Sepulveda Basin Crime Rate Trends — Los Angeles
Sepulveda Basin is the flood-control basin behind Sepulveda Dam in the central San Fernando Valley — a 2,000-acre recreation area containing Lake Balboa, the Sepulveda Basin Wildlife Reserve, the Woodley Park golf courses, and the Sepulveda Basin Sports Complex. Almost no residential population in the polygon itself.
March 2026 was a quiet month in Sepulveda Basin. No tracked category crossed an anomaly threshold — zero signals across the full flag mix — making this one of the calmer briefings in recent months.
The 12-month volume picture is broadly lower across property and violent crime. Burglary is down 71.4% against the prior year (2 incidents vs. 7), motor vehicle theft is down 66.7% (4 vs. 12), and aggravated assault is down 51.9% (13 vs. 27). Robbery is the one exception, up 60.0% year-over-year, though the underlying counts remain small — 8 incidents in the current 12 months against 5 in the prior period.
Notable signals 0
Nothing notable surfaced this month — every category sits within normal range against its baseline.
All categories, last 24 months
Each panel: recent monthly count vs. trailing 12-month context. MoM is the most recent month vs. the one before; 12mo YoY compares the trailing year to the year before that.
What's been quietly true for a year
Spikes get attention. Sustained shifts shape policy. These are multi-quarter patterns where the past 12-month total differs meaningfully from the year before — they often precede the baseline resetting.
No sustained shifts surfaced this month.
What next month likely looks like
Forecasts trained through March 2026, with a likely range we're 95% confident the actual count will fall inside. Categories with too little recent volume — or violent categories at the neighborhood level — show no forecast and are surfaced through signals above instead. See the methodology page for the gating rules.
Aggravated Assault
Too low-volume per neighborhood for a reliable point forecast — see the rare-event and streak-break signals above instead.
Arson
Below the volume threshold for a reliable forecast — too few incidents in recent months to project from.
Burglary
Below the volume threshold for a reliable forecast — too few incidents in recent months to project from.
Homicide
Too low-volume per neighborhood for a reliable point forecast — see the rare-event and streak-break signals above instead.
Motor Vehicle Theft
Below the volume threshold for a reliable forecast — too few incidents in recent months to project from.
Other Larceny
Below the volume threshold for a reliable forecast — too few incidents in recent months to project from.
Robbery
Too low-volume per neighborhood for a reliable point forecast — see the rare-event and streak-break signals above instead.
Sexual Assault
Too low-volume per neighborhood for a reliable point forecast — see the rare-event and streak-break signals above instead.
Theft from Vehicle
Vandalism
How Sepulveda Basin compares
Peer neighborhoods picked by closest 12-month other larceny volume — a pragmatic v1 of peer matching. Demographic / housing-stock peer matching isn't built yet (we deliberately don't ingest income or race data alongside crime). Volume similarity has the right intuition: “neighborhoods experiencing comparable other larceny levels.”
Elysian Valley
13 incidents over the past 12 months — 0 below Sepulveda Basin's 13.
Open page →Mount Washington
15 incidents over the past 12 months — 2 above Sepulveda Basin's 13.
Open page →Carthay
18 incidents over the past 12 months — 5 above Sepulveda Basin's 13.
Open page →Recurring local terms (last 12 months)
Top terms in incident descriptions for Sepulveda Basin, excluding generic crime taxonomy. Useful as texture — what kinds of specifics show up here that don't show up elsewhere.
Hour-of-day, day-of-week, and seasonality
Distribution of bucketed incidents in this neighborhood across the full analysis window. Useful for routine context — shopping-strip thefts vs. late-night assaults read very differently when you can see when each typically happens.
How we built this page
Data → Anomalies → Forecast → Page
Incident data is pulled from SFPD's open dataset, mapped to 10 NIBRS-aligned categories, and aggregated to neighborhood × category × month. Anomalies are surfaced using strict thresholds (~p < 0.01). Forecasts are Prophet with low-count gating; violent categories at the neighborhood level skip the forecast and show rare-event / streak signals instead.
Spike rule: 12-mo total > baseline mean + 2.5σ AND ≥ 20 incidents AND 6-mo confirms. Drop rule: 12-mo total < baseline mean − 2.5σ AND baseline mean ≥ 20. Rare event: any incident in the last 90 days, no prior comparable in ≥ 5 years.