The CDPWater Report 2020 finds that responding to water risks costs 5 times less than inaction
The NEW CDPWater Report finds that responding to water risks costs 5 times less than inaction. It’s time for all businesses to tackle water risks for a resilient, NetZero future. Companies in the food, apparel, energy, chemicals, pharmaceuticals and mining sectors are...
PCA Review – Trust, Sustainability and Uncertainty in Artificial Intelligence (AI)
We live in a world with significant health, economic, climate, human population and geopolitical pressures. At the same time, we have rapid advances in technology, especially digital and AI, that are transforming our work, play and finances. In general, we hope that...
Who is leading the world in Climate Change and Sustainability commitments?
See link to World Economic Forum video below. https://twitter.com/PCAanalytics/status/1326610149725917188?s=20 This is a tweet from the PCA cognition aggregator feed on Twitter
Pandemic impacts on mining employment – report
Covid-19 is impacting employment in so many industries. In October 2020, it was a major focus of the Annual General Meeting of the Intergovernmental Forum on Mining, Minerals, Metals and Sustainable Development (IGF). A link to the summary article is provided below....
Successfully Evaluating AI Models in Industry
An interesting article from University of Delaware: "A new approach to artificial intelligence that builds in uncertainty." AI workers are combining the best of both worlds. Deterministic models based on scientific understanding of processes and statistical models, to...
Private Collaborative Webs – Now on Slack Platform
PCA currently uses Private Collaborative Webs on the Slack platform. Slack manages the IT infrastructure in the cloud, with enterprise-grade data protection that meets your compliance requirements. PCA acts as a catalyst to significantly improve your process and...
Scatterplot comparing Spearman and Pearson correlation 1
Scatterplot comparing Pearson and Spearman correlation 2
Python Code for Scatterplot comparing Pearson and Spearman correlation 2
Scatterplot comparing Spearman and Pearson correlation 3
The Standard Normal Probability Distribution with shaded regions
Attribution: D Wells [CC BY-SA 4.0], via Wikimedia Commons
The Grampian Prepared Foods Factory, Industrial Estate Road, UK
Attribution: Eric Jones / The Grampian Prepared Foods Factory, Industrial Estate Road, via Wikimedia Commons
Visualisation of how standard deviation (σ) is calculated
Attribution: Thebiologyprimer [CC BY-SA 4.0], via Wikimedia Commons
Processing facilities at the Essakane Mine in Burkina Faso
Excess Kurtosis Beta Distribution with mean for full range and variance from 0.05 to 0.25
Attribution: Dr. J. Rodal [CC BY-SA 3.0], via Wikimedia Commons
Graph of bias in estimated standard deviation vs. alpha (significance level) and N (sample size)
Attribution: Rb88guy [CC BY-SA 3.0], via Wikimedia Commons
3D representation of a hierarchical tree defining a classification (cluster) performed after a factorial analysis of the multiple correspondences on the "tea" dataset available under R with FactoMineR
Attribution: Jackverr [CC BY-SA 3.0], via Wikimedia Commons
This is based on a print of the “Single Malt Whisky Flavor Map” which was designed by the “Friends of the Classic Malts”, Glasgow, and published in free copies 2007
Dave Broom was named as the Editor. Diageo funded the project.
Attribution: Tasma3197 [CC BY-SA 3.0], via Wikimedia Commons
Cameronbridge Distillery, Scotland. This Diageo distillery is the birthplace of Cameronbridge pure grain whisky, and it is also where Gordons Gin, Smirnoff Vodka and other 'exotic' spirits are distilled
Attribution: James Allan / Cameronbridge Distillery, via Wikimedia Commons
Norbord Factory, Scotland. Manufacturers of engineered wood based panel products
Attribution: Ivor MacKenzie / Norbord Factory, via Wikimedia Commons
Visit of an EITI commission 2008 in Ghana: In the caldera of the Ahafo mine, an open-pit mine of the Newmont Ghana Gold Limited
Attribution: The EITI [CC BY-SA 2.0], via Wikimedia Commons
Processing scheme for the Rosebel Gold Mine in Suriname
VisIt's Scatter plot allows for the visualisation of multivariate data of up to four dimensions
The Scatter plot takes multiple scalar variables and uses them for different axes in phase space. The different variables are combined to form coordinates in the phase space and they are displayed using glyphs and coloured using another scalar variable.
Attribution: UCRL [Public domain], via Wikimedia Commons
Box-plot of normal and non normal distribution. Created with R
Attribution: Gbdivers [CC BY-SA 3.0], via Wikimedia Commons
The Ravensthorpe Nickel Mine, Western Australia
Attribution: Calistemon [CC BY-SA 3.0], via Wikimedia Commons
An example of the bivariate Gaussian (normal), Student-t, Gumbel, and Clayton copulæ
Attribution: Avraham [CC BY 4.0], via Wikimedia Commons
This is number 5 Blast Furnace located at the Port Talbot Corus (now Tata) Steel Plant, UK
Attribution: Grubb at English Wikipedia [Public domain], via Wikimedia Commons
Data fusion involves techniques that combine data from multiple sources (dimension #1 & #2) and gather that information in order to achieve inferences (see scatter plot)
More effective and potentially more accurate than using a single source of data (one or the other histogram).
Attribution: Jarekt [CC BY-SA 3.0], via Wikimedia Commons
Aluminium smelter of TRIMET Aluminium, Essen, Germany
Attribution: Tuxyso / Wikimedia Commons / CC BY-SA 3.0, via Wikimedia Commons
International Paper Company, Georgetown, USA
Attribution: Pollinator [CC BY-SA 3.0], via Wikimedia Commons
Image of random data plus trend, with best-fit line and smoothing curves
The data is 1000 points, with a trend of 1-in-100, with random normal noise of SD 10 superimposed. The r2 fit of the raw data is 0.08; of the 10-pt-smoothed, 0.57; of 100-pt-smoothed, 0.97. For the raw data, the simple trend line explains almost none of the variance of the time series (only 8%). For the 100-pt filtering, the trend line explains almost all of the data (97%). The trend lines are almost identical as are the confidence levels. It shows that a low r2 value should not be interpreted as evidence of lack of trend.
Attribution: Maksim [CC BY-SA 3.0], via Wikimedia Commons
Twin Creeks gold mine, Nevada, USA; Carlin-style mineralisation in Mesozoic sedimentary rocks
Attribution: Geomartin [CC BY-SA 3.0], via Wikimedia Commons
Terra Mineralia. Minerals Exhibition TU Bergakademie Freiberg (Gypsum with Calcite in foreground)
Attribution: Kora27 [CC BY-SA 4.0], via Wikimedia Commons
Get Started Today
There is a need in the industrial marketplace for a trusted, independent, data-based service to assist suppliers and industrial sites to improve process and chemistry performance. PCA’s mission is to provide your business with that service.