Sea-Tac Airport · KSEA
Seattle, Seattle-Tacoma International Airport
As of 2:10 pm · Thursday, August 20
Sunny
78.80°F
station reports whole-degree readings (±1°)
↑82.00°
↓59.00°
Trend
81.60°
by thu 5:10 pm
Raw local trend ±2.19°/hr
+1.36°/hr
not statistically significant right now - the error bar spans zero, so treat this as flat
Applied, after damping
41%
How much of the raw trend the model trusts, based on proximity to sunrise/peak-heat hour and current cloud/wind. Low near those turning points, since the trend is about to reverse.
Uncertainty band
78.30°–84.90° (±6.60°)
Widens when local pressure is falling (unsettled weather approaching), and independently when the marine push or offshore flow signals below are elevated - separate from the trend confidence above.
Widened: noisy local trend fit.
Last 6h + projection
6h ago
thu 5:10 pm
Conditions · last 6h
6h ago
now
The same station readings the model itself runs on - what the trend fit and the cross-station gradient network are built from. History only; the dashed projection above is temperature-specific.
Estimated hottest/coldest time of day
↑
82.00°
projected for today's peak-heat hour · est. peak ~3:59 pm
NWS hourly forecast - too far out for the local trend to be worth anything (local trend 81.6° · NWS 82.0°)
↓
59.00°
expected low tonight · est. trough ~fri 6:13 am
Confidence, from similar past days
↑79%based on 13 days with marine push steady, offshore flow steadyMAE 1.09°F, bias -0.16°F
↓85%based on 6 days with marine push steady, offshore flow steady, pressure risingMAE 0.52°F, bias +0.49°F
Measured from finalized days whose marine-push, offshore-flow and pressure-gradient state at prediction time matched today's, not one average across every day regardless of conditions (calibration_log.py). Falls back to the all-days figure until a specific combination has 5 matching days behind it - the sample count above always says which one you are looking at.
Actual so far today
↑
80.60°
recorded at 1:50 pm
station reported 27°C (whole degree), so this is ±0.9°F
↓
59.00°
recorded at 5:35 am
station reported 15°C (whole degree), so this is ±0.9°F
Yesterday
↑
83°
recorded at 4:45 pm
↓
55°
recorded at 3:25 am
final NWS climate report (CLI) - the value Kalshi settled on
Conditions
Wind
6.90 mph
Cloud cover
0%
Pressure
steady
Trend confidence
41%
Marine push
quiet
via KHQM + KORS
Offshore flow
quiet
via KELN
Trend confidence is how much the model trusts its own short-term extrapolation right now - not confidence in the readings above. It's deliberately low near sunrise or the day's peak-heat hour, since the trend is about to reverse there regardless of how strong it looks right before. Marine push (coastal/strait pressure gradient) and offshore flow (interior gap-wind gradient) are two distinguishable patterns behind Seattle temperature swings - the latter is the mechanism behind most real heat events, not just solar heating. Both are still first-pass signals, not yet calibrated against real outcomes (see calibration log).
Tomorrow's high
81.00°
~4:00 pm · reference confidence 70%*
From the NWS hourly forecast (HRRR model) - real atmospheric dynamics, not this tool's own trend/persistence guess. Reference confidence is measured from the last 28 finalized next-day predictions using this same source (calibration_log.py) - not a placeholder.
Tomorrow's low
59.00°
~6:00 am · reference confidence 78%*
From the NWS hourly forecast (HRRR model) - real atmospheric dynamics, not this tool's own trend/persistence guess. Reference confidence is measured from the last 28 finalized next-day predictions using this same source (calibration_log.py) - not a placeholder.
Kalshi · today's high market
Estimated high: 82.00°F
78° or below
79° to 80°
81° to 82°
83° to 84°
85° to 86°
87° or above
Highlighted bracket is the one this tool's own estimate falls into - not a probability call, just a quick eyeball check against the market's pricing.
Bid/ask are the current highest buy offer and lowest sell offer for that bracket (last-price is the most recent trade, which can lag). A wide gap between them usually means a thin, less reliable market.
KXHIGHTSEA-26AUG20
Kalshi · today's high market volume
25,740
contracts traded, last 24h
Dollar volume (our estimate)
≈$5,157 est.
Contract count matches Kalshi's own "Volume" figure; the dollar amount is our own estimate (contracts × that hour's average price) since Kalshi doesn't publish a dollar total directly. Applies to all four volume charts on this page (today's/tomorrow's high/low).
Kalshi · today's low market
Observed low: 59.0°F
station's own 1-minute figure from the METAR remarks - not the rounded 5-minute feed
51° or below
52° to 53°
54° to 55°
56° to 57°
58° to 59°
60° or above
Trades stay manual for now - this is a side-by-side view for a human to review, not an automated signal.
KXLOWTSEA-26AUG20
Kalshi · today's low market volume
6,722
contracts traded, last 24h
Dollar volume (our estimate)
≈$2,979 est.
Kalshi · tomorrow's high market
Estimated high: 81.00°F
78° or below
79° to 80°
81° to 82°
83° to 84°
85° to 86°
87° or above
Highlighted bracket is the one this tool's tomorrow-high estimate falls into.
KXHIGHTSEA-26AUG21
Kalshi · tomorrow's high market volume
5,816
contracts traded, last 24h
Dollar volume (our estimate)
≈$830 est.
Kalshi · tomorrow's low market
Estimated low: 59.00°F
52° or below
53° to 54°
55° to 56° thin
57° to 58°
59° to 60°
61° or above
Highlighted bracket is the one this tool's tomorrow-low estimate falls into.
KXLOWTSEA-26AUG21
Kalshi · tomorrow's low market volume
211
contracts traded, last 24h
Dollar volume (our estimate)
≈$34 est.
Next-day forecast · track record
| Forecast for | High est. | Actual | Err | Low est. | Actual | Err |
|---|---|---|---|---|---|---|
| 08-21 | 81.0 | — | pending | 59.0 | — | pending |
| 08-20 | 81.0 | 80.6 | pending | 57.0 | 59.0 | pending |
| 08-19 | 77.0 | 82.9 | -5.9 | 57.0 | 55.4 | +1.6 |
| 08-18 | 78.0 | 80.6 | -2.6 | 57.0 | 57.0 | -0.0 |
| 08-17 | 79.0 | 80.6 | -1.6 | 57.0 | 54.0 | +3.0 |
| 08-16 | 78.0 | 75.0 | +3.0 | 58.0 | 57.2 | +0.8 |
| 08-15 | 79.0 | 75.2 | +3.8 | 58.0 | 57.0 | +1.0 |
| 08-14 | 80.0 | 78.8 | +1.2 | 58.0 | 55.4 | +2.6 |
High: MAE 1.99°F, bias -0.16°F over 29 days · Low: MAE 1.23°F, bias +0.65°F over 29 days. Bias is signed forecast minus actual, so positive means the forecast ran warm. Days still in progress show pending - they are excluded from the averages, because scoring against a partial day's high is what made these numbers look twice as bad as they are.
Weekly performance · high (7 of 7 days)
| Date | Predicted | Night before | 1h before pred. | NWS 1h before | Actual | 1h before actual | Temp Δ | Time Δ | Kalshi peak vol. | Kalshi implied |
|---|---|---|---|---|---|---|---|---|---|---|
| 08-19 | 4:00pm · 80.6° | 77.0° (-6.0) | 78.8° | 77.0° | 5:35pm · 83.0° | 80.6° | -2.40 | -95 min | 8,486 @ 4:45pm | 83° (83° or above) |
| 08-18 | 4:01pm · 78.0° | 78.0° (-2.0) | 75.2° | 77.0° | 5:25pm · 80.0° | 78.8° | -2.00 | -84 min | 14,696 @ 5:15pm | 78° (78° to 79°) |
| 08-17 | 4:02pm · 79.0° | 79.0° (-1.0) | 75.2° | 77.0° | 4:35pm · 80.0° | 77.0° | -1.00 | -33 min | 8,748 @ 3:30pm | 80° (79° to 80°) |
| 08-16 | 4:03pm · 77.0° | 78.0° (+3.0) | 71.6° | 75.0° | 4:53pm · 75.0° | 72.0° | +2.00 | -50 min | 1,719 @ 4:45pm | 76° (76° or below) |
| 08-15 | 4:04pm · 78.0° | 79.0° (+4.0) | 71.6° | 76.0° | 5:40pm · 75.0° | 73.4° | +3.00 | -96 min | 978 @ 2:00pm | 78° (78° or below) |
| 08-14 | 4:05pm · 81.0° | 80.0° (+2.0) | 73.4° | 79.0° | 5:15pm · 78.0° | 75.2° | +3.00 | -70 min | 10,385 @ 5:15pm | 78° (77° to 78°) |
| 08-13 | 4:05pm · 81.0° | 81.0° (+0.0) | 78.8° | 81.0° | 3:55pm · 81.0° | 75.2° | +0.00 | +10 min ✓ | 6,636 @ 3:30pm | 80° (80° to 81°) |
Trailing 7 days, most recent first. Predictions only appear once calibration_log.py has logged them (recent addition) - actual/Kalshi columns work back further.
Weekly performance · low (7 of 7 days)
| Date | Predicted | Night before | 1h before pred. | NWS 1h before | Actual | 1h before actual | Temp Δ | Time Δ | Kalshi peak vol. | Kalshi implied |
|---|---|---|---|---|---|---|---|---|---|---|
| 08-19 | 6:11am · 55.9° | 57.0° (+2.0) | 55.4° | 57.0° | 5:45am · 55.0° | 55.4° | +0.90 | +26 min ✓ | 688 @ 3:15am | 56° (55° to 56°) |
| 08-18 | 6:09am · 57.1° | 57.0° (+0.0) | 57.2° | 57.0° | 6:53am · 57.0° | 57.9° | +0.10 | -44 min | 2,415 @ 6:45am | 56° (56° to 57°) |
| 08-17 | 6:08am · 54.0° | 57.0° (+3.0) | 53.6° | 57.0° | 6:07am · 54.0° | 55.4° | +0.00 | +0 min ✓ | 2,609 @ 6:15pm | 54° (53° to 54°) |
| 08-16 | 6:07am · 57.2° | 58.0° (+0.0) | 59.0° | 59.0° | 6:39am · 58.0° | 59.0° | -0.80 | -32 min ✓ | 903 @ 6:00am | 56° (56° to 57°) |
| 08-15 | 6:06am · 57.6° | 58.0° (+1.0) | 57.2° | 58.0° | 6:53am · 57.0° | 57.9° | +0.60 | -47 min | 2,353 @ 6:45am | 56° (56° to 57°) |
| 08-14 | 6:04am · 57.0° | 58.0° (+2.0) | 57.2° | 58.0° | 8:35am · 56.0° | 57.2° | +1.00 | -151 min | 6,294 @ 8:00am | 56° (55° to 56°) |
| 08-13 | 6:03am · 57.0° | 57.0° (+1.0) | 57.2° | 57.0° | 7:17am · 56.0° | 57.2° | +1.00 | -74 min | 10,000 @ 9:15pm | 56° (56° to 57°) |
Monthly performance · August 2026
High
Temp bias (signed)+0.07°F (19 days)
Temp MAE1.34°F
NWS bias (signed)-1.16°F (19 days)
NWS MAE1.79°F
model's MAE is 0.45°F lower (better) than NWS's this month.
Peak-time bias (signed)-38 min
Peak-time MAE55 min
Mean Kalshi peak volume8,226 contracts
Model agreed w/ Kalshi favourite (at prediction time)84% (19 days)
Low
Temp bias (signed)+0.41°F (19 days)
Temp MAE0.62°F
NWS bias (signed)+0.89°F (19 days)
NWS MAE1.21°F
model's MAE is 0.59°F lower (better) than NWS's this month.
Peak-time bias (signed)-42 min
Peak-time MAE113 min
Mean Kalshi peak volume2,420 contracts
Model agreed w/ Kalshi favourite (at prediction time)67% (18 days)
Bias/MAE use the same (predicted − actual) sign convention as the backtest above. Positive bias means the model's prediction ran warm/high or late; negative means it ran cool/low or early.
Paper trading · strategies compared
Trailing 7 days
Same-day · edge-triggered (1hr leg)
Insufficient data - only 1 bet(s) so far (need at least 5 to treat win rate/band coverage as meaningful).
Same-day · unconditional (high + low)
Simulated P&L$-1.53
Win rate57% (14 bets)
Avg. edge at entry-40 pts
Within stated uncertainty band86%
On the 7 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 2 time(s), market was closer 5 time(s).
Next-day advance · cashed out early
Positions exited early8
Realized on exit+$0.51
Avg. exit above entry4.6 cents
Avg. holding time15.0 h
Bought at the ask, sold at the bid - the spread is paid on both legs, never a mid-price fill. These gains are NOT added to any settlement P&L below: "the market re-priced in our favour" and "the forecast was right" are different claims.
Next-day advance · held to settlement
Simulated P&L$-3.00
Win rate0% (6 bets)
August 2026
Same-day · edge-triggered (1hr leg)
Simulated P&L$-3.50
Win rate0% (7 bets)
Avg. edge at entry16 pts
Within stated uncertainty band71%
On the 3 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 0 time(s), market was closer 3 time(s).
Same-day · unconditional (high + low)
Simulated P&L$-1.30
Win rate62% (16 bets)
Avg. edge at entry-45 pts
Within stated uncertainty band88%
On the 8 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 1 time(s), market was closer 7 time(s).
Next-day advance · cashed out early
Positions exited early10
Realized on exit+$0.78
Avg. exit above entry6.3 cents
Avg. holding time14.0 h
Bought at the ask, sold at the bid - the spread is paid on both legs, never a mid-price fill. These gains are NOT added to any settlement P&L below: "the market re-priced in our favour" and "the forecast was right" are different claims.
Next-day advance · held to settlement
Simulated P&L$-3.00
Win rate0% (6 bets)
Four independent decision rules, deliberately never summed into one number - each answers a different question, so a combined P&L would be the average of four experiments rather than the result of any of them. Edge-triggered bets only when the model's probability disagrees with Kalshi by at least 15 points (shown here for the 1hr leg only; the 1hr-vs-2hr comparison is its own experiment and lives in the block below). Unconditional bets the bracket the model's point estimate falls into, every day, no edge required. The two next-day advance rows are the same positions split by how they ended: bought at the ask the evening before, then either sold at the bid early because the price moved our way, or carried into settlement and scored against the actual weather. Simulated only - no real orders, ever.
Paper trading · trailing 7 days
1hr before peak
Insufficient data - only 1 bet(s) so far (need at least 5 to treat win rate/band coverage as meaningful).
2hr before peak
No simulated bets placed yet in this window.
Simulated only - no real orders placed. A bet is logged when the model's own (backtest-calibrated) probability disagrees with Kalshi's price by at least 15 points - independently at ~1hr and ~2hr before the predicted peak, so the two lead times can be compared rather than picking one upfront. Kept separate on purpose - see the two blocks below.
Low market: always-bet-the-model vs. edge-gated
Low - edge-triggered (1hr)
No simulated bets placed yet in this window.
Low - unconditional (1hr)
Simulated P&L$-0.23
Win rate71% (7 bets)
Avg. edge at entry-56 pts
Within stated uncertainty band100%
On the 3 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 0 time(s), market was closer 3 time(s).
Low market only. "Edge-triggered" is the same 15-point-disagreement bet already counted above under "1hr before peak" (isolated here to just the low side, since the block above pools high and low together); "unconditional" instead bets every single day on whichever bracket the model's own point estimate falls into, no disagreement required. Comparing the two answers whether just following the model daily beats only betting when a real mispricing shows up. High doesn't get an unconditional mode - this comparison only applies to low.
Paper trading · August 2026
1hr before peak
Simulated P&L$-3.50
Win rate0% (7 bets)
Avg. edge at entry16 pts
Within stated uncertainty band71%
On the 3 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 0 time(s), market was closer 3 time(s).
2hr before peak
No simulated bets placed yet in this window.
Low market: always-bet-the-model vs. edge-gated
Low - edge-triggered (1hr)
Simulated P&L$-2.50
Win rate0% (5 bets)
Avg. edge at entry17 pts
Within stated uncertainty band80%
On the 2 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 0 time(s), market was closer 2 time(s).
Low - unconditional (1hr)
Simulated P&L$-0.18
Win rate75% (8 bets)
Avg. edge at entry-59 pts
Within stated uncertainty band100%
On the 4 bet(s) where the model and Kalshi disagreed most: model was closer to the actual outcome 0 time(s), market was closer 4 time(s).
Seattle (Fremont) · NWS gridpoint forecast
80.6°
Sunny · KBFI, 2:10 pm
Wind
6.9 mph
Today, per NWS
↑
78.0°
forecast high ~6:00 pm
↓
66.0°
forecast low ~11:00 pm
A separate, closer-to-home comparison point - not part of the KSEA model above, and not blended into it. Sea-Tac Airport runs warmer than Fremont in summer (further from Lake Union/marine moderation), so treat these as two different microclimates. Current conditions are real observations from KBFI (Boeing Field, nearest full ASOS station - still ~5-6mi from Fremont). The high/low is NWS's own HRRR-based forecast for Fremont's actual coordinates, not this tool's in-house trend/gradient-network model - no backtesting or paper trading behind these numbers yet.