With rapid development in new technologies our intelligence and expertise in artificial intelligence (AI) have increased significantly. Intelligent machines are preferred, which motivates us to incorporate highly sophisticated technologies. Geographic analysis for environmental applications has advanced recently, owing to the vast explosion of geospatial data, the accessibility of powerful computing resources, and advancement in AI. Geospatial analytics at a high-resolution scale is now possible because AI reshapes our research environment. High-resolution satellite imaginaries used in geospatial analysis always include bigdata; thus, alternative methods other than traditional data-processing applications are needed to deal with these large datasets. AI has become an alternative method to handle big data in recent decades. Geospatial information from high-resolution remote sensing and other environmental sensors generates enormous data. AI makes the process more effective and makes it possible to derive deep understandings and information from the data.
Aerosols are an integral part of the earth's climate system and their effect on climate makes this field a relevant research problem. The artificial neural network (ANN) technique is an upcoming technique in different research fields. In the current work, we have evaluated the performance of an ANN with its parameters in simulating the aerosol's properties. ANN evaluation is performed over three sites (Kanpur, Jaipur, and Gandhi College) in the Indian region. We evaluated the performance of ANN for model's hyperparameter (number of hidden layers) and optimizer's hyperparameters (learning rate and number of iterations). The optical properties of aerosols from AERONET (AErosol RObotic NETwork) are used as input to ANN to estimate the aerosol optical depth (AOD) and Angstrom exponent. Results emphasized the need for optimal learning rate values and the number of iterations to get accurate results with low computational cost and to avoid overfitting. We observed a 23–25% increase in computational time with an increase in iteration. Thus, a meticulous selection of these parameters should be made for accurate estimations. The result indicates that the developed ANN can be utilized to derive AOD, which is not assessed at AERONET stations.
In the present work, we explored the inherent characteristics of the wind over a complex terrain site ‘Ranchi’ situated near a strategic location of the monsoon trough with various mathematical and statistical tools, i.e., time-series analysis, Fast Fourier transform (FFT), FFT coefficients, wavelet decomposition, and Weibull distribution. The time-series analysis showed a rapid day-to-day variability with a seasonal variation with a peak during summer. Fourier coefficients were concentrated for the winter/post-monsoon, indicating lower wind conditions, while wide spreads of the points indicate agility, i.e., high wind during the summer. The spectral features obtained using FFTs infer that wind has a prominent peak at a frequency f=0.00106724 (day−1) and f=0.00266809 (day−1). The power spectrum and wavelet decomposition show that the prominent frequencies correspond to yearly, 8, 6, and 4 months. Weibull probability density function, cumulative probability distributions, and probability profiles are studied. Results show that the Weibull distribution function reasonably models the probability distribution of daily wind speed. Weibull scale parameter varied between 0.26 and 1.33 m/s, and the shape parameter ranged between 1.09 and 2.88. Results from various analyses indicate that the seasonal variation of wind speed over Ranchi is mainly associated with the development of monsoon trough over the site.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.