Fair Value Weather & Climate — Friday, July 31, 2026

A detailed daily look at some of the most interesting weather and climate prediction markets at ForecastEx and elsewhere.

• 1.43°F, ForecastEx ranks 1st of 12. Average error on daily highs, 7 days, 5:00 PM ET day before through 5:00 AM ET. Aviation Forecast next at 1.52°F.
• 7°F, Largest error, San Francisco high. Settled 73°F against 66°F from the National Weather Service.
• 8.0×, Best return on daily temperatures yesterday. Yes on the Charlotte low below 67° at 12¢, priced 31 hours before it resolved and 14 hours before the low itself happened, settled 66°, net of fees.
• 4°F, Widest disagreement for Saturday, Los Angeles. ForecastEx below the National Weather Service forecast on the high.
• 33%, At least one major Atlantic hurricane in August. A Yes contract at 33¢ pays 3.0× the money put in, net of fees.

• Access to live probabilities and the ability to trade is available via IBKR Prediction Markets.
• General primers on how these prediction markets work are available in the IBKR prediction markets FAQ (scroll down) and the ForecastEx FAQ.

1) San Francisco’s marine layer, and what it means for daily temperature markets

The stratus deck that sits over San Francisco International Airport on summer mornings cleared on Thursday, and the high reached 73°F against 66°F from the National Weather Service at the Wednesday afternoon lead, the largest city-average miss on the scorecard. Whether that deck clears or holds is worth several degrees at this station, and the same question is open again for Saturday, where thirteen models span 11.6°F on the high. The National Weather Service office serving the Bay Area, in its forecast discussion, describes limited patches of stratus lingering along the coast and a warming trend through Saturday, with an elevated fire weather threat across the interior hills.

2) How ForecastEx temperature markets compared with the weather models on Thursday

Below is a scorecard for the forecasts as they stood at 5:00 PM ET on Wednesday, July 29th, for the target day of Thursday, July 30th. The highs and lows are shown as separate grids below. Each grid below orders its cities by mean absolute error (MAE) for that metric, which is the average size of the miss in degrees regardless of direction, from largest to smallest. ForecastEx is scored against eleven public forecast tools throughout this letter, all listed with links in the FAQ at the end. The grids below pull out four canonical tools for illustration, the American model, the European model, the National Weather Service, and the Aviation Forecast.

San Francisco carried the largest error on highs, at 4.7°F averaged across the five systems, and the American model was the weakest system on that metric at 3.65°F against ForecastEx at 1.43°F.

The lows ranked differently, led by Philadelphia at 3.08°F in the grid above.

Postmortem on the San Francisco miss. The high reached 73°F. The National Weather Service had carried 66°F from the Wednesday afternoon lead, a 7°F miss on the cold side.

At the lead, the office’s forecast discussion expected breezy onshore winds each afternoon and lingering marine layer influence keeping coastal areas in check. By the target day it was describing generally clear skies with limited patches of stratus confined to the immediate coast. A forecast holding the marine layer over the station had nowhere to put a clear afternoon, and the high came in at the warm end of the panel.

Over the window ending Thursday, the ForecastEx prediction market records the lowest error of the twelve systems at 1.43°F on daily highs, with the Aviation Forecast second at 1.52°F.

This constitutes ongoing evidence that weather prediction markets like ForecastEx may be the most accurate short-range weather forecasts available, and the difference becomes greater as lead time decreases.

This is because a ForecastEx price is a confidence-weighted consensus of participants who can condition on every tool shown here, plus whatever additional knowledge they bring to the table at live timescales. One way to think about it is that ForecastEx is a constantly offered rewards program for anyone who can push prices and probabilities toward their true, most-calibrated values (and a penalty for those who try but fail which encourages improvement).

On average, no public tool beats ForecastEx consistently, but the section below asks the narrower question of where a single tool could potentially be used to identify edge in particular circumstances.

The most undervalued contracts for Thursday were

• Access to live probabilities and the ability to trade is available via IBKR Prediction Markets.
• General primers on how these prediction markets work are available in the IBKR prediction markets FAQ (scroll down) and the ForecastEx FAQ.

The most undervalued contract above was Yes on the Charlotte low below 67 degrees, 12 cents 31 hours before it resolved and 14 hours before the low itself arrived at 6:52 AM, for an 8.0 times return net of fees. The National Weather Service was exactly on that outcome at 66 degrees.

3) ForecastEx temperature market forecasts and prices for Saturday

The widest disagreement on the map above is the Los Angeles high, where ForecastEx sits 4.4°F below the National Weather Service forecast. Prices on the map are as of 12:40 PM ET, which is 35 to 38 hours before these contracts resolve depending on the city.

• Access to live probabilities and the ability to trade is available via IBKR Prediction Markets.
• General primers on how these prediction markets work are available in the IBKR prediction markets FAQ (scroll down) and the ForecastEx FAQ.

If the tool that was closest for each market on Thursday proves exactly right, the most undervalued contract on the high side is No on the Minneapolis high above 81 degrees at 10 cents, a 9.5 times return net of fees, with the National Blend of Models predicting 80. On the low side it is No on the Oklahoma City low below 73 degrees at 15 cents, a 6.5 times return, with the National Weather Service predicting 73.

Temperature Market of the Day, San Francisco

The highlighted market for Saturday is San Francisco (KSFO)‘s daily high temperature contract. The figure above runs through the end of Saturday, showing two independent hourly forecasts, each model’s forecast high and low for the contract day, and the most recent high ladder at right.

Thirteen models span 11.6°F on Saturday’s high, from the German model at 78.8 down to the Japanese model at 67.2, and the middle half of them sit 2.7°F apart. The reason for the large spread is uncertainty in the same marine layer behavior that decided Thursday.

4) Atlantic hurricane forecast contracts, still no hurricanes

The Bahamas lead the major hurricane landfall map at 10.9%, equivalent to a Yes contract at 11 cents, with Florida just behind at 10.4%. The probability of a Category 4 United States landfall (by November 30th) stands at 7.9%, which represents the seasonal forecasts and is not influenced by any current storm. The season’s two named storms, Arthur at 46 mph and Bertha at 58 mph, both peaked as tropical storms.

The probability of a major hurricane making landfall within 50 miles of Miami-Dade, Florida currently stands at around 4.7%. Thus, a purchase of a “Yes” at 5 cents can be thought of as an analog to parametric insurance, which pays out when a measured weather parameter crosses a threshold, with no claims process and no need to prove a loss. In this case it would pay 18X of the purchase price.

The NOAA Climate Prediction Center’s Global Tropical Hazards Outlook covering August 5th to August 18th expects El Niño conditions to continue to suppress Atlantic tropical cyclone activity, with formation chances lower than usual over the Caribbean and the central Atlantic through that window.

Two named storms have formed against the 1.8 the season would normally have produced by now if it finishes at the total forecast by the hurricane research team at Colorado State University. On the hurricane count ladder above, Kalshi continues to price the season above ForecastEx across the strikes the two venues share, and the gap persists into the tail.

Frequently asked questions

What is a weather prediction market?

A market in which each contract pays one dollar if a stated weather outcome occurs and nothing if it does not, so the contract’s price is the market’s probability of that outcome. ForecastEx lists these on daily high and low temperatures at individual weather stations, on Atlantic named storm and hurricane counts, and on major hurricane landfall by location, among many others.

What are the four canonical forecast systems compared here?

All four commonly referenced forecast systems rely on physical numerical weather prediction models that solve the equations of the atmosphere forward in time. ECMWF (the European model) and GFS (the American model) are shown here in their raw form. Raw physical models are flexible and can handle weather situations they have never seen (they are not explicitly trained on historical data but rather adhere to the laws of physics), but forecasts apply to a relatively large discrete grid box that contains the weather station rather than the single point where the station sits, causing them to carry systemic biases relative to the stations.

The Aviation Forecast is a model output statistics system. It compares historical forecasts from physical models with what actually occurred and uses the errors to statistically correct systemic biases at the level of individual weather stations. The tradeoff is that a statistical fit is anchored in past situations and bends less readily to a genuinely unusual one. The National Weather Service’s National Digital Forecast Database is undergirded by the National Blend of Models but layers on human forecasters’ judgment, which is more flexible in dynamic weather situations but introduces subjective judgment (more on all of this here).

What are all the forecast tools used here?

• National Weather Service — the official public forecast, human judgment layered on model guidance; that judgment is subjective and can lag a fast-changing day.
• Aviation Forecast — statistically corrected to each station and strong inside a day; reaches only about 25 hours and is anchored in past situations.
• National Blend of Models — averaging many models cancels much of their individual error; a blend can be slow to commit when the models genuinely split.
• European model — consistently among the most accurate global physical models; raw grid-box output still carries station-level bias.
• American model — a global physical model updated four times a day; prone to systematic warm or cold stretches in conditions it resolves poorly.
• German model — a modern global physical model with strong mid-latitude performance; the same grid-box limitations as its peers.
• German statistical model — station-calibrated output built on multiple physical models; anchored in past relationships between forecast and outcome.
• Canadian model — an independent global physical model whose errors differ usefully from the American and European models; raw station-level accuracy is middling.
• UK model — a long-developed global physical model; coarser at United States stations than the domestic systems.
• French model — an independent global physical model that adds diversity to the panel; raw station-level accuracy trails the leaders.
• Japanese model — an independent global physical model; often the weakest of the panel on the daily-high standings, which is itself informative about model diversity.

How does a ForecastEx ladder become a single forecast temperature?

ForecastEx does not publish a single forecast temperature. It lists a ladder of contracts at different strikes, and each price is the ForecastEx probability that the day’s extreme passes that strike. Comparing ForecastEx with the other systems therefore requires converting that ladder into a central estimate. The 50 percent level is the ForecastEx implied median, so where two adjacent listed strikes bracket that crossing, the central value is interpolated between them. Where the ladder does not bracket 50 percent, because every listed strike sits far in or far out of the money, no central value is recorded and ForecastEx is left unscored rather than extrapolated beyond the quoted ladder. That reflects how the strikes happened to be listed rather than anything about forecast quality, so it should count neither for nor against ForecastEx.

Further Reading

Prediction market basics

• The Value of Climate Prediction Markets — The case for why prediction markets can represent the best collective knowledge about our energy and climate future.
• Daily High Temperature Markets at ForecastEx — how the daily temperature contracts are built and settled.

Temperature markets and energy

• Energy expenditure implications of next-day temperature forecasts — what day-ahead temperature uncertainty costs utilities, energy traders and risk managers.

Hurricane and climate contracts

• Hurricane Forecast Contracts — how the count and landfall contracts work.
• Disaster Insurance Applications of Forecast Contracts — using landfall contracts as parametric cover.
• Hurricane Forecast Contracts as a Diversifying Asset in an Investment Portfolio — correlation properties against conventional assets.
• Bundling “NO” Hurricane Landfall Forecast Contracts to Reduce Downside Risk — constructing a bundle across locations.

Climate Contracts

• Global Crop Yield Forecast Contracts (view here).
• How Quickly Will The Globe Warm? Paris Agreement Forecast Contracts (view here).
• Will the Atlantic Overturning Circulation (AMOC) Collapse? Prediction Markets Can Quantify Sentiment (view here).

About the author

Patrick T. Brown is the Head of Climate Analytics at Interactive Brokers, where his work focuses on the information discovery and risk-transfer applications of prediction markets in weather, climate, and natural disasters.

He holds a PhD in Earth and Climate Science from Duke University, a master’s degree in Meteorology and Climate Science from San Jose State University, and a bachelor’s degree in atmospheric and oceanic sciences from the University of Wisconsin, Madison. He is an adjunct faculty member (lecturer) in the Energy Policy and Climate Program at Johns Hopkins University and has conducted research at the Carnegie Institution at Stanford University, NASA JPL at Caltech, NASA Langley in Virginia, NASA Goddard in Washington, D.C., and NOAA’s GFDL at Princeton University. He has published scientific papers in Nature, PNAS, and Nature Climate Change, as well as many disciplinary journals, and his research and commentary have appeared in The New York Times, The Wall Street Journal, The Economist, CNBC, CNN, The BBC, The Washington Post, NPR, Newsweek, The Guardian, The Atlantic, Foreign Policy, and The Los Angeles Times, among other venues.