Bad weather forecasts are costing Aus solar $100m+ per year, finds Solstice AI report

Global market for solar forecasting to reach $80bn by 2030

MELBOURNE, Australia, Dec. 10, 2025 /PRNewswire/ -- Dr. Julian de Hoog, honorary research fellow at the University of Melbourne and the CEO of Solstice AI, has published a report on the millions of dollars lost by solar farms, rooftop solar installations, VPPs and energy traders due to inaccurate weather forecasting. The data shows that Australian solar installations are losing hundreds of millions of dollars every year, solar operators have a poor understanding of cloud cover, and the global opportunity for better forecasting technology will reach $80bn by 2030. 

Solstice AI is a climate startup that graduated from the same Energy Lab cohort as The National Renewable Network and Conry Tech. The company uses artificial intelligence to identify rooftop solar panel location, orientation and capacity across extended regions, combined with cloud movement forecasts to predict solar generation with a high degree of accuracy. This can help stakeholders in the solar / energy ecosystem make more accurate price bids, avoid forecast error penalties like Frequency Performance Payments (FPP), maximise their yields, take advantage of price spikes caused by unexpected cloud cover, and manage their exposure to market volatility.   

Key findings in the new report include: 

• Solstice AI estimates that large regions throughout Australia have ~10% more solar capacity than is recorded in official Government databases like CER and DER – used by the likes of AEMO, NEM and energy traders (based on a Solstice AI study in Queensland)
• Cloud forecast data is poorly understood and implemented in the Australian solar ecosystem. Many stakeholders use generic cloud cover forecasts, but lack a deeper understanding of cloud height, thickness, temperature, movement, moisture content and local geography, which can have a major impact on solar generation
• Across all Australian utility scale solar farms, just a 10% improvement in weather / solar forecasting accuracy would generate an extra $38 million per year in profit. Worldwide, this figure is $9.5bn 
• Battery energy storage systems make a disproportionate amount of revenue during extreme price spikes. In just one week (2% of the year) battery energy storage systems can generate more than a third (36%) of their annual revenue. The annual value of improved solar forecasting for these providers is in the hundreds of millions of dollars every year
• Solstice AI believes the global solar forecasting opportunity by 2030 on the order of AU$80 Billion per year or more, growing quickly in line with accelerating global solar energy growth

"It's no exaggeration to say that solar has already reshaped the Australian energy system, but this is just the tip of the iceberg," said Julian De Hoog, Solstice AI founder. "The financial cost of forecasting failure is already in the billions, and will reach 80bn by 2030. Every single stakeholder in the solar ecosystem can benefit from better forecasting. For solar farms, it's a route to maximising yield and market revenue. For traders and gentailers, it's an essential part of managing their portfolio's exposure to solar volatility. Market operators like AEMO need to balance supply and demand, and VPPs need to aggregate and coordinate thousands of rooftop systems. The technology coming to market today can transform solar from a variable resource into a predictable and manageable component of the energy system — a foundational requirement for the renewable energy transition."

ABOUT SOLSTICE AI

Solstice AI is an artificial intelligence company on a mission to be the world's leading solar energy generation forecast provider. It helps energy utilities, traders, and solar generation asset owners increase profits and manage their risk – in an energy market increasingly impacted by variable solar energy. Its state-of-the-art technology identifies solar generation in the region, including solar panel orientation and capacity. It also forecasts how much solar power will be generated, by accurately forecasting cloud movement and attributes, which are major factors in solar generation. By combining the two products, Solstice AI can forecast the output of individual sites, or the aggregate output of all solar PV (including all small-scale rooftop solar PV) of an entire region, such as a state or a country.

SOURCE Solstice AI