Accounting for minimum data required to train a machine learning model to accurately monitor Australian dairy pastures using remote sensing.

Precision in grazing management is highly dependent on accurate pasture monitoring. Typically, this is often overlooked because existing approaches are labour-intensive, need calibration, and are commonly perceived as inaccurate. Machine-learning processes harnessing big data, including remote sensing, can offer a new era of decision-support tools (DST) for pasture monitoring. Its application on-farm remains poor because of a lack of evidence about its accuracy. This study aimed at evaluating and quantifying the minimum data required to train a machine-learning satellite-based DST focusing on accurate pasture biomass prediction using this approach. Management data from 14 farms in New South Wales, Australia and measured pasture biomass throughout 12 consecutive months using a calibrated rising plate meter (RPM) as well as pasture biomass estimated using a DST based on high temporal/spatial resolution satellite images were available. Data were balanced according to farm and week of each month and randomly allocated for model evaluation (20%) and for progressive training (80%) as follows: 25% training subset (1W: week 1 in each month); 50% (2W: week 1 and 3); 75% (3W: week 1, 3, and 4); and 100% (4W: week 1 to 4). Pasture biomass estimates using the DST across all training datasets were evaluated against a calibrated rising plate meter (RPM) using mean-absolute error (MAE, kg DM/ha) among other statistics. Tukey's HSD test was used to determine the differences between MAE across all training datasets. Relative to the control (no training, MAE: 498 kg DM ha-1) 1W did not improve the prediction accuracy of the DST (P > 0.05). With the 2W training dataset, the MAE decreased to 342 kg DM ha-1 (P < 0.001), while for the other training datasets, MAE decreased marginally (P > 0.05). This study accounts for minimal training data for a machine-learning DST to monitor pastures from satellites with comparable accuracy to a calibrated RPM which is considered the 'gold standard' for pasture biomass monitoring.

Comparison of rampage and non-rampage mass shootings in the U.S.: A 5-year demographic analysis.

BACKGROUND: Rampage mass shootings (RMS) are a subset of mass shootings occurring in public involving random victims. Due to rarity, RMS are not well-characterized. We aimed to compare RMS and NRMS. We hypothesized that RMS and NRMS would be significantly different with respect to time/season, location, demographics, victim number/fatality rate, victims being law enforcement, and firearm characteristics. STUDY DESIGN: Mass shootings (4 or more victims shot at a single event) from 2014-2018 were identified in the Gun Violence Archive (GVA). Data were collected from the public domain (e.g. news). Crude comparisons between NRMS and RMS were performed using Chi-squared or Fisher's exact tests. Parametric models of victim and perpetrator characteristics were conducted at the event level using negative binomial regression and logistic regression. RESULTS: There were 46 RMS and 1626 NRMS. RMS occurred most in businesses (43.5%), whereas NRMS occurred most in streets (41.1%), homes (28.6%), and bars (17.9%). RMS were more likely to occur between 6AM-6PM (OR=9.0 (4.8-16.8)). RMS had more victims per incident (23.6 vs. 4.9, RR: 4.8 (4.3,5.4)). Casualties of RMS were more likely to die (29.7% vs. 19.9%, OR: 1.7 (1.5,2.0)). RMS were more likely to have at least one police casualty (30.4% versus 1.8%, OR: 24.1 (11.6,49.9)) or police death (10.9% versus 0.6%, OR: 19.7 (6.4,60.3)). RMS had significantly greater odds that casualties were adult (OR: 1.3 (1.0,1.6)) and female (OR: 1.7 (1.4,2.1)). Deaths in RMS were more likely to be female (OR: 2.0 (1.5,2.5)) and White (OR: 8.6 (6.2,12.0) and less likely to be children (OR: 0.4 (0.2,0.8)). Perpetrators of RMS were more likely to die by suicide (34.8%), be killed by police (28.3%), or be arrested at the scene (26.1%), while more than half of perpetrators from NRMS escaped without death or apprehension (55.8%). Parametric models of perpetrator demographics indicated significant increases in the odds that a RMS shooter was White (OR: 13.9 (7.3,26.6)) or Asian (OR: 16.9 (3.7,78.4)). There was no significant difference in weapon type used (p=0.35). CONCLUSION: The demographics, temporality, and location differ between RMS and NRMS, suggesting that they are dissimilar and require different preventive approaches.

SPEAQeasy: a scalable pipeline for expression analysis and quantification for R/bioconductor-powered RNA-seq analyses.

BACKGROUND: RNA sequencing (RNA-seq) is a common and widespread biological assay, and an increasing amount of data is generated with it. In practice, there are a large number of individual steps a researcher must perform before raw RNA-seq reads yield directly valuable information, such as differential gene expression data. Existing software tools are typically specialized, only performing one step-such as alignment of reads to a reference genome-of a larger workflow. The demand for a more comprehensive and reproducible workflow has led to the production of a number of publicly available RNA-seq pipelines. However, we have found that most require computational expertise to set up or share among several users, are not actively maintained, or lack features we have found to be important in our own analyses. RESULTS: In response to these concerns, we have developed a Scalable Pipeline for Expression Analysis and Quantification (SPEAQeasy), which is easy to install and share, and provides a bridge towards R/Bioconductor downstream analysis solutions. SPEAQeasy is portable across computational frameworks (SGE, SLURM, local, docker integration) and different configuration files are provided ( http://research.libd.org/SPEAQeasy/ ). CONCLUSIONS: SPEAQeasy is user-friendly and lowers the computational-domain entry barrier for biologists and clinicians to RNA-seq data processing as the main input file is a table with sample names and their corresponding FASTQ files. The goal is to provide a flexible pipeline that is immediately usable by researchers, regardless of their technical background or computing environment.