IntroductionGeographic information system (GIS) based distributed hydrologic models simulate the hydrologic processes using spatial parameters derived from geospatial data. These data mainly have information about relief, soil and land cover types, and intensity. Land cover has a great impact on the water quantity and quality in a river basin. Better estimation of land cover parameters improves the performance of the hydrologic model used. Appropriate spatial and temporal resolution of the used land cover improves the prediction of the hydrologic model (Huang et al., 2013). Several studies have been conducted to study the impact of land cover change on hydrology and water quality by (1) using readily available data (Cai et al., 2012;Yan et al., 2013), (2) using artificial land cover scenarios including farming practices (Chaplot et al., 2004;De Girolamo and Lo Porto, 2012;Mbonimpa et al., 2012), and (3) generating land use change scenarios using the land use change models (one such land use change model is the conversion of land use and its effects model (CLUE-s, Verburg et al.,
Soil nitrogen, phosphorous, and potassium concentrations accurately revealed spatial distribution maps and site-specific management-prone areas through inverse distance weighting (IDW) method in the Amik Plain, Turkey. Spatial mapping of soil nitrogen, phosphorous, and potassium is a very severe need to develop an economically and environmentally sound soil management plans. The objectives of this study were (a) to map spatial variability of total N, available P, and exchangeable-K content of Amik Plain's soils and (b) to locate problematic areas requiring site specific management strategies for the nutrient elements. Spatial analyses of Kjeldhal-N, Olsen-P, and exchangeable-K concentrations of the soils were performed by the IDW method. Mean N content for surface soils (0-20 cm) was 1.38 g kg -1 , available P was 28.19 kg ha -1 and exchangeable-K was 690 kg ha -1 with the differences between maximum and minimum being 7.63 g N kg -1 , 242 kg P ha -1 , and 2,082 kg K ha -1 . For the surface soil, site-specific management-prone areas of Kjeldahl-N, Olsen-P, and exchangeable-K for ''low and high ? very high'' classes were found to be 20.1-17.8%, 24.7-10.0%, and 4.1-39.6%, respectively. Consequently, lands with excessive nutrient elements require preventiveleaching practices, whereas nutrient-poor areas need fertilizer applications in favor of increasing plant production.
In this study, two kernel-based models were used which include Support Vector Regression (SVR) and Gaussian Process Regression (GPR) and were compared with two tree-based models that are M5 and Random Forest (RF) for estimating missing monthly precipitation data in Antakya, Dortyol, Iskenderun and Samandag stations, which are the important precipitation stations in the Eastern Mediterranean region, Turkey. For this purpose, firstly 10% random precipitation data were assumed as missing data for the period 1980-2019. Secondly, the missing data in each station was estimated with the data of other stations within the framework of four data combinations scenarios. In Kernelbased SVR and GPR methods, the RBF kernel gave suitable results for the selected study area. While SVR and RF methods gave very close estimation results, the SVR method gave relatively better results than the other methods especially in error minimizing aspects. Gaussian function based GPR model generally tries to estimate missing data closer to means. This is the main disadvantage of the GPR model and therefore it is unsuccessful in the estimation process. Finally, the results showed that the algorithms based on machine learning are successful in estimating the missing precipitation data.
Use of the satellite and reanalysis precipitation products, as supplementary data sources, are steadily rising for hydrometeorological applications, especially in data-sparse areas. However, the accuracy of these data sets is often lacking, especially in Turkey. is study evaluates the accuracy of satellite precipitation product (TRMM 3B42V7) and reanalysis precipitation product (NCEP-CFSR) against rain gauge observations for the 1998-2010 periods. Average annual precipitation for the 25 basins in Turkey was calculated using rain gauge precipitation data from 225 stations. e inverse distance weighting (IDW) method was used to calculate areal precipitation for each basin using GIS. According to the results of statistical analysis, the coefficient of determination for the TRMM product gave satisfactory results (R 2 > 0.88). However, R 2 for the CFSR data set ranges from 0.35 for the Eastern Black Sea basin to 0.93 for the West Mediterranean basin. RMSE was calculated to be 95.679 mm and 128.097 mm for the TRMM and CFSR data, respectively. e NSE results of TRMM data showed very good performance for 6 basins, while the PBias value showed very good performance for 7 basins. e NSE results of CFSR data showed very good performance for 3 basins, while the PBias value showed very good performance for 6 basins.
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.