The habitat requirements of western freshwater mussels, Anodonta, Gonidea, and Margaritifera, remain unclear despite their imperiled status. Freshwater mussels provide a series of ecosystem services including habitat enhancement, substratum stabilization, nutrient cycling, and water clarification, which makes their loss from aquatic ecosystems particularly detrimental. To improve the efficacy of restoration actions targeting these organisms, I used random forest modeling to investigate the biotic and abiotic factors influencing mussel density and distribution throughout a 55-kilometer (km) segment of the Middle Fork John Day River (MFJDR), in northeastern Oregon. Data was collected to characterize the occurrence of mussels with respect to the hierarchical, hydrogeomorphic structure of habitat within reaches of varying valley confinement and channel units nested within these reaches. Data regarding functional habitat features were also included to ensure that models included the wide range of characteristics that mussels need from their environment. By collecting data at both the reach and channel unit scale, I was able to investigate how mussel densities and distributions vary with spatial scale and other biophysical parameters. Throughout the study area, Margaritifera density exhibited a unimodal distribution with respect to river km, while Anodonta and Gonidea density showed a negative relationship with river km and exhibited higher densities downstream. The large scale, longitudinal trends of Margaritifera were related to hydrogeomorphic characteristics at the reach scale, while less than half of the longitudinal variation in Anodonta and Gonidea were explained by hydrogeomorphic and water quality parameters. At the channel unit scale, all mussel genera responded to the patchy variation in physical habitat characteristics, particularly habitat factors that indicated more stable parts of the channel. Overall, physical habitat characteristics such as woody debris, emergent aquatic vegetation, coarse substratum, and channel morphology were more important than hydraulic, biotic, and chemical variables. These results suggest that at both the reach and channel unit scales, mussel density and distribution are influenced by high flow refugia and the hierarchical structuring of hydrogeomorphic habitat characteristics. These results will assist mussel restoration efforts by providing specific guidance about the types of physical habitat conditions that are suitable for mussels.

Survival Analysis in the context of Political Science is frequently used to study the duration of agreements, political party influence, wars, senator term lengths, etc. This paper surveys a collection of methods implemented on a modified version of the Power-Sharing Event Dataset (which documents civil war peace agreement durations in the Post-Cold War era) in order to identify the research questions that are optimally addressed by each method. A primary comparison will be made between a Cox Proportional Hazards Model using some advanced capabilities in the glmnet package, a Survival Random Forest Model, and a Survival SVM. En route to this comparison, issues including Cox Model variable selection using the LASSO, identification of clusters using Hierarchal Clustering, and discretizing the response for Classification Analysis will be discussed. The results of the analysis will be used to justify the need and accessibility of the Survival Random Forest algorithm as an additional tool for survival analysis.

We analyzed recent total suspended solids (TSS) data from 45 gages on 36 rivers throughout the state of Minnesota. Watersheds range from 32 to 14,600 km2 and represent a variety of distinct settings in terms of topography, land cover, and geologic history. Our study rivers exhibited three distinct patterns in the relationship between discharge and TSS: simple power functions, threshold power functions, and peaked or negative power functions. Differentiating rising and falling limb samples, we generated sediment rating curves (SRC) of form TSS = aQb, Q being normalized discharge. Rating parameters a and b describe the vertical offset and steepness of the relationships. We also used the fitted SRCs to estimate TSS values at low flows and to quantify event-scale hysteresis. In addition to quantifying the watershed-average topographic, climatic/hydrologic, geologic, soil and land cover conditions, we used high-resolution lidar topography data to characterize the near-channel environment upstream of gages. We used Random Forest statistical models to analyze the relationship between basin and channel features and the rating parameters. The models enabled us to identify morphometric variables that provided the greatest explanatory power and examine the direction, form, and strength of the partial dependence of the response variables on individual predictor variables. The models explained between 43% and 60% of the variance in the rating curve parameters and determined that Q-TSS relation steepness (exponent) was most related to near-channel morphological characteristics including near-channel local relief, channel gradient, and proportion of lakes along the channel network. Land use within the watershed explained most variation in the vertical offset (coefficient) of the SRCs and in TSS concentrations at low flows.

El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / Online social media has made the process of disseminating news so quick that people have shifted their way of accessing news from traditional journalism and press to online social media sources. The rapid rotation of news on social media makes it challenging to evaluate its reliability. Fake news not only erodes public trust but also subverts their opinions. An intelligent automated system is required to detect fake news as there is a tenuous difference between fake and real news. This paper proposes an intelligent gravitational search random forest (IGSRF) algorithm to be employed to detect fake news. The IGSRF algorithm amalgamates the Intelligent Gravitational Search Algorithm (IGSA) and the Random Forest (RF) algorithm. The IGSA is an improved intelligent variant of the classical gravitational search algorithm (GSA) that adds information about the best and worst gravitational mass agents in order to retain the exploitation ability of agents at later iterations and thus avoid the trapping of the classical GSA in local optimum. In the proposed IGSRF algorithm, all the intelligent mass agents determine the solution by generating decision trees (DT) with a random subset of attributes following the hypothesis of random forest. The mass agents generate the collection of solutions from solution space using random proportional rules. The comprehensive prediction to decide the class of news (fake or real) is determined by all the agents following the attributes of random forest. The performance of the proposed algorithm is determined for the FakeNewsNet dataset, which has sub-categories of BuzzFeed and PolitiFact news categories. To analyze the effectiveness of the proposed algorithm, the results are also evaluated with decision tree and random forest algorithms. The proposed IGSRF algorithm has attained superlative results compared to the DT, RF and state-of-the-art techniques. / Revisión por pares

京都大学 / 0048 / 新制・課程博士 / 博士(工学) / 甲第18654号 / 工博第3963号 / 新制||工||1610(附属図書館) / 31568 / 京都大学大学院工学研究科都市環境工学専攻 / (主査)教授 田村 正行, 准教授 須﨑 純一, 准教授 横松 宗太 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DFAM

No description available.

No description available.

No description available.

No description available.

Groundwater is a vital non-renewable resource that is being over exploited at an alarming rate. In Saudi Arabia, the majority of groundwater is used for agricultural activities. As such, the mapping of irrigated lands is a crucial step for managing available water resources. Even though traditional in-field mapping is effective, it is expensive, physically demanding, and spatially restricted. The use of remote sensing combined with advanced computational approaches provide a potential solution to this scale problem. However, when attempted at large scales, traditional computing tends to have significant processing and storage limitations. To address the scalability challenge, this project explores open-source cloud-based resources to map and quantify center-pivot irrigation fields on a national scale. This is achieved by first applying a land cover classification using Random Forest which is a machine learning approach, and then implementing a circle detection algorithm. While the analysis represents a preliminary exploration of these emerging cloud-based techniques, there is clear potential for broad application to many problems in the Earth and environmental sciences.