Drought is a continuous period of lack of rainfall that causes damage and reduced yields in crops and has a direct impact on the quality and quantity of water and agricultural resources in the region. Remote sensing technology is Geographic Information Systems (GIS) are useful tools for processing and interpretation of spatial data and can be used for drought monitoring. The purpose of this study is to determine the most appropriate remote sensing indicators and to present a composite drought index based on the intelligent artificial neural network method. Based on the results, the best remote sensing indicators to determine the risk of drought in the region are vegetation indices, rainfall, and land surface temperature. The results were evaluated based on standardized precipitation index (SPI) values ​​obtained from meteorological stations. Accordingly, the accuracy of the results of the multivariate regression method was R2 = 0.62 and the multilayer perceptron neural network was R2 = 0.91. Therefore, the multilayer perceptron neural network method is more robust than the multivariate regression method to create a more accurate hybrid drought index. According to the results, there is a potential for monthly drought in most areas of Kermanshah province. Moreover, the annual drought potential is observed in the eastern regions of the province. Islamabad, Songor, and Harsin are cities with a low risk of drought.

The agricultural sector of every country is vulnerable to drought and the consequences of climate change; Therefore, planning to monitor and manage agricultural drought can help to control the damage caused by drought. The use of satellite images is used as a useful tool to monitor agricultural drought.Therefore, in this research, TCI, VCI, and VHI remote sensing indices have been investigated in seasonal, 6 month, and annual scales, and the correlation coefficient with SPI standardized precipitation index has been investigated using the data of 4 rain gauge stations in Urmia Plain during the period of 2003 to 2018.The results show that the distance measurement indices on an annual scale have a higher correlation compared to the seasonal and 6 month ones with the SPI index, and in general, the correlation coefficient of the VCI index on an annual scale is higher than the TCI and VHI indices. By dividing the Urmia plain into 17 study areas through the Thyssen polygon method, using piezometric wells in the Urmia plain to investigate remote sensing indicators on a smaller scale, it shows that in each region, depending on the specific climatic conditions and vegetation, there is a different correlation coefficient with the remote sensing indicators. and it is not possible to choose an optimal index for the whole region of Urmia; Therefore, to choose the optimal drought index, it is suggested to consider the scale of the studied area to be smaller in order to choose the best index for agricultural drought monitoring.

Widespread impacts of human activities have been the most important environmental issues of the current century that resulted in the loss of major parts of the structures and functions of important ecosystems around the world. This dilemma, clarifies the need to assess and control these destructive trends. Assessment and monitoring of ecosystem health, means a continuous assessment of overall performance, including: monitoring of sustainability and stability of the structure, function and process of the ecosystem and its resilience after the occurrence of a disturbance or stress. Ecosystem health has been recently monitored by establishing quantitative indicators, detecting and monitoring their changes over a long period of time. Current research illustrates how ecological problems ranging from biodiversity loss to land-use change have benefited greatly from advances in geospatial technologies such as GIS and remote sensing, both in the provision of data and access to spatial data analysis tools. This research intend to study and suggest a new method for monitoring and assessing the environmental health by using spatial indicators based on remote sensing and GIS technologies. The result of the study indicates that among the indicators of ecosystem health based on remotely sensed data, land cover maps with suitable temporal resolution and vegetation indices like NDVI and LAI are the most suitable indicators for ecosystem health estimation. This research also suggests the integration of landscape and biodiversity matrixes as well as non-remote sensing indicators (like carrying capacity and environmental loads estimation) are to be proposed indicators in order to estimate ecosystem health with more accuracy.

Drought in Zagros, which is one of the most important ecosystems in Iran, is a big challenge. Remote sensing has a unique application in diagnosis, monitoring and management of natural resources. The purpose of this study is to investigate and analyze the drought situation in the middle and southern Zagros basin based on atmospheric general circulation models and neural network in relation to remote sensing indices NDVI, VCI, TCI, VHI, DDI, EVI, NDWI and SAVI. At first the Modis satellite time series images were used in a 20-year period. First the mentioned indicators were produced from MOD021KM products of Terra sensor from 2000 to 2019. Then amount of precipitation were estimated by using of statistical-dynamic model MP5 under RCP 2.6, RCP 4.5 and RCP 8.5 scenarios and neural network and Remote sensing indicators during the period from 2020 to 2039, And then the state of droughts was investigated in 2 periods of 20 years based on the SPI method (2000-2019) and based on RCP scenarios and remote sensing methods and neural networks for the next 20 years (2021-2039). The results showed that both in the period of 2000-2019 and 2020-2039, the high areas of the studied area have and will have severe and very severe wet year. Also, the spatial analysis of droughts and remote sensing indices of the second period has depicted an irregular pattern in all indices, and only in NDVI and SAVI indices, the spatial analysis of droughts has been able to present a relatively regular pattern

Due to declining rainfall in the last two decades, drought has become a major problem in the world, especially in arid and semi-arid regions such as Iran, so monitoring and managing it is important. Remote sensing and geographic information system (GIS) and remote sensing (RS) provide the ability to study various indicators to evaluate the types of droughts. So, in the present study, the drought of Iran using multi remote sensing indicators including precipitation condition index (PCI), temperature condition index (TCI), Vegetation Conditions Index (VCI), and the integrated under the heading the scaled drought condition Index (SDCI) during the statistical period 2000 to 2018 were evaluated. To evaluate the accuracy of the obtained results, these results were compared with the standardized precipitation-evapotranspiration index (SPEI). The results of this study showed that the three indices of PCI, VCI, and TCI are well matched. The results of the SDCI index indicated that severe droughts occurred in 2000, 2008, and 2017, which are consistent with SPEI index. It should be noted that minor differences between the two indicators (SDCI and SPEI) can be justified by the fact that the SPEI index is a climatic index that considers two parameters of temperature and precipitation for annual drought assessment, while the SDCI index in addition assessment to temperature and precipitation factors (‎meteorological drought), it also considers ‎agriculture drought and more comprehensively evaluates drought. Finally, it can be mentioned that based on the calculations performed, the SDCI has been more effective in assessing drought than other indicators used.

The agricultural drought, severely affecting human life, occurs unpredictably at different times with different intensities. The conventional methods for assessing drought often relay on indices obtained using meteorological data, but due to the low spatial coverage, incompleteness and inaccuracy of these data, meteorological indices cannot be considered as a comprehensive method. Therefore, it is suggested that remote sensing constitute more versatile approach, as it allows to assess the drought using the adequate spatial and temporal coverage for the study area. In the study, performed for the Panjshir river basin in Afghanistan, the 2010-2019 period is used to evaluate vegetation rate using NDVI data from MODIS. To calculate agricultural drought indices (DSI, VCI and TCI), May and June were selected, as the peak vegetation time occurs for these months. On the base of the remote sensing indicators it was shown that during the study period the drought conditions were normal in the region, except for 2011, 2017, and 2018, which were the driest years, and for 2019, which was the wettest year. Agricultural drought indices were compared to SPI index calculated using winter and spring precipitation data recorded at the meteorological stations. It was observed that the remote sensing indices showed the highest correlation with data from Kabul meteorological station, which is located at the same altitude and climate as the dense vegetation zone. Furthermore, the comparison showed that the ground precipitation data is characterized by higher amplitudes than the remote sensing data. From the above it steams that the vegetation in the Panjshir basin is influenced by both seasonal rainfall and rivers that continuously flood the area.

One of the main problems in the management of watersheds in the country is the lack of information and data. Due to the lack of Sediment Measurement stations in most country's watersheds and insufficient data, empirical models can be important tools for the preparation of these layers. EPM model is used in experimental models, the use of these models to estimate erosion and sediment in basins without data has the costs and difficulties in providing map. In EPM model, the user factor is one of the factors that can be provided through remote sensing with good accuracy and at lower costs. Tarik dam Basin in the west of Rudbar, Guilan province, was considered as study basin. The area of basin was 6102.1 ha with average elevation of 11296 m. Digital elevation model (DEM) from satellite SRTM radar were provided and the required maps were provided from DEM and satellite images. Land use map was prepared based on visual interpretation of Google Earth images and field views. The user factorof EPM model based on the conventional method (field views and corresponding table) and mean opinions of three experienced expert was appointed for each landuse unit. A number of indicators associated with a landuse such as NDVI, PVI, SAVI and MSAV were extracted on ETM satellite image in 2011. The average indices for every land use were calculated by Software of remote sensing, and by using a linear regression model, the relationship between the user factor and remote sensing indicators were analyzed. At the next stage, other factors of model based on traditional methods was carried out in determining and estimating of erosion. The erosion of basin was again estimated by using all previous factors and by more appropriate index. The best relationship between vegetation index (VI) and user factor of model was obtained that correlation coefficient was 0.793.

Effective and timely drought monitoring can contribute to the development of drought systems and the optimal management of water resources using these systems in turn can minimize the costs of drought. The purpose of this study is to investigate the drought using Landsat satellite data and meteorological and agricultural drought indices in three regions with different climatic conditions (Birjand, Shiraz and Rasht). For this purpose, drought indices based on satellite data including Normalized Difference Vegetation Index (NDVI), Soil Adjustment Vegetation Index (SAVI) and Simple Ratio (SR) were extracted from Landsat images for the period 2002, 2014 to 2020. Then the results of these indices were compared with the values of standard precipitation index (SPI) and Reconnaissance Drought Index (RDI). The study of indicators shows that the amount of indicators is high in all studied years in Rasht region. In Shiraz region, a significant decrease in the average value of indicators occurred in August and September from 2015 to 2020. Also, this decrease was seen in the average value of indicators in Birjand region from September 2002 to 2020. On the other hand, among the studied months, September 2015 in Rasht and Shiraz regions and 2014 (September) Birjand had the most drought in terms of remote sensing indicators. The results showed that in all three regions, remote sensing indices including NDVI and SAVI have a high correlation with SPI and RDI indices. The RDI index is superior to the SPI index for drought monitoring and prediction. As a result, the RDI index takes into account evapotranspiration in addition to rainfall and is more sensitive especially in dry areas such as Shiraz and Birjand where evapotranspiration is higher than rainfall.

Soil salinity is one of the most important environmental problems, especially in arid and semi-arid regions. Soil salinity is caused naturally and/or by humans. High soil salinity negatively affects crop growth and productivity and ultimately leads to land degradation. Monitoring and mapping of soil salinity Due to the serious problems of spreading this issue to regional ecology, food security and agricultural development in the early stages, it is necessary to implement an effective soil rehabilitation program to prevent and reduce soil salinity. Remote sensing science performs better than traditional methods for assessing soil salinity and offers fast and cost-effective techniques for monitoring and mapping soil salinity. Soil salinity can be identified using direct indices that are related to the properties of surface soil salts as well as indirect indices. The aim of this research is to review the challenges of selecting appropriate indices in soil salinity studies through the investigation of researches conducted in the field of soil salinity and spectral indices used in soil salinity cases, which are helpful in land management at the regional scale. It is worth noting that in this regard, the most common vegetation and salinity indices used to detect and mapping of soil salinity were discussed. Many researchers have used different remote sensing indicators to map soil salinity. Among these, BI Brightness index, SI salinity index, NDVI normalized differential vegetation index and NDSI normalized differential salinity index showed the highest correlation between data obtained from satellite images in salinity-affected soils. Choosing the most appropriate band or indices depends on the soil conditions, geographical area, climatic conditions, satellite data, physiography of the area and the type of land use.

One of the widely used elements that plays an important role in sustainable agricultural production is potassium.The potassium in the surface soil of the playa originates from the potassium present in the underground water. As a result, there is a correlation between the surface soil potassium and the potassium grade of the groundwater. The aim of this research is to utilize a combination of the random forest (RF) algorithm and satellite imagery to establish the relationship between soil surface potassium and remote sensing indicators. This will enable the prediction of the potassium grade of the underground in Khoor and Biabank playa in Isfahan province. For this purpose, 60 soil samples were taken from the 0-5 cm layer to measure potassium in the surface layer(dependent variable). In order to determine the sampling coordinates, the Latin supercube method was used. Twelve boreholes were drilled to extract and measure the potassium grade of underground saline water. The 12 bands of the Sentinel-2 satellite and four main mathematical operations were used to define the index (independent variables) to model the potassium content of the surface soil layer and ultimately estimate the rate of potassium grade in the underground saline water. The data were categorized into two groups: 70% for calibration (training) and 30% for validation (testing). The data were modeled using the RF algorithm in the Google Colab environment and implemented with the Python programming language. The results of this algorithm were obtained with R2, MSE, RMSE and MAE statistical indices of 0.51, 0.0179, 0.1338 and 0.1130 respectively. The results of this research confirm the effectiveness of remote sensing data and machine learning algorithms in predicting the potassium grade of saline groundwater.