Markets for energy-related commodities figure prominently in developmental economics, international trade, and environmental law and policy. Markets for Brent oil, West Texas intermediate crude, gasoline, and diesel affect not only energy policy but also demand for agricultural commodities that serve as feedstocks for ethanol and biodiesel. The natural resource curse in developmental economics arises largely from fossil fuel markets as well as gemstones and precious metals. Factors affecting oil prices include wars and other political disturbances, shifts in global supply and demand, and technological and regulatory changes promoting demand for renewable energy. Even ephemera such as OPEC production decisions and extreme weather events must be taken into account. Amid climate change and death by pandemic disease, the factors affecting energy commodity markets closely track the four horsemen of the Apocalypse: pestilence, war, famine, and death.In its original and proper Greek sense, the term ἀποκάλυψις (apokálupsis) simply means “revelation,” or the unveiling of previously hidden mysteries. Among statistical and computational methods used in economics and finance, unsupervised machine learning methods such as clustering, decomposition, and manifold learning come closest to this understanding of apocalypse as revelation and demystification.In this spirit, this paper extends previous work using unsupervised machine learning to examine commodity markets. Clustering Commodity Markets in Space and Time (SSRN: 3791138) examined returns, volatility, and trading regimes in markets for raw commodities. That paper marshaled quantitative evidence supporting the conventional ontology of commodity markets for precious metals, base metals, agricultural commodities, and crude oil and refined fuels. A sequel to that paper, A Pattern New in Every Moment (SSRN: 3901479), used temporal clustering to identify critical periods in energy-related markets.This paper uses unsupervised learning to examine a quartet of distinctive attributes of energy-related commodity markets: (1) macroeconomic versus specific-effects, (2) supply-side versus demand-side shocks, (3) upside versus downside asymmetry in oil and refined fuel prices, and (4) interactions with agricultural substitutes for and complements to fossil fuels. Formally, this paper combines the ontological methodology of Commodity Markets in Space and Time with the temporal clustering methods of A Pattern New in Every Moment. Spatial or ontological clustering, contingent upon the identification of structural breaks and other critical periods within these financial time series, is this paper’s distinctive contribution
