from a reputable agricultural supplier. Sorghum was sown in early May 2025. Pre-planting mulch treatments—including black plastic, white plastic, straw, cardboard, and a control with no mulch—were applied. Drip irrigation was used throughout the experiment. Drought stress was applied at the six-leaf stage by maintaining soil moisture at three levels: 90%, 50%, and 25% of field capacity. To mitigate wind effects, sunflower windbreaks were planted one month before sorghum sowing and positioned perpendicular to the prevailing wind direction around the plots. Considering that the protective effect of grass windbreaks typically extends to 5–10 times their height, the distance between the sunflower row and the first sorghum plot was set at one times the final plant height in order to maintain the protective effect while minimizing shading and competition. Weed control was performed on three dates: 16 May 2025, 14 June 2025, and 9 July 2025. Forage sorghum was harvested at the soft-dough seed stage. Average plant height was measured in centimeters using a ruler. The fresh and dry weights of both shoots and roots were measured using a precision balance with an accuracy of 0.01 g. All data were analyzed using analysis of variance (ANOVA) in SPSS software, and means were compared using Duncan's multiple range test at a 5% probability level (α = 0.05). Result Mulch application, particularly white and black plastic mulch, significantly reduced weed density. Under severe drought stress conditions and in the absence of windbreaks, white plastic mulch reduced weed counts by 99.5%, 96.5%, and 98.68% on the three sampling dates, respectively, compared to the no-mulch control. Plastic mulches also produced the greatest reduction in weed biomass across all sampling dates. Plant height was likewise influenced by mulch type. Under severe drought stress and without windbreaks, white and black plastic mulches increased sorghum height by 37% to 76% across the five growth stages relative to the unmulched control. In addition, mulch treatments enhanced sorghum biomass. Under severe drought and without windbreaks, white plastic mulch increased shoot fresh and dry weight by 69% and 72%, respectively, compared to the control. Cardboard mulch also increased root fresh and dry weight by 72.9% and 72%, respectively. Overall, mulch application effectively alleviated the negative effects of drought stress by reducing weed infestation and significantly increasing sorghum height, as well as the fresh and dry weight of both shoots and roots. Discussion Drought stress significantly reduced both weed density and biomass. This effect was further amplified by mulch application, which significantly reduced weed density and biomass across all sampling dates, likely due to a shading effect that limits weed establishment and growth. Plant height also decreased significantly with increasing drought stress, likely as a consequence of reduced meristematic cell production under limited water availability. However, mulch application mitigated this effect and significantly increased plant height. By conserving soil moisture and improving water availability to plants, mulch enhances physiological processes critical for growth, such as cell turgor and cell division. Furthermore, plant height was greater in plots protected by windbreaks than in unprotected plots. Similarly, drought stress significantly reduced the fresh and dry weight of both roots and shoots by limiting plant-available water. Mulch application counteracted this reduction by reducing evaporation from the soil surface, thereby maintaining a more favorable soil moisture regime for sustained plant growth https://deej.kashanu.ac.ir/article_115445.html This Research was conducted as a three-factorial factorial experiment in a randomized complete block design with three replications and for six months in field conditions. The factors studied included plant growth-promoting bacteria (four levels: no inoculation, inoculation with Bacillus halotolerans, inoculation with Bacillus amyloliquefaciens and simultaneous inoculation of both bacteria), irrigation water salinity stress (four levels: control 0.3, 4, 8 and 12 dS/m) and biosolids (three levels: no application, application 10 and 30 tons/ha). The results showed that salinity had a significant effect on reducing the uptake of elements, such that the uptake of phosphorus (20.3%), potassium (32.6%), calcium (31.7%) and chlorophyll (14.1%) decreased. In contrast, salinity stress led to an increase in antioxidants (160.3%), total phenols (88.2%) and proline (112%).. Simultaneous application of biosolids and bacteria increased leaf magnesium and calcium content by 10 and 11%, respectively. Under saline irrigation conditions, bacteria increased potassium (32.4%), calcium (37.6%), and phosphorus (60.1%) uptake and decreased sodium uptake by 32.5%. Bacterial inoculation, especially the combination of the two bacteria, increased soluble sugars (39.3%) and proline (137.7%) and decreased antioxidants (110.2%) and phenols (65.3%). Finally, inoculation of B. halotolerans and B. amyloliquefaciens bacteria improved plant tolerance to salinity. These results emphasize the need to integrate microbiological approaches and organic resource management in saline land reclamation programs.