مهدی Amiri; Farzad Amiri; Mohammad Hossein Pourasad; Seyfollah Soleimani
Abstract
Clean air quality, as one of the most essential needs of living organisms, has been compromised by natural and artificial activities. Dust storms have been constantly increasing in recent years, which have resulted in countless social, economic and environmental health damages for residents of southern ...
Read More
Clean air quality, as one of the most essential needs of living organisms, has been compromised by natural and artificial activities. Dust storms have been constantly increasing in recent years, which have resulted in countless social, economic and environmental health damages for residents of southern and southwestern regions of Iran. In this study, (MODIS) sensor data are used to investigate dust storms and detect horizontal depth of field. The advantages of MODIS sensor data include high spectral and temporal resolution. In addition, data from meteorological stations are collected according to the study period. After pre-processing data and preparing field observations, features required for modeling are derived from the MODIS sensor data through a differential method between the selected bands of each MODIS sensor image along with the features extracted from the sensor. Ground meteorological stations are used. With further studies and evaluations and using the opinions of meteorological experts 42 features are used of which36 are extracted from different bands of Moody's images and 6 features are extracted from meteorological station data. Next, best features are identified through feature selection techniques and a new method called ML-Based GMDH. which is the result of improving the GMDH neural network by changing partial functions with machine learning models, was used to detect dust concentration and horizontal visibility. In addition, to achieve the appropriate accuracy, the meta-parameters of this model are adjusted by the TLBO optimization algorithm. Furthermore, basic GMDH machine learning methods SVM, MLP, MLR, RF and their group model are implemented to compare with the main approach. Results shows that the ML-Based GMDH method adjusted with TLBO by improving on the best methods. The machine learner provides good accuracy in detecting dust concentrations.
fariba gilreyhan; Khalil Valizadeh Kamran; davood mokhtari; ali akbar rasouli
Abstract
Urmia Lake is one of the largest saltwater lakes in the world, which unfortunately is drying up and has caused many dangers and concerns, especially in relation to salt dust in its dried areas. Therefore, in this research, we tried to investigate the relationship between vegetation and dust in the cities ...
Read More
Urmia Lake is one of the largest saltwater lakes in the world, which unfortunately is drying up and has caused many dangers and concerns, especially in relation to salt dust in its dried areas. Therefore, in this research, we tried to investigate the relationship between vegetation and dust in the cities around Lake Urmia. Salinity in plants causes physiological disorders; salt stress causes growth, photosynthesis, protein, respiration, energy production, premature senescence, water reduction in plants. Considering these effects, it was tried to evaluate the overall health of plants by using related indicators including NDVI, CIre, GCI, CRI2, NDWI, NDII, MSI, PSRI. These indicators evaluate the amount of plant water, plant water stress, photosynthesis capacity, plant growth and water deficit, the amount of chlorophyll, nitrogen and pigments, which are related to plant energy and health. According to these indicators, the health of plants is generally in a favorable condition, and mostly the highest numerical values of the indicators were assigned to gardens. Using Landsat and Sentinel 2 images and the NDVI index, the vegetation changes of the region were determined in the period from 2010 to 2020, and then using the MERRA-2 database, the amount of dust concentration was also extracted for the mentioned years. The results showed that the average NDVI in the studied area follows a constant trend with an overall average of 0.2957 and sometimes it increases or decreases due to the influence of external factors such as dust. Based on this, the highest (0.3495) average NDVI is related to 2018 and the lowest (0.2579) is related to 2013. Also, two methods of linear and logarithmic regression were used to investigate the relationship between vegetation cover and dust, and the results showed that based on the linear (0.7703) and logarithmic (0.7915) regression, the highest coefficient of explanation between the two mentioned indicators was in May.
