<p>Environmental models often require soil maps to represent the spatial variability of soil attributes. However, mapping soils using conventional in-situ survey protocols is time-consuming and costly. As an alternative, digital soil mapping offers a fast-mapping approach that might be used to monitor soil attributes and their interrelationships over large areas. In Brazil, conventional survey methods are still widely used, and thus maps still in development are considered as the state-of-the-art products for decades. In this study, we address this lack of updated spatial information on many soil attributes by producing regional statistical soil models using an innovative framework. This new framework attempts to reduce prediction redundancies due to high multicollinearity, by implementing a Feature Selector algorithm. This is expected to improve a model&#8217;s strength by decreasing its unexplained variance. The framework&#8217;s core is composed of the Soil-Landscape Estimation and Evaluation Program (SLEEP) and a calibrated Gradient Boosting Model capable of modelling the spatial distribution of soil attributes at multiple soil depths. These models allowed us to explain the spatial distribution of some basic soil attributes (physical and chemical), and its environmental drivers. The model training and testing approach used 30 environmental attributes, and data from 223 soil profiles for the state of Pernambuco, Brazil. Our models demonstrated a consistent potential to perform spatial extrapolations with r<sup>2</sup> ranging from 0.8 to 0.97, and PBIAS from -0.51 to 2.03. The properties related to topographic and climatic conditions were dominating when estimating the number of horizons, percentage of silt and the sum of bases (a measure of soil fertility). We believe that our framework features high flexibility, while reducing capital investments when compared to <em>in situ</em> surveys and traditional mapping protocols. These findings also have implications for the improvement and testing of pedotransfer functions. We thank FACEPE for funding this through APQ 0646-9.25/16.</p>
Soil water content is an important variable in the understanding of hydrology in agricultural and environmental systems in a region. It is known that soil moisture is related to soil characteristics, porosity, depth, hydraulic conductivity, among others, that is, characteristics that define its typology. Studies related to soil moisture are still very precarious in Brazil. Recently, the Europe Space Agency has provided soil moisture data estimated worldwide with satellite data. This availability made possible the spatial and temporal assessment of soil magna.moura@embrapa.br moisture for different studies in the world, even though we did not know the accuracy of these data. Many studies have used multivariate analysis to find groups that have similar characteristics that can be analyzed and managed with the same actions. Therefore, this study sought to analyze the similarities and dissimilarities between soil types when considering the characteristics of soil moisture, precipitation, soil elevation and soil depth. After applying the statistical methods it was possible to perceive that the soil moisture does not depend strongly on the precipitation and to suggest caution in the analysis of the relations between the humidity factor and the others scored.
Brain tumor is a major cause of an increased transient between children and adults. This article proposes an improved method based on magnetic resonance (MRI) brain imaging and image segmentation. Automated classification is encouraged by the need for high accuracy in dealing with a human life. Detection of brain tumor is a challenging problem due to the high diversity in tumor appearance and ambiguous tumor boundaries. MRI images are chosen for the detection of brain tumors as they are used in the determination of soft tissues. First, image preprocessing is used to improve image quality. Second, the multi-scale decomposition of complex dual-wavelet tree transformations is used to analyze the texture of an image. Resource extraction draws resources from an image using gray-level co-occurrence matrix (GLCM). Therefore, the neuro-fuzzy technique is used to classify brain tumor stages as benign, malignant, or normal based on texture characteristics. Finally, tumor location is detected using Otsu threshold. The performance of the classifier is evaluated on the basis of classification accuracies. The simulated results show that the proposed classifier provides better accuracy than the previous method.
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.