RPA Historical observational data (1979-2015) for the conterminous United States at the 1/24 degree grid scale based on MACA training data (METDATA)

2017 ◽  
Author(s):  
Linda A. Joyce ◽  
David P. Coulson
Keyword(s):  
United States ◽  
Observational Data ◽  
Training Data

The two extinctions of the Carolina Parakeet Conuropsis carolinensis

2021 ◽  
pp. 1-8
Author(s):  
KEVIN R. BURGIO ◽  
COLIN J. CARLSON ◽  
ALEXANDER L. BOND ◽  
MARGARET A. RUBEGA ◽  
MORGAN W. TINGLEY
Keyword(s):  
Climate Change ◽  
United States ◽  
Observational Data ◽  
18Th Century ◽  
Species Extinction ◽  
Extinct Species ◽  
Industrial Expansion ◽  
Island Endemics ◽  
The World ◽  
Habitat Conversion

Summary Due to climate change and habitat conversion, estimates of the resulting levels of species extinction over the next century are alarming. Devising conservation solutions will require many different approaches, including examining the extinction processes of recently extinct species. Given that parrots are one of the most threatened groups of birds, information regarding parrot extinction is pressing. While most recent parrot extinctions have been island endemics, the Carolina Parakeet Conuropsis carolinensis had an 18th-century range covering nearly half of the present-day United States, yet mostly disappeared by the end of the 19th century. Despite a great deal of speculation, the major cause of its extinction remains unknown. Establishing the date when a species went extinct is one of the first steps in determining what caused their extinction. While there have been estimates of their extinction date, these analyses used a limited dataset and did not include observational data. We used a recently published, extensive dataset of Carolina Parakeet specimens and observations combined with a Bayesian extinction estimating model to determine the most likely extinction dates. By considering each of the two subspecies independently, we found that they went extinct ˜30 years apart: the western subspecies C. c. ludovicianus going extinct around 1914 and the eastern subspecies C. c. carolinensis either in the late 1930s or mid-1940s. Had we only considered all observations together, this pattern would have been obscured, possibly missing a major clue in solving the mystery of the parakeet’s extinction. Since the Carolina Parakeet was a wide-ranging species that went extinct during a period of rapid agricultural and industrial expansion, conditions that mirror those occurring in many parts of the world where parrot diversity is highest, any progress we make in unraveling the mystery of their disappearance may be vital to modern conservation efforts.

scholarly journals Application of a Fusion Method for Gas and Particle Air Pollutants between Observational Data and Chemical Transport Model Simulations Over the Contiguous United States for 2005–2014

2019 ◽  
Vol 16 (18) ◽  
pp. 3314
Author(s):  
Niru Senthilkumar ◽  
Mark Gilfether ◽  
Francesca Metcalf ◽  
Armistead G. Russell ◽  
James A. Mulholland ◽  
...  
Keyword(s):  
United States ◽  
Air Quality ◽  
Spatial Variation ◽  
Temporal Variation ◽  
Observational Data ◽  
Transport Model ◽  
Chemical Transport ◽  
Daily Basis ◽  
Quality Data ◽  
Chemical Transport Model

Accurate spatiotemporal air quality data are critical for use in assessment of regulatory effectiveness and for exposure assessment in health studies. A number of data fusion methods have been developed to combine observational data and chemical transport model (CTM) results. Our approach focuses on preserving the temporal variation provided by observational data while deriving the spatial variation from the community multiscale air quality (CMAQ) simulations, a type of CTM. Here we show the results of fusing regulatory monitoring observational data with 12 km resolution CTM simulation results for 12 pollutants (CO, NOx, NO2, SO2, O3, PM2.5, PM10, NO3−, NH4+, EC, OC, SO42−) over the contiguous United States on a daily basis for a period of ten years (2005–2014). An annual mean regression between the CTM simulations and observational data is used to estimate the average spatial fields, and spatial interpolation of observations normalized by predicted annual average is used to provide the daily variation. Results match the temporal variation well (R2 values ranging from 0.84–0.98 across pollutants) and the spatial variation less well (R2 values 0.42–0.94). Ten-fold cross validation shows normalized root mean square error values of 60% or less and spatiotemporal R2 values of 0.4 or more for all pollutants except SO2.

scholarly journals A Continuum Deformation Approach for Growth Analysis of COVID-19 in the United States

2021 ◽  
Author(s):  
Sadra Hemmati ◽  
Hossein Rastgoftar
Keyword(s):  
United States ◽  
Growth Dynamics ◽  
State Level ◽  
The United States ◽  
Growth Patterns ◽  
Training Data ◽  
Deformation Model ◽  
Global Pandemic ◽  
The Stability ◽  
Continuum Deformation

Abstract The COVID-19 global pandemic has significantly impacted every aspect of life all over the world. The United States is reported to have suffered more than 20% of the global casualties from this pandemic. It is imperative to investigate the growth dynamics of the disease in the US based on varying geographical and governmental factors that best manifest itself in each state of the country. This paper utilizes a hybrid machine learning and continuum deformation-based approach for analyzing the stability of the rapid COVID-19 growth. The proposed continuum deformation model is used to learn the parameters of pandemic growth based on the training data of total cases, deaths, and recoveries in each state of the United States from March 12, 2020 to January 28, 2021. Using this approach, multiple periods of the nationwide and State-level pandemic growth patterns are discovered and analyzed.

scholarly journals A United States Fair Lending Perspective on Machine Learning

2021 ◽  
Vol 4 ◽  
Author(s):  
Patrick Hall ◽  
Benjamin Cox ◽  
Steven Dickerson ◽  
Arjun Ravi Kannan ◽  
Raghu Kulkarni ◽  
...  
Keyword(s):  
United States ◽  
Machine Learning ◽  
Financial Services ◽  
The United States ◽  
Training Data ◽  
Consumer Finance ◽  
Regulatory Environment ◽  
The Many ◽  
Legal Concepts ◽  
Fair Lending

The use of machine learning (ML) has become more widespread in many areas of consumer financial services, including credit underwriting and pricing of loans. ML’s ability to automatically learn nonlinearities and interactions in training data is perceived to facilitate faster and more accurate credit decisions, and ML is now a viable challenger to traditional credit modeling methodologies. In this mini review, we further the discussion of ML in consumer finance by proposing uniform definitions of key ML and legal concepts related to discrimination and interpretability. We use the United States legal and regulatory environment as a foundation to add critical context to the broader discussion of relevant, substantial, and novel ML methodologies in credit underwriting, and we review numerous strategies to mitigate the many potential adverse implications of ML in consumer finance.

scholarly journals Using a Coevolutionary Postprocessor to Improve Skill for Both Forecasts of Surface Temperature and Nowcasts of Convection Occurrence

2019 ◽  
Vol 147 (11) ◽  
pp. 4241-4259 ◽  
Author(s):  
Paul J. Roebber ◽  
John Crockett
Keyword(s):  
United States ◽  
Surface Temperature ◽  
Numerical Weather Prediction ◽  
Weather Prediction ◽  
Evolutionary Programming ◽  
The United States ◽  
Training Data ◽  
New Approach ◽  
Numerical Weather ◽  
Probabilistic Forecasts

Abstract An evolutionary programming postprocessor, using coevolution in a predator–prey ecosystem model, is developed and applied both to 72-h, 2-m temperature forecasts for the conterminous United States and southern Canada and to 60-min nowcasts of convection occurrence for the United States east of 94°W. The new approach improves deterministic and probabilistic forecasts of surface temperature relative to bias-corrected numerical weather prediction forecasts and to an earlier version of evolutionary programming forecasts for these same data. The new method also improves deterministic performance for an artificial neural network trained and evaluated for these same data. Additionally, the new approach substantially improves these forecasts’ reliability, as evidenced by reductions in the occurrence of excessive outliers in the rank histogram. The coevolutionary postprocessor also improves deterministic nowcasts of convection occurrence when compared to those produced by the National Weather Service’s AutoNowCaster system and to those obtained using multiple logistic regression. Notably, the degree of improvement relative to traditional methods appears to be problem dependent, while the training and implementation of such a system requires additional effort. However, the coevolutionary system is shown to be robust to imbalances between the frequency of positive and null events in the training data, unlike many postprocessing methods; to be implementable and effective in an adaptive mode, removing the need for retraining as inputs (such as numerical weather prediction model data) change; and to provide a useful, alternative perspective on the likelihood of event occurrence when used in combination with other methods.

scholarly journals Auto tuning SIR model parameters using genetic algorithm

2021 ◽  
Author(s):  
Fei Liu ◽  
Kristen Lee
Keyword(s):  
United States ◽  
Genetic Algorithm ◽  
Observational Data ◽  
Parameter Tuning ◽  
Sir Model ◽  
Model Parameters ◽  
Manual Intervention ◽  
Tuning Process ◽  
Optimal Set ◽  
Good Agreement

Earlier studies comparing Covid-19 simulations using extended SIR model with observed new cases in New Jersey and United States showed good agreement between simulated results and observational data. The parameters of the SIR model controlling the behavior of the model have to be manually adjusted until the modeled results and observations reach good agreement. The parameter tuning process is tedious and time consuming. In this work, we have developed an approach using genetic algorithm to automatically select the most optimal set of parameters to minimize the residual between simulated result and observational data. The parameter tuning process applying SIR model can now be automated without tedious and time consuming manual intervention.

Sign in / Sign up

Export Citation Format

Share Document