This article presents the results of studies on lysimeters and drainage carried out in the karst zone of Lithuania. The studies included the estimation of the changes of water quality in a soil profile of moraine loam and sandy loam soils in respect of the land usage and fertilization intensity. Fluctuations of N-NO 3 concentrations contained in soil water mainly depend on N losses through the yield (r 2 ¼ 0.78). The highest N concentrations (up to 28.7 mg l À1 ) were observed in the fields where potatoes were grown; six times lower N concentrations occurred in the fields of barley with undercrop and the lowest N concentrations (up to 5.1 mg l À1 ) were determined in fields of perennial grass. This was because N losses with the yield of potatoes are 1.7-2.0 times less than its losses with barley and even 3.0-4.5 times less than N losses with perennial grass. Efficient application of fertilizers results in decreased N-NO 3 and TP concentrations contained in soil water (r 2 ¼ 0.27-0.56 and r 2 ¼ 0.18-0.57 respectively). Compared to the field of perennial grass, the arable land contained even 9 times higher N-NO 3 concentrations and 2.6 times lower TP concentrations in the whole soil profile. However, when migrating into deeper soil layers in arable land, N-NO 3 concentrations decrease, while in the field of perennial grass the lowest N-NO 3 concentrations occur in the root zone of plants. TP concentrations tend to decrease in deeper soil layers in arable land as well as in the field of perennial grass.The selection of proper land use in studied soils is a particularly important factor. In order to reduce N-NO 3 leaching, the area of perennial grass might be increased, however this may result in higher TP concentrations. Moreover, it is precarious to leave tilled land for the period abundant in water (winter and spring).
The aim of this research was to model bankruptcy dependency of Lithuanian enterprises on their financial ratios and its dynamics over time by the integration of artificial neural networks and fuzzy logic technology using Adaptive Network – based Fuzzy Inference System (ANFIS). We used data from financial reports for three years’ of 230 Lithuanian going and failed enterprises. Input variables used for the ANFIS model training and testing composed of 13 financial ratios of the last year before bankruptcy and 13 variables characterizing changes of that ratios over time. It was checked 1716 subsets of input variables, each subset containing five input variables. This way the ANFIS model and the best subset of predictive variables with minimal training errors was found. Test of that model showed that percentage of right failure and success predictions reached 80 %. Fuzzy rules of the ANFIS were used to construct interpretable rules base, which can be useful for enterprise managers as knowledge for the linguistic diagnosis of failure or financial problems.
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.