The fuel use data in the Exhibit below is very much a function of geology and the good and bad luck associated with it. The large hydrocarbon users' consumption patterns are a function of what they have – if you have a lot of coal, you use a lot of coal. The significant build-out of nuclear in France is partly because of Frances’ exceptional track record with the technology but also because the country does not have anything else to fall back on. Japan’s nuclear component was much higher before Fukashima. It is, however, worth noting the almost insignificant share of wind and solar anywhere, and then to put this into context with the collective ambitions, not just for 2050, but for the much shorter 2030 targets.
The battery storage investment chart below is interesting in that it shows significant pairing with Solar facilities and less with wind. If we are to meet the green hydrogen goals that many are optimistically predicting over the next 10 years, then the new wind and solar investments need to be paired with hydrogen and hydrogen-based swing power generation capacity. This is the only way that countries will develop effective hydrogen grids. Simply having one or two large hydrogen facilities and/or import facilities will result in very inefficient distribution models either for fuel cell vehicles or for heating and swing power generation. A distributed network for hydrogen makes much more sense and modular electrolyzers coupled with modular hydrogen power generators is a more holistic model, with much more flexibility than adding batteries. Granted, the battery technology is tested and available today, but the broader ambitions for hydrogen will not be met if we do not get out of the blocks soon.
Last week, and in our dedicated ESG and climate report this week, we talked about the challenges of shipping hydrogen, and the linked bp project for Western Australia will have the same problem to solve – choosing ammonia according to the announcement over the very inefficient toluene/cyclohexane option we discussed last week. The appeal of Western Australia is the unpopulated available land that has little alternative use and sees abundant sunshine. The bp project assumes that the facility can buy attractively priced renewable power from third parties, but the company must have a specific power project in mind for the bulk of the electricity needed. The stumbling block here will likely be when the power project(s) bid out the solar module contract, find out that the suppliers are sold out and are asking higher prices to cover reinvestment and higher material prices, and then have to go back to bp with a much higher than expected cost of power. The advantage of solar and wind projects is that inflation only impacts upfront capital costs, which can be amortized over the life of the project – feedstocks are free! That said, most of the announced projects have declining capital costs per megawatt in their planning assumptions today.
We are back on one of our pet topics today which is the reasonableness around some of the assumptions around the future cost of renewable power. We reference, work done by the US Department of Energy in the Exhibit below, and see two potential pitfalls with the assumptions around continuous improvement in solar, wind, and hydrogen costs, although there is a slight twist for hydrogen. The first is around the dynamics of learning curves. As the exhibit shows, in the early stages of any product development, there are huge leaps in cost improvements, driven by scale, better know-how, more efficient manufacturing, and in the case of solar power, both better processes for installation and some technology improvements. However, as you drive costs lower, the cost of raw materials becomes a much larger component of overall costs, and your ability to lower costs further can be overwhelmed by moves in material costs. Any inability to pass on the costs will result in economics that do not justify additional capital and you find yourselves in a commodity cycle. This is something that we have seen in basic polymers for decades, and no buyer of polyethylene today can claim that they are benefiting from a learning curve improvement. Closer to home for solar, we are seeing the same issue today in semiconductors – not enough margin to invest as everyone has been trying to push costs lower. The expectation in the DOE study and highlighted in the CNBC take on the study below is that annual solar installations in the US need to rise by 3-4X to meet some of the renewable power goals the Biden Administration is looking for by 2030, while similar growth is expected in other markets – the solar panel and other component makers have to be making good money to achieve this.
The ESG investment shakeup could be one of the major events of this year, and as many of the headlines in our daily report suggest, there is a lot of work to be done, whether it is agreeing on a common set of measurement metrics – note the US and European differences discussed in one story – or the introduction of more empirical methods to judge whether what is labeled as an ESG investment fund is labeled correctly. There is also the issue of comparable disclosures, especially for companies in complex industries. It is interesting to note that in many analyses we see around carbon footprint or greenhouse gas emissions, and the potential routes to and cost of abatement, the chemical industry is omitted, except for ethanol and hydrogen. This is despite the industry accounting for 15% of the non-power emissions in the US industrial sector (similar in size to refineries). We believe that this is because the complexity of the industry makes it hard to model, and analysts choose to exclude it because they are not sure what they are doing.