SWAT+ calibration and validation on AWS EC2 | SWATGenX

Key takeaways

• SWATGenX runs PSO (particle-swarm) calibration and validation on AWS EC2 compute-optimized instances, not on a shared queue — each job gets its own dedicated machine.
• The instance size is chosen automatically from the model: the swarm's forward runs are spread across the cores, and the box must hold enough of them in RAM to run at full parallelism.
• The pricing model is chosen automatically from run length — jobs estimated under about an hour use interruptible spot; longer jobs run on a dedicated on-demand instance that AWS cannot reclaim mid-run, so multi-hour calibrations finish through validation. If a short spot job is interrupted mid-run, SWATGenX automatically relaunches it on a non-reclaimable on-demand instance — warm-started from the last saved iteration — so an interruption costs a little time but never the run.
• You can monitor the run live on your dashboard — objective metrics and the global-best and per-particle convergence curves update every iteration — and stop it yourself at any time based on your own read of the fit; you keep the best parameters found so far.
• Every instance launches on demand and auto-terminates the moment results are fetched — no idle compute.

How a calibration job reaches AWS

1. 1
   Bundle

   Your built model plus the pinned SWAT+ engine binary are packaged into a ~32 MB bundle on the SWATGenX server.

2. 2
   Select

   The instance size is picked from the model (cores plus the RAM needed to hold the parallel swarm), and the pricing model from the estimated run length — interruptible spot for short jobs, dedicated on-demand for jobs of roughly an hour or more so they can't be reclaimed mid-run.

3. 3
   Run & monitor

   The PSO swarm runs on the box — forward runs are evaluated in parallel across the cores. Live progress streams back to your dashboard every ~20 seconds: objective metrics, the initial-stage hydrograph, and the global-best and per-particle convergence curves. You can watch the swarm converge and stop the run whenever you judge the fit is good enough — you keep the best result so far. If AWS reclaims a spot box mid-run, the job restarts automatically on an on-demand instance from the last checkpoint.

4. 4
   Fetch & terminate

   Calibrated parameters, metrics and hydrographs sync to your dashboard, then the instance terminates automatically (a shell trap guarantees it, even on error).

Instance options (c7i, us-east-1)

The instance is chosen automatically so the parallel swarm fits in memory and finishes fastest. RAM is the binding limit: each forward run needs roughly 0.5–4 GiB, so a 64 GiB box runs about 16 in parallel and a 128 GiB box about 32. Bigger swarms or big basins benefit from the larger instances.

Compute time by basin size (measured models)

Reference workload: 7-year calibration window, 32-particle swarm x 50 PSO iterations + 32 warm-up samples (1,632 forward runs).

Each row is a real SWATGenX model from the runtime sweep (engine 247e95b, NetCDF + print-filter), for a 7-year window and a 32-particle x 50-iteration PSO (1,632 forward runs) on one c7i.8xlarge. "Runs on" is the pricing model SWATGenX selects from the estimated wall time. Big basins finish faster on a larger instance or with a smaller swarm; parallelism here is capped at the 32-particle pool.

Availability and accuracy

• Cloud calibration is in preview and offered to Pro users by request — it is not yet a self-serve checkout.
• Spot capacity is not guaranteed: a short job may wait briefly for a slot, and AWS can reclaim a spot box mid-run. SWATGenX surfaces the wait on your dashboard and, on a reclaim, automatically resumes the job on a non-reclaimable on-demand instance (warm-started from the latest checkpoint) — so spot interruptions never lose work. Long jobs run on on-demand capacity from the start.
• Runtime constants were fit (R²=0.996) to a six-model sweep and translated to c7i; your exact wall time depends on basin size, channel count, the calibration window, and swarm settings.

Engine 61.0.2.61-353-g247e95b · reference instances us-east-1.