37200 research outputs found
Sort by
Predicting Cloud-To-Ground Lightning in the Western United States from the Large-Scale Environment Using Explainable Neural Networks
Get PDFLightning is a major source of wildfire ignition in the western United States (WUS). We build and train convolutional neural networks (CNNs) to predict the occurrence of cloud-to-ground (CG) lightning across the WUS during June-September from the spatial patterns of seven large-scale meteorological variables from reanalysis (1995-2022). Individually trained CNN models at each 1° × 1° grid cell ( = 285 CNNs) show high skill at predicting CG lightning days across the WUS (median AUC = 0.8) and perform best in parts of the interior Southwest where summertime CG lightning is most common. Further, interannual correlation between observed and predicted CG lightning days is high (median = 0.87), demonstrating that locally trained CNNs realistically capture year-to-year variation in CG lightning activity across the WUS. We then use layer-wise relevance propagation (LRP) to investigate the relevance of predictor variables to successful CG lightning prediction in each grid cell. Using maximum LRP values, our results show that two thermodynamic variables-ratio of surface moist static energy to free-tropospheric saturation moist static energy, and the 700-500 hPa lapse rate-are the most relevant CG lightning predictors for 93%-96% of CNNs depending on the LRP variant used. As lightning is not directly simulated by global climate models, these CNNs could be used to parameterize CG lightning in climate models to assess changes in future CG lightning occurrence with projected climate change. Understanding changes in CG lightning risk and consequently lightning-caused wildfire risk across the WUS could inform fire management, planning, and disaster preparedness
Oregon State Rank Assessment for Camas Pocket Gopher (Thomomys bulbivorus)
Get PDFOregon state conservation status assessment for Camas pocket gopher (Thomomys bulbiforus) using NatureServe methodology, 2024
Oregon State Rank Assessment for Columbia Mottled Sculpin (Cottus hubbsi)
Get PDFOregon state conservation status assessment for Columbia mottled sculpin (Cottus hubbsi) using NatureServe methodology, 2024
Belt It Out
No full textA series of essays and poems that focus on feeling invisible and unheard. It\u27s a breaking of silence and voicing complicated emotions and memories. The collection explore themes of growing up, family dynamics & relationships, gender, sexuality, friendship, and physical & mental health
AARS Online: A Collaborative Database on the Structure, Function, and Evolution of the Aminoacyl-Trna Synthetases
Get PDFThe aminoacyl-tRNA synthetases (aaRS) are a large group of enzymes that implement the genetic code in all known biological systems. They attach amino acids to their cognate tRNAs, moonlight in various translational and non-translational activities beyond aminoacylation, and are linked to many genetic disorders. The aaRS have a subtle ontology characterized by structural and functional idiosyncrasies that vary from organism to organism, and protein to protein. Across the tree of life, the 22 coded amino acids are handled by 16 evolutionary families of Class I aaRS and 21 families of Class II aaRS. We introduce AARS Online, an interactive Wikipedia-like tool curated by an international consortium of field experts. This platform systematizes existing knowledge about the aaRS by showcasing a taxonomically diverse selection of aaRS sequences and structures. Through its graphical user interface, AARS Online facilitates a seamless exploration between protein sequence and structure, providing a friendly introduction to the material for non-experts and a useful resource for experts. Curated multiple sequence alignments can be extracted for downstream analyses. Accessible at www.aars.online, AARS Online is a free resource to delve into the world of the aaRS
Applying Positive Unlabeled Learning Techniques and Using the Kullback-Leibler Divergence to Improve Geothermal Surveying Assessments
Get PDFAs we face the current climate crisis, the discovery of geothermal energy resources has the potential to greatly reduce our dependence on fossil fuels worldwide. However, the development of any new energy infrastructure is expensive and depends on the willingness of energy agencies and developers to make initial investments based on calculated risk measures. One such measure, called geothermal favorability, is the likelihood that a site has conditions favorable for geothermal systems containing recoverable energy potential. Its prediction from existing geophysical datasets proves to be a nontrivial task. The prediction of geothermal favorability can be framed as a binary classification problem, the data for which consists entirely of samples which are either positive (location contains a conventional hydrothermal system) or unlabeled (location does not contain any known geothermal system but should not be considered strictly negative). Data that comprises only positive and unlabeled examples is called positive unlabeled data, or PU data. PU learning is the branch of semi-supervised learning concerned with learning effectively from PU data. In addition to containing no negative examples, the dataset this thesis uses is heavily imbalanced, with many unlabeled examples and very few positive examples.
Previously, resource assessments have required experts to be directly involved in the assessment process, which can be time-consuming, expensive, and incurs human bias. Recent work in geothermal favorabililty prediction has used undersampling to mitigate class imbalance when training linear and nonlinear machine learning models, but more sophisticated techniques exist in the larger body of literature to specifically target the deficiencies in PU data. Furthermore, the metrics most common to the classification literature, e.g., F1 score and area under the receiver operating characteristic curve(ROC-AUC), do not adequately reflect the performance of models trained on PU data with such severe class imbalance. This thesis introduces the Kullback-Leibler divergence (DKL) as a means of model evaluation for PU data and explores two PU learning techniques, Selected-at-Random Expectation-Maximization (SAR-EM) and Difference-of-Estimated-Densities-based PU Learning (DEDPUL), on U.S. Geological Survey data from 2008. It then compares these two most current PU learning techniques against previous naïve methods using logistic regression and XGBoost. We demonstrate that, when used as a scoring function to tune hyperparameters for linear and nonlinear machine learning models, the DKL has an intrinsic ability to separate the unlabeled from predicted positive distributions. It has the weakness of being a highly variable scoring function, however: the strategy with the highest DKL score has a standard deviation that is 38% larger than its mean.
In the PU learning context, a nontraditional classifier (NTC) is a classifier that is trained on PU data to separate positive from unlabeled examples as if it were performing traditional binary classification. NTCs are often an integral part of PU learning algorithms, where they function to reduce data dimensionality, provide a lower bound for class prior prediction, and act as a baseline for determining PU learning algorithm performance. We show that when logistic regression is used to train an NTC, SAR-EM achieves a more accurate estimate of the class prior over other methods, with an MAE 185% lower than the closest naïve approach. SAR-EM also produces a slight improvement of 18% in F1 score compared to all other methods. The favorability maps resulting from SAR-EM resemble those given by naïve logistic regression methods in that the transition between regions of favorability is much more gradual and the lower favorability regions much smaller than the other methods explored. When XGBoost is used to train an NTC, DEDPUL enhances the model’s bias toward heavily penalizing likely negative samples/regions with steep boundaries between favorability regions. When comparing ridge plots, naïve XGBoost is better at separating the unlabeled distribution from predicted positive results, even over more advanced PU methods. It remains that these simpler models such as logistic regression and XGBoost, which rely on undersampling and the appropriate tuning of class weights, and treat all unlabeled examples as negative, can provide performance that is on par with the current state-of-the-art in PU learning
Coordinated Population Forecast for Washington County, its Urban Growth Boundaries (UGB), and Area Outside UGBs 2024-2074
Get PDFThis report for population forecasts for Washington County was made in compliance with Oregon House Bill 2253 relating to population forecasts for land use planning. Portland State University Population Research Center is tasked with creating population projections for all Oregon counties except Multnomah, Clackamas, and Washington as well as population forecasts for all Urban Growth Boundaries (UGBs), except for the Metro area UGB. These population forecasts are generated using standardized demographic methods with input and feedback from county, city, and other local stakeholders
Coordinated Population Forecast for Tillamook County, its Urban Growth Boundaries (UGB), and Area Outside UGBs 2024-2074
Get PDFThis report for population forecasts for Tillamook County was made in compliance with Oregon House Bill 2253 relating to population forecasts for land use planning. Portland State University Population Research Center is tasked with creating population projections for all Oregon counties except Multnomah, Clackamas, and Washington as well as population forecasts for all Urban Growth Boundaries (UGBs), except for the Metro area UGB. These population forecasts are generated using standardized demographic methods with input and feedback from county, city, and other local stakeholders
Polyphonic Storying with Human and More-Than Human Co-Collaborators
No full textWe believe that our most powerful approach to defy the erasure of people, knowledges, and open ways of living and being is generative storying together with children and families, educators, and the more-than-human. Storying takes many forms and is about more than overcoming coloniality or the earthly survival of humans. It is about taking a stance with a “citizenship of strangers” to compose more equitable, care-filled, and relational ways of living, especially with young children and their families. Thinking with storying as a liberatory and transformative process, we believe the perspectives of our human and more-than-human co-collaborators—the people, places, and materialities that collectively co-create these stories—are urgently required to offer satellites of hope amid the darkness and to practice living in radical relationality and a project of love