NiO (Nickel Oxide)

Data

Notes

In typical pottery, nickel oxide, as a raw powder, is not nearly as commonly used as other metal oxides. Most often, it is used to modify and soften the color of other metallic oxides, and thus small amounts are normally employed. That being said, this oxide is common in black glazes, used in combination with iron, manganese and cobalt. By itself, nickel commonly produces muted browns and greens.

Nickel is incorporated into calcined mixed-metal oxide pigments where it locks into a stable crystal structure to create black spinels, nickel silicates/greens, and nickel-titanate/rutile yellows.

It is not normally used in low-fire glazes due to the refractory nature of nickel oxide powder. Glazes that are already matte or immature will thus be made more dry by the addition of nickel.

Since nickel is used in smaller amounts, flashing from other glazed ware and the chemistry of the glaze can have an effect on ware color.

However, in crystalline glazes it is more common, since it can color the willemite crystals and/or interact with the crystal/glass partitioning. An interesting question highlight the value of using an AI chatbot to research the following question: "Is the blue coloration of crystallization in macro-crystalline zinc glazes, colored solely with nickel, the result of contamination of nickel compounds with cobalt? As I understand it, research from the 1960s (e.g. Singer 1963 and others) suggested this.". Answering such a question using traditional research techniques would be challenging indeed, but here is what ChatGPT told me:

Yes — Singer’s explanation is a real historical one, but it is probably not the whole story. Draney’s 1969 thesis summarizes the older view very clearly: in crystalline glazes, colorants partition selectively; he says iron and nickel tend to color the glassy matrix, while copper and cobalt tend to color the crystals. He then quotes Singer & Singer’s Industrial Ceramics saying that “trade nickel oxide” contains a trace of cobalt oxide, and that in a zinc-silicate crystalline glaze the crystals become blue because they have attracted the cobalt content of the glaze.

So, for mid-20th-century technical-grade nickel oxide, the cobalt-contamination explanation is quite plausible. Even modern industrial nickel oxide may not be chemically pure; one Vale SDS gives a typical nickel oxide content of only 90–96%, and explicitly discusses nickel oxide with cobalt oxide impurity, with classification changes triggered at ≥0.3% cobalt oxide impurity. Since cobalt is strongly scavenged into willemite crystals, a very small bulk cobalt level could become visually exaggerated in the crystal phase.

However, later work complicates the claim that blue must be cobalt. A 2010 Journal of the Korean Ceramic Society paper specifically on NiO additions to willemite crystalline glazes reports that nickel can substitute for zinc ions and produce blue willemite crystals on a brown glaze base; at higher NiO levels, excess nickel reacts to form green nickel silicate/olivine, Ni₂SiO₄. Recent nickel-doped willemite/liebenbergite pigment work likewise reports blue or green hues depending on the proportions of nickel-doped willemite, NiO, and liebenbergite phases.

My take: Singer was likely correct for many “nickel-only” glazes made with trade nickel oxide, especially where the blue is very cobalt-like and the nickel level is modest. But it is too strong to say that all nickel-blue macrocrystalline zinc glazes are cobalt contamination. There is credible evidence that Ni²⁺ in the willemite structure itself can be a blue chromophore, while excess nickel tends to push toward green Ni₂SiO₄-type phases.

The practical way to settle it is to run a line blend using certified high-purity NiO or NiCO₃ with a Co assay, alongside your usual ceramic nickel source, plus tiny deliberate cobalt additions. Then analyze crystals and matrix separately by LA-ICP-MS, EPMA, or at least SEM-EDS if cobalt is enriched enough. If the crystals are blue with no measurable cobalt, it supports true nickel-blue willemite; if cobalt concentrates in the crystals while nickel stays mostly in the matrix, Singer’s mechanism is operating.

Ceramic Oxide Periodic Table

Pretty well all common traditional ceramic base glazes are made from less than a dozen elements (plus oxygen). Go to the full picture of this table and click or tap each of the oxides to learn more (on its page at digitalfire.com). When materials melt, they decompose, sourcing these elements in oxide form. The kiln builds the glaze from them, it does not care what material sources what oxide (assuming, of course, that all materials do melt or dissolve completely into the melt to release those oxides). Each of these oxides contributes specific properties to the glass. So, you can look at a formula and make a good prediction of the properties of the fired glaze. And know what specific oxide to increase or decrease to move a property in a given direction (e.g. melting behavior, hardness, durability, thermal expansion, color, gloss, crystallization). And know about how they interact (affecting each other). This is powerful. A lot of ceramic materials are available, hundreds - that is complicated when individual materials source multiple oxides. Viewing a glaze as a simple unity formula of ceramic oxides is just simpler.

Links

Mechanisms

PayPal	No tracking, No ads, No paywall, No transient content! Just organized, concise information constantly updated and improved. Was this helpful? Consider supporting me.

By Tony Hansen Follow me on

Got a Question?

Buy me a coffee and we can talk