نشریه علوم و فنون نقشه برداری
سال سیزدهم شماره 2 (پیاپی 50، پاییز 1402)

Gossans are the easiest and fastest way to explore subsurface resources and actually represent mineral zones on the earth's surface. Gossans that have important mineral resources such as copper and gold are called true gusans. The aim of this study was to identify true Gossans in small exploration areas. In this paper, an algorithm for deep convolutional cane crusts was designed. In the proposed algorithm, first preprocessions such as geometric and spectral correction and restoration, division of satellite images into smaller images and amplification of training data are performed to prepare RGB data to enter the chip. The proposed CNN cane has a encoder-decoder structure that in the coding stage different and efficient features are extracted at different scales and in the decoding stage the generated features are combined to estimate the Gossan regions. Then, the desired network was implemented for the images of the studied exploratory area called "Tal Bargah" located in Darab city and the Gossan areas of the region were extracted. For field evaluation of the obtained results, the results of the network and its location on the copper orthodontic interpolation map of the region and review of the integrated lithological results and the real gusans of the region with statistical accuracy of sensitivity parameters: 0.957, F1 score: 0.457, rock detection accuracy 92% and average Copper grade above 4% was detected in these areas.

Road and urban transport network facilitate our daily life for optimal routing. In the road network, traffic management is one of the main challenges of managers. In this regard, the first step is to estimate the density of cars at the level of the urban road network. Estimating the number of cars or the level of occupancy of cars in the whole city, taking into account less time and cost, is only possible with satellite images. In this regard, in this research, satellite images with high spatial resolution available and downloadable from the Google Earth system have been used. To identify the position of the cars, the single shot deep learning method with RetinaNet architecture and based on residual neural networks with the number of layers 18, 34 and 50 have been used. For the training data, the position of the cars is marked with bounding boxes and then satellite images with dimensions of 128 x 128 pixels and 64 pixels pitch are cut. Of the total training data, 80% have been used for training and 20% for validation. The models were trained in 50 epochs and with an average accuracy of 0.7. Satellite images containing more than 15000 cars was used to evaluate the trained models. The parameter of the possibility of overlapping of the non-maximum suppression method was applied equal 25%. The final result shows that the use of the proposed model in the identification of cars has a good accuracy. The RetinaNet detector model based on the residual deep learning network with 50 layers has performed best in terms of average accuracy with 0.87, precision with 0.7, recall with 0.99 and F1-score with 0.82. The main challenge of the proposed models is in areas with high car density, which reduces the possibility of accurately detecting the number of cars due to the size of the ground sampling distance of satellite images, but it estimates the occupancy level better.

Natural phenomena in the world, such as earthquakes and heavy rains, which are sometimes combined with wind storms, can cause landslides. These landslides in one area can damage several parts and cause significant damage to natural and human infrastructure. Landslides occur in almost all countries of the world and play an important role in the changing of the earth's surface. There are different geodetic and non-geodetic methods to measure the changes caused by this phenomenon. Geodetic methods are not suitable for preparing a landslide damage map due to their limitations such as high cost and time consuming. Therefore, we have to use non-geodetic methods. Nowadays, the use of remote sensing techniques has received much attention. Radar images have been proposed as a suitable tool for monitoring landslides due to their high spatial resolution, wide view, the possibility of capturing in any kind of weather conditions and during the night, the high frequency of spatial and temporal observations, and acceptable accuracy. In addition, there are various methods for extracting information from this type of data, most of which require large initial data, and time-consuming processing. But in this research, we are trying to produce a landslide damage map by using the least input data and in the shortest possible time (no need to spend time for downloading all the required data). Therefore, the method used in this research is the use of Sentinel-1A RADAR images and processing these images in the Google Earth Engine (GEE) processing platform. In this article, we will prepare landslide damage map by examining the changes in the backscattering coefficient image (σ° ) between before and after landslide RADAR images. In this research, by having two sets of images related to before and after the occurrence of the landslide in ASC and DSC pass mode, we can produce the Iratio image between the image before and after the landslide for ASC and DSC mode. After that, we can average between IratioASC and IratioDSC to produce the IratioAverage. After producing this image and removing areas that cause errors and ambiguity, such as seas and lakes, agricultural areas, deforested areas, etc. finally, by determining a suitable threshold, it is possible to detect landslide areas. In order to evaluate the accuracy, since the lack of ground data in the study area, the generated landslide map was compared with Sentinel-2 optical sensor images and the results showed a high agreement between these two data sets, and this shows the high accuracy of the proposed method.

Tourism as a distinguished 21st-century phenomenon requires capital flows, people, cultures and a persistent interaction between the aforementioned variables. The significance of tourism in this era depends mostly on its economic cycle; And high economic dynamism, both locally and internationally, has led to the expansion and development of the spectrum of services in this field. One of the pillars of this development is the use of public information, which is a very powerful and diverse dataset that can be used for free in spatial decision making. Among the spatial decision-making criteria in tourism is the analysis of datasets regarding restaurants, which can be used to measure their general performance in terms of service. Therefore, in this research, a series of public-opinion-based information in regards to restaurants were collected from different social networks; And the goal is to examine the quality of service for restaurants in different geographic units with the help of STFTiS model. In this regard, the information obtained from users' comments after preparation and sorting were processed with the help of clustering methods. Thereupon, after clustering results and the ratings given by users across all cities of Mazandaran province were integrated, by analysing the correlation between them and status of tourism in those cities, the results could be validated and policies regarding the development of restaurants across the province could be planned. The results obtained are that the cities of Ramsar, Nowshahr, Tankabon and Mahmudabad are cities with good performance in terms of tourism and services. Also, the similarity of 4 out of 5 cities that can be developed in the results of the proposed method compared to similar articles obtained from other methods shows an 80% match.

The shortage and restriction of drinking water and even water consumption in many water-scarce countries of the globe, including Iran, has become an essential and vital issue. This is one of the key reasons that people and communities maximize the development of crops. The best management of crop production, taking into account the requirement for water in the agricultural sector, is one of the acceptable options in nations like Iran, which is also active in the field of agriculture. On the basis of this, it is vital to look at various analytical, planning, and decision-making techniques. Additionally, taking into account and calculating virtual water can significantly improve the cultivation pattern and decrease the amount of water currently consumed; as a result, optimizing the cultivation pattern using virtual water calculations can be highly beneficial. Coherent management and accurate decision-making in a variety of areas will result from the usage and implementation of spatial information systems, and taking into account virtual water will enhance navigation patterns and decrease water consumption. In order to achieve the best allocation of the cultivation pattern and as a result, the correct use of water in the agricultural lands of Ben-Rood district in the operations of Varzaneh city, located in the southeast of Isfahan province, was achieved in the current research by using the decision-making system that was created with the capabilities of GIS and artificial intelligence, along with the virtual water calculations of some agricultural plants. Using the collective intelligence algorithm of the ant community (ACO) in conjunction with the spatial information system, it was possible to achieve this goal after examining the optimization methods in decision-making using environmental parameters. This was done by taking into account the virtual water of cultivation and the growth of plants in the irrigation networks of the agricultural lands of the mentioned sector. Finally, the findings of this study demonstrate that the amount of water consumed may be decreased to 37% of the initial amount after optimizing the allocation of land for the cultivation of specific crops in that area, based on the virtual water of the crops.

The noise in the GNSS position time series is mainly a combination of white noise and power law noise. Noise amplitudes are estimated using variance component estimation (VCE) procedures. These methods require repeated inversion of covariance matrix, which is a computational burden for analysis of long time series. This work proposes an algorithm to estimate the white noise amplitude, through the estimation of wavelet variance based upon the Maximal Overlap Discrete Wavelet Transform (MODWT). MODWT can be used for any sample size and number of wavelet and scaling coefficients does not decrease by factor 2 for each increase in the level of the transform, so it does not decrease our ability to perform statistical analysis. To test the performance of the proposed algorithm, we used 180 synthetic daily time series with different lengths (2000, 4000 and 8000) emulating real GNSS time series. They composed of linear trends, periodic signals, offsets, transient displacements, gaps (up to 10%), and a combination of white, flicker, and random walk noises. The results of proposed method were compared to those of REstricted Maximum Likelihood (REML) approach. Biases of white noise amplitudes for the proposed and REML method indicated that results given by the two methods are in good agreement. Moreover, the proposed algorithm has computational complexity of order O(N) where N is the number of observations. Also, the results demonstrated that this proposed algorithm can be about 450-10000 times faster than REML method depending on the length of time series.  For further evaluation of the method, the time series of 19 real stations were used, and the results indicated the effectiveness of the proposed method. The low complexity of the proposed algorithm can considerably speed up the processing of GNSS time series.

Landslides are a common natural hazard around the world, but the accuracy of the maps produced can be impacted by various adverse effects and uncertainties. Researchers have continuously sought to improve the accuracy of landslide susceptibility maps. This study aims to create a landslide susceptibility map for Austria using t-test and random forest models. Nine criteria for landslide occurrence, including elevation, slope, aspect, distance to drainages, distance to faults, distance to roads, land cover, lithology, and precipitation, were used. In the t-test model, the weight of each criterion was calculated using the t-statistical test and then combined with each other using the Simple Additive Weighting technique to draw the final landslide susceptibility map. The random forest model was trained using multiple decision trees and based on the landslide occurrence points and criterion layers, the relative weight of each layer was calculated, resulting in the final landslide susceptibility map. The receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) were used to compare the two models, with the results showing that the random forest model performed better with an AUC of 0.893, compared to the t-test model with an AUC of 0.852. The importance of different criteria was assessed, and it was found that slope and precipitation were the most important factors in the occurrence of landslides in both models. The results showed that both models have unique advantages in landslide susceptibility mapping. Accordingly, the higher accuracy of the random forest model, and the possibility of weighting the criteria and sub-criteria in the t-test model, make both models practical in this field.

This study used satellite imagery to evaluate the effect of oak trees’ decline on carbon storage and its economic value in Zagros forests of Kuhdasht, Lorestan Province, Iran. To this goal, the study used the Sentinel-2 Satellite MSI sensor data recorded on June 15, 2021. In order to measure the ground biomass, we randomly selected 250 square samples with dimensions of 30 × 30. The Diameter at Breast Height [DBH] of each tree was measured and the amount of ground biomass for each sample plot was also obtained. General multivariate regression, Artificial Neural Networks, and K-nearest neighbors were used for modeling the ground biomass of the selected regions. In order to value the amount of stored carbon, the average rate was used for each ton of absorbed carbon dioxide gas (54 euros). The plot for the monetary valuation of carbon (in terms of carbon dioxide absorption) was determined by using the relationship between the amount of ground biomass and stored carbon, as well as absorbed carbon dioxide gas. The results showed that linear regression obtained by the vegetation index of NDVI with R2=0.73 and RMSE (%) = 21.88 was the best model for the studied area. The findings confirm that Sentinel-2 imagery data were considerably efficient for estimating the ground biomass of the Zagros declined forests.  Moreover, the results of the economic valuation of the carbon inventory in terms of carbon dioxide absorption service showed that each hectare of forests in the region has a value equivalent to 2547.12 Million Rial in carbon dioxide absorption function. The economic valuation of declined areas indicated that the more the degradation [decline] of these areas escalates, the more their economic value decreases. Accordingly, the highest value was obtained in the healthy areas and the lowest amount was calculated in the most declined regions. The findings suggest that Sentinel satellite images could be used to determine the accurate biomass map for the degraded areas. This map can be employed as a base map for decision-making, forestation/protection operations, and the economic valuation of these invaluable resources.