Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Acta Geophysica

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Application of machine learning ensemble models for rainfall prediction

Ahmadi Hasan, Aminnejad Babak, Sabatsany Hojat

Acta Geophysica

2023

Vol. 71, no. 4

1775--1786

Practical information can be drawn from rainfall for making long-term water resources management plans, taking flood mitigation measures, and even establishing proper irrigation systems. Given that a large amount of data with high resolution is required for physical modeling, this study proposes a new standalone sequential minimal optimization (SMO) regression model and develops its ensembles using Dagging (DA), random committee (RC), and additive regression (AR) models (i.e., DA-SMO, RC-SMO, and AR-SMO) for rainfall prediction. First, 30-year monthly data derived from the year 1988 to 2018 including evaporation, maximum and minimum temperatures, maximum and minimum relative humidity rates, sunshine hours, and wind speed as input and rainfall as the output were acquired from a synoptic station in Kermanshah, Iran. Next, based on the Pearson correlation coefficient (r-value) between input and output variables, different input scenarios were formed. Then, the dataset was separated into three subsets: development (1988–2008), calibration (2009–2010), and validation (2011–2018). Finally, the performance of the developed algorithms was validated using different visual (scatterplot and boxplot) and quantitative (percentage of BIAS, root mean square error, Nash–Sutcliffe efficiency, and mean absolute error) metrics. The results revealed that minimum relative humidity had the greatest effect on rainfall prediction. The most effective input scenario featured all the input variables except for wind speed. Our findings indicated that the DA-SMO ensemble algorithm outperformed other algorithms.

Evaluating the reconstruction method of satellite based monthly precipitation over Golestan province, Northern Iran

Abdollahipour Arman, Ahmadi Hassan, Aminnejad Babak

Acta Geophysica

2021

Vol. 69, no. 6

2305--2323

Accurate gridded precipitation data with high spatial and temporal scales are required for diverse studies such as climatology, meteorology, and hydrology. Currently, one of the sources of global precipitation estimation is the satellite-based precipitation estimate products. Nonetheless, their spatial resolution is often too coarse for usage in local region and basin scales or for parameterizing of meteorological and hydrological models at regional scales. In the present paper, a reconstruction method of satellite-based monthly precipitation was developed to attain improved pixel-based precipitation data with high spatial resolution on Golestan province in Northern Iran. In this endeavor, we considered the spatially heterogeneous relationships between tropical rainfall measuring mission (TRMM) precipitation and environmental variables utilizing the moving-window regression methods, the geographically weighted regression (GWR) and the mixed geographically weighted regression (MGWR) models. By in situ observations from rain gauges in the study area, the calibration and validation were performed, and the following conclusions were derived: (1) the proposed procedure had the ability to enhance both the spatial resolution and accuracy of satellite-based precipitation estimates; (2) the monthly reconstructed precipitation using the GWR model (CC=0.69, bias=0.75) and using the MGWR model (CC=0.72, bias=0.64) outperformed the TRMM-3B43V7 data (CC=0.58, bias=0.84) against ground observations; (3) this research offered a potential solution for producing gridded precipitation estimates at high spatial resolution. remote sensing