Evaluating four interpolation methods of temperature and vegetation indices obtained from satellite images in daily reference evapotranspiration modeling

نویسندگان
doi
10.22034/ewe.2024.473908.1961
چکیده

Due to the requirement for extensive meteorological data, the standard FAO Penman-Monteith method for estimating reference evapotranspiration (ET 0 ) is limited. Moreover, the lack of sufficient meteorological data in many regions has led to the utilization of remote sensing imagery as a valuable alternative. However, these images often have multi-day temporal resolutions. To obtain daily remote sensing data, in this study four mathematical functions: spline (S), cubic spline (CS), Bezier (B), and composite Bezier (CB) for interpolating 8-day land surface temperature (LST-D/N) and 16-day vegetation indices (NDVI and LAI) to daily values were compared. Subsequently, four remote sensing variables were used as inputs under 12 scenarios for two neural network models: Multi-Layer Perceptron (MLP) and Multi-Layer Perceptron combined with Stochastic Gradient Descent (MLP-SGD) to estimate ET 0 . This study was conducted at two stations, Urmia and Kerman, from 2001 to 2022. The determination coefficients of 0.89 in Urmia and 0.83 in Kerman demonstrated the superiority of spline-based interpolation methods in estimating ET 0 . Spline functions are recommended for interpolating remote sensing variables to estimate reference evapotranspiration.

کلیدواژه‌ها
Materials andMethods, Conclusion, In the Urmia station and the MLP method, the MLP-4 scenario, i.e. the use of all four parameters and with cubic spline interpolation, and in the SGD-MLP method, the SGD-MLP-2 scenario, i.e. the model using day and night LST and with spline interpolation, were the best models., In the Kerman station, with the MLP-5 scenario, i.e. the use of day and night LST and with cubic spline interpolation, and in the SGD-MLP modeling, the SGD-MLP-2 scenario, i.e. with the use of day and night LST and with spline interpolation, were the best models., In general, the MLP model with spline interpolated data and the SGD-MLP model with cubic spline interpolated data performed better. Finally, the best model at the Urmia station was the S-SGD-MLP-2 scenario and at the Kerman station was the CS-MLP-2. Also, the statistical results showed that the MLP model had less error compared to the SGD-MLP model in similar scenarios., RIS, EndNote, Mendeley, BibTeX, APA, MLA, HARVARD, CHICAGO, VANCOUVER