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.
Mehdi Amiri; Saif ollah Soleimani; Fakhteh Soltani Tafreshi
Abstract
Dust storm increased in both spatial and temporal aspects during last decade. Middle East dust storms have caused countless social, economic and environmental damages for the residents of South and Southwest regions of Iran. MODIS satellite imagery has certain advantages, including available and useful ...
Read More
Dust storm increased in both spatial and temporal aspects during last decade. Middle East dust storms have caused countless social, economic and environmental damages for the residents of South and Southwest regions of Iran. MODIS satellite imagery has certain advantages, including available and useful spectral bands, with high spatial and radiation resolution and MODIS data are used in the present study. In this study, two MODIS datasets were used. Part one, model development data (January 18-21, 2018) and part two, model evaluation data. Metrological data are collected with respect to time interval studied. After preprocessing MODIS data and preparing field observations, features (artificial neural network input) were generated by proposed method from MODIS data. A model through artificial neural network analysis was developed. This model extracts dust storm and estmates visibility. Model outputs were compared visually with NDDI outputs.To evaluate the effectiveness of the proposed method, the developed model was tested with other time data. Model outputs were compared visually with NDDI outputs. Eventually, in order to reveal the strengths and weaknesses of the proposed method, an accuracy assessment has been carried out by comparing the models output with visibility parameter of synoptic stations. The observation root mean squared error are10%, 10%, 15% and 10% related to January 18th, January 19th, January 20th and 21th, and also, 20% and 25% related to January 26th, 2019 and October 28th, 2018, respectively.